- Comp-neuro - lists.cnsorg.org

[Deadline Nov. 1st][Call for Data & Papers] 2nd International Whole Brain Architecture Workshop (Feb. 24th, 2025)

by Hiroshi Yamakawa

Dear Colleagues, << Abstract submission site is now open; data paper templates are available! >> We are pleased to announce the Second International Whole Brain Architecture Workshop, building on the remarkable success of our inaugural event. (The first online workshop, held in July 2024, attracted over 100 participants and generated significant enthusiasm in the field.) This second workshop will be held on February 24th, 2025 ( https://wba-initiative.org/en/24521/ ). Registration for presentations opens on October 20th, 2024, and we eagerly anticipate your submissions of BRA data. About This Workshop: The development of brain-inspired artificial intelligence, which aims to understand and simulate the computational functions of the brain, is a promising approach to reproducing human-like problem-solving abilities. This ambitious goal requires knowledge from diverse research fields, including neuroscience and cognitive science. Given the vast amount of knowledge needed, it is crucial to accumulate and share standardized design information as open knowledge. This workshop serves as a platform for cooperation and sharing of standardized design information (BRA data) essential for developing brain-inspired AI. Additionally, it provides an opportunity to enhance the academic value of submitted datasets through expert discussions and peer review. Why Participate: • Contribute to the cutting-edge field of brain-inspired AI • Share your research with a global audience of experts • Gain insights from interdisciplinary discussions • Potential for your work to be published on the BRA Editorial System (BRAES) https://ggle.io/6ybj • Access to standardized data paper templates to ensure high-quality submissions We invite submissions of BRA data and accompanying papers. Accepted data and papers will be published on BRAES, with paper DOIs shared on the workshop program page. We believe that this sharing and integration of brain-inspired AI design information will significantly advance the field. Date and Location (hybrid): • Date: February 24th, 2025 (Monday) • Venue: Tokyo, Japan (on-site) and online (details TBA) Important Dates: • BRA Data submission opens: October 20th, 2024 (JST) • Paper abstract submission deadline: November 1st, 2024 (JST) • BRA Data submission deadline: December 20th, 2024 (JST) • Full Paper submission deadline: January 4th, 2025 (JST) • Completed BRA Data submission deadline: January 4th, 2025 (JST) • Paper notification: January 24th, 2025 (JST) New Updates: The submission site for data paper abstracts is now open and accessible at https://ggle.io/79e3 The data paper template is now available for download at https://ggle.io/79e5 For detailed submission guidelines, please visit: https://wba-initiative.org/en/24521/ We look forward to welcoming you and your colleagues to present data and papers and to engage in stimulating discussions that will shape the future of brain-inspired AI. If you have any questions, please don't hesitate to contact the Workshop organizers at bra-support(a)wba-initiative.org. Join us in advancing the frontier of brain-inspired artificial intelligence! Best regards, BRA Support Team

Oct. 22, 2024

Re: Some scientific history that I experienced relevant to the recent Nobel Prizes to Hopfield and Hinton

by Grossberg, Stephen

Dear Sara, I reply below to your claims. From: Sara A. Solla <sasolla(a)gmail.com> Date: Monday, October 21, 2024 at 5:12 PM To: Grossberg, Stephen <steve(a)bu.edu> Cc: André Fabio Kohn via Comp-neuro <comp-neuro(a)lists.cnsorg.org>, Stephen Grossberg <steve(a)cns.bu.edu> Subject: Re: [Comp-neuro] Re: Some scientific history that I experienced relevant to the recent Nobel Prizes to Hopfield and Hinton You don't often get email from sasolla(a)gmail.com. Learn why this is important<https://aka.ms/LearnAboutSenderIdentification> Stephen, You have been complaining about not getting enough credit since I first met you in the mid 1980s. That is not true. You refer to publishing before Hopfield's 1984 paper. You deliberately ignore his 1982 paper, which received 27946 citations: Neural networks and physical systems with emergent collective computational abilities, JJ Hopfield PNAS, April 15, 1982, 79 (8) 2554-2558 My post was originally on a web site with strict word limits. That is why I mentioned Hopfield’s 1984 article, but not his 1982 article. Section 6 of my 1988 review article: Grossberg, S. (1988) Nonlinear neural networks: Principles, mechanisms, and architectures. Neural Networks, 1 , 17-61. https://sites.bu.edu/steveg/files/2016/06/Gro1988NN.pdf reviews Binary, Linear, and Continuous-Nonlinear classical neural network models by many authors. This article has been cited 2410 times. Section 6 shows that the 1982 equation that Hopfield used is a variant of the 1943 McCulloch-Pitts model. The Liapunov function for it is just a discrete version of the Liapunov function for the Additive Model. In contrast, the 1971 student paper you mentioned received 118 citations. I assume that you mean: Grossberg, S. (1971). Embedding fields: Underlying philosophy, mathematics, and applications to psychology, physiology, and anatomy. Journal of Cybernetics, 1, 28-50. https://sites.bu.edu/steveg/files/2016/06/Gro1971JoC.pdf This was a review article published in a journal that ceased to exist in 1980 (see below) and thus could not be searched well by Google, which began in 1998. The article discussed Generalized Additive Models (see its Section 6). I was able to get articles published proving global limit and oscillation theorems for Generalized Additive Models in the Proceedings of the National Academy of Sciences between 1967 and 1971; e.g., Grossberg, S. (1971). Pavlovian pattern learning by nonlinear neural networks. Proceedings of the National Academy of Sciences, 68, 828-831. https://sites.bu.edu/steveg/files/2016/06/Gro1971ProNatAcaSci.pdf See Equations 1, 2, 3, and 4 etc. Your 1983 paper with Michael Cohen in IEEE Transaction of Man, Systems, and Cybernetics was received on August 1, 1982, several months after the 1982 paper by Hopfeld had appeared in print. You did get a good number of citations on this paper, 3344, but not as good as 27946. Michael Cohen and I tried to submit it to the Journal of Cybernetics in 1980. But there was a glitch in the submission process due to the fact that the Journal of Cybernetics unexpectedly stopped publishing that year and our article got lost in the shuffle, unknown to us for a while. We resubmitted in 1982, which is why it was published in 1983. Our results pre-dated Hopfield 1982 and 1984 by two years. About the difference in citations: There is a difference between discovery and marketing. I was told that Hopfield knew about my work before and with Michael Cohen before he went around the country lecturing about work that we had previously published, without citation. You mention a 1982 paper with Michael Cohen; I have not been able to find it. I think that was a typo. Michael published the following article in 1992: Cohen, M. A. (1992). The construction of arbitrary stable dynamics in nonlinear neural networks. Neural Networks, 5, 83 – 103. https://www.sciencedirect.com/science/article/abs/pii/S0893608005800085 Here is the Abstract: “In this paper, two methods for constructing systems of ordinary differential equations realizing any fixed finite set of equilibria in any fixed finite dimension are introduced; no spurious equilibria are possible for either method. By using the first method, one can construct a system with the fewest number of equilibria, given a fixed set of attractors. Using a strict Lyapunov function [boldface mine] for each of these differential equations, a large class of systems with the same set of equilibria is constructed. A method of fitting these nonlinear systems to trajectories is proposed. In addition, a general method which will produce an arbitrary number of periodic orbits of shapes of arbitrary complexity is also discussed. A more general second method is given to construct a differential equation which converges to a fixed given finite set of equilibria. This technique is much more general in that it allows this set of equilibria to have any of a large class of indices which are consistent with the Morse Inequalities. It is clear that this class is not universal, because there is a large class of additional vector fields with convergent dynamics which cannot be constructed by the above method. The easiest way to see this is to enumerate the set of Morse indices which can be obtained by the above method and compare this class with the class of Morse indices of arbitrary differential equations with convergent dynamics. The former set of indices are a proper subclass of the latter, therefore, the above construction cannot be universal. In general, it is a difficult open problem to construct a specific example of a differential equation with a given fixed set of equilibria, permissible Morse indices, and permissible connections between stable and unstable manifolds. A strict Lyapunov function is given for this second case as well. This strict Lyapunov function [boldface mine] as above enables construction of a large class of examples consistent with these more complicated dynamics and indices. The determination of all the basins of attraction in the general case for these systems is also difficult and open.” I have never heard anybody referring to you as 'the father of AI'. As an acolyte of Hopfield, you wouldn’t. What I do remember is a visit to your group at BU many, many years ago - in the late 80s or early 90s. I was amazed at finding out that you closely supervised every word in every slide that anybody in your group was allowed to show when invited to give a talk. Everybody was under a lot of pressure to 'stay on message', where the 'message' was your view on things. I had never encountered a scientific group run as a cult. It made an impression, but not a positive one. So much for training over 100 people - by teaching them not to think by themselves. You describe my devoted teaching as something ugly, even ad hominem. When I was a student, no one told me how to write an article or how to prepare and give a talk or poster. I developed a method to enable my students to grow intellectually and become independent scholars. When I started working with a new PhD student or postdoc, we discussed what topics would potentially interest them. Then we read hundreds of psychological and neurobiological articles together about that topic and began to discuss the results in them. For students interested in engineering and AI, we studied all the methods that were available to solve problems in a targeted problem domain. I encouraged my students to advance their own concepts about what might be the underlying mechanisms that generated an article’s data or benchmarks. Because we studied large amounts of data, favorite concepts often hit a brick wall and had to be discarded. We developed a modeling method that I like to call the Method of Minimal Anatomies. See Figure 2.37 in my 2021 Magnum Opus https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552 This Method is just Occam’s Razor applied to neural networks. As the Figure summarizes, it “Operationalizes the proper level of abstraction” and “that you cannot ‘derive a brain’ in one step”. Our models have been getting incrementally developed in a principled way to the present time. Your statement that “the message was your [my] view on things” is the opposite of how we worked. And how would you know? You were not there. The proof of the pudding is that all my students got positions that they wanted after they earned their PhD’s with me. I was also told by multiple famous scientists that our department sent them their best postdoctoral fellows. In fact, various major labs would contact me to let me know that they had an open position and asked if one of my students was about to graduate. My students have gone on to successful careers after their postdocs and other first post-PhD positions. Around half of them went into academe, and the other half into engineering, technology, and AI. Groups of us have periodically gotten together for happy social events, either at international conferences or in the Boston area. And they sent me information about their accomplishments and growing families for many years. As for back-propagation, this is not what Hinton is cited for in the Nobel Prize citation. It is for the Boltzmann machine. Yes, I know that, and I have also noted that my PhD student, James Williamson, developed statistical neural network models that did not have problems related to deep Learning. I have elsewhere noted that: Restricted Boltzmann Machines (RBMS) also have analogs in the Adaptive Resonance Theory (ART) family of models, but without the problems that follow from using variants of Deep Learning. Here are two of them, both developed by my PhD student, James R. Williamson: Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps https://www.sciencedirect.com/science/article/pii/0893608095001158 A Constructive, Incremental Learning Network for Mixture Modeling and Classification http://techlab.bu.edu/files/resources/articles_tt/A%20constructive,%20incre… Finally, I always wondered: If ART solves all problems, why are there ML/AI problems that remain to be solved? I would never claim that. I have always taught that science is never done. See the Method of Minimal Anatomies. The fact that you can even think that about my work shows, sad to say, how biased you have become. On Mon, Oct 21, 2024 at 7:49 AM Grossberg, Stephen via Comp-neuro <comp-neuro(a)lists.cnsorg.org<mailto:comp-neuro@lists.cnsorg.org>> wrote: Dear Comp-neuro colleagues, Here are some short summaries of the history of neural network discoveries, as I experienced it, that are relevant to the recent Nobel Prizes to Hopfield and Hinton: ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++THETHE THE NOBEL PRIZES IN PHYSICS TO HOPFIELD AND HINTON FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HOPFIELD Here I summarize my concerns about the Hopfield award. I published articles in 1967 – 1972 in the Proceedings of the National Academy of Sciences that introduced the Additive Model that Hopfield used in 1984. My articles proved global theorems about the limits and oscillations of my Generalized Additive Models. See sites.bu.edu/steveg<http://sites.bu.edu/steveg> for these articles. For example: Grossberg, S. (1971). Pavlovian pattern learning by nonlinear neural networks. Proceedings of the National Academy of Sciences, 68, 828-831. https://lnkd.in/emzwx4Tw This article illustrates that my mathematical results were part of a research program to develop biological neural networks that provide principled mechanistic explanations of psychological and neurobiological data. Later, Michael Cohen and I published a Liapunov function that included the Additive Model and generalizations thereof in 1982 and 1983 before Hopfield (1984) appeared. For example, Cohen, M.A. and Grossberg, S. (1983). Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transactions on Systems, Man, and Cybernetics, SMC-13, 815-826. https://lnkd.in/eAFAdvbu I was told that Hopfield knew about my work before he published his 1984 article, without citation. Recall that I started my neural networks research in 1957 as a Freshman at Dartmouth College. That year, I introduced the biological neural network paradigm, as well as the short-term memory (STM), medium-term memory (MTM), and long-term memory (LTM) laws that are used to this day, including in the Additive Model, to explain data about how brains make minds. See the review in https://lnkd.in/gJZJtP_W . When I started in 1957, I knew no one else who was doing neural networks. That is why my colleagues call me the Father of AI. I then worked hard to create a neural networks community, notably a research center, academic department, the International Neural Network Society, the journal Neural Networks, multiple international conferences on neural networks, and Boston-area research centers, while training over 100 gifted PhD students, postdocs, and faculty to do neural network research. See the Wikipedia page. That is why I did not have time or strength to fight for priority of my models. Recently, I was able to provide a self-contained and non-technical overview and synthesis of some of my scientific discoveries since 1957, as well as explanations of the work of many other scientists, in my 2021 Magnum Opus Conscious Mind, Resonant Brain: How Each Brain Makes a Mind https://lnkd.in/eiJh4Ti ++++++++++++++++++++++++++++++++++++++++++++++++++++ THE NOBEL PRIZES IN PHYSICS TO HOPFIELD AND HINTON FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HINTON Here I summarize my concerns about the Hinton award. Many authors developed Back Propagation (BP) before Hinton; e.g., Amari (1967), Werbos (1974), Parker (1982), all before Rumelhart, Hinton, & Williams (1986). BP has serious computational weaknesses: It is UNTRUSTWORTHY (because it is UNEXPLAINABLE). It is UNRELIABLE (because it can experience CATASTROPHIC FORGETTING. It should thus never be used in financial or medical applications. BP learning is also SLOW and uses non-biological NONLOCAL WEIGHT TRANSPORT. See Figure, right column, top. In 1988, I published 17 computational problems of BP: https://lnkd.in/erKJvXFA BP gradually grew out of favor because other models were better. Later, huge online databases and supercomputers enabled Deep Learning to use BP to learn. My 1988 article contrasted BP with Adaptive Resonance Theory (ART) which I first published in 1976: https://lnkd.in/evkfq22G See Figure, right column, bottom. ART never had BP’s problems. ART is now the most advanced cognitive and neural theory that explains HOW HUMANS LEARN TO ATTEND, RECOGNIZE, and PREDICT events in a changing world. ART also explains and simulates data from hundreds of psychological and neurobiological experiments. In 1980, I derived ART from a THOUGHT EXPERIMENT about how ANY system can AUTONOMOUSLY learn to correct predictive errors in a changing world: https://lnkd.in/eGWE8kJg The thought experiment derives ART from a few facts of life that do not mention mind or brain. ART is thus a UNIVERSAL solution of the problem of autonomous error correction in a changing world. That is why ART models can be used in designs for AUTONOMOUS ADAPTIVE INTELLIGENCE in engineering, technology, and AI. ART also proposes a solution of the classical MIND-BODY PROBLEM: HOW, WHERE in our brains, and WHY from a deep computational perspective, we CONSCIOUSLY SEE, HEAR, FEEL, and KNOW about the world, and use our conscious states to PLAN and ACT to realize VALUED GOALS. For details, see Conscious Mind, Resonant Brain: How Each Brain Makes a Mind https://lnkd.in/eiJh4Ti +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ _______________________________________________ Comp-neuro mailing list -- comp-neuro(a)lists.cnsorg.org<mailto:comp-neuro@lists.cnsorg.org> Mailing list webpage (to subscribe or view archives): https://www.cnsorg.org/comp-neuro-mailing-list To contact admin/moderators, send an email to: comp-neuro-owner(a)lists.cnsorg.org<mailto:comp-neuro-owner@lists.cnsorg.org> To unsubscribe, send an email to comp-neuro-leave(a)lists.cnsorg.org<mailto:comp-neuro-leave@lists.cnsorg.org>

Oct. 21, 2024

Re: Some scientific history that I experienced relevant to the recent Nobel Prizes to Hopfield and Hinton

by Sara A. Solla

Stephen, You have been complaining about not getting enough credit since I first met you in the mid 1980s. You refer to publishing before Hopfield's 1984 paper. You deliberately ignore his 1982 paper, which received 27946 citations: Neural networks and physical systems with emergent collective computational abilities, JJ Hopfield PNAS, April 15, 1982, 79 (8) 2554-2558 In contrast, the 1971 student paper you mentioned received 118 citations. Your 1983 paper with Michael Cohen in IEEE Transaction of Man, Systems, and Cybernetics was received on August 1, 1982, several months after the 1982 paper by Hopfeld had appeared in print. You did get a good number of citations on this paper, 3344, but not as good as 27946. You mention a 1982 paper with Michael Cohen; I have not been able to find it. I have never heard anybody referring to you as 'the father of AI'. What I do remember is a visit to your group at BU many, many years ago - in the late 80s or early 90s. I was amazed at finding out that you closely supervised every word in every slide that anybody in your group was allowed to show when invited to give a talk. Everybody was under a lot of pressure to 'stay on message', where the 'message' was your view on things. I had never encountered a scientific group run as a cult. It made an impression, but not a positive one. So much for training over 100 people - by teaching them not to think by themselves. As for back-propagation, this is not what Hinton is cited for in the Nobel Prize citation. It is for the Boltzmann machine. Finally, I always wondered: If ART solves all problems, why are there ML/AI problems that remain to be solved? On Mon, Oct 21, 2024 at 7:49 AM Grossberg, Stephen via Comp-neuro < comp-neuro(a)lists.cnsorg.org> wrote: > Dear Comp-neuro colleagues, > > > > Here are some short summaries of the history of neural network > discoveries, as I experienced it, that are relevant to the recent Nobel > Prizes to Hopfield and Hinton: > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++THETHE THE NOBEL > PRIZES IN PHYSICS TO HOPFIELD AND HINTON > FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HOPFIELD > > Here I summarize my concerns about the Hopfield award. > > I published articles in 1967 – 1972 in the Proceedings of the National > Academy of Sciences that introduced the Additive Model that Hopfield used > in 1984. My articles proved global theorems about the limits and > oscillations of my Generalized Additive Models. See sites.bu.edu/steveg for > these articles. > > For example: > > Grossberg, S. (1971). Pavlovian pattern learning by nonlinear neural > networks. Proceedings of the National Academy of Sciences, 68, 828-831. > https://lnkd.in/emzwx4Tw > > This article illustrates that my mathematical results were part of a > research program to develop biological neural networks that provide > principled mechanistic explanations of psychological and neurobiological > data. > > Later, Michael Cohen and I published a Liapunov function that included the > Additive Model and generalizations thereof in 1982 and 1983 before Hopfield > (1984) appeared. > > For example, > > Cohen, M.A. and Grossberg, S. (1983). Absolute stability of global pattern > formation and parallel memory storage by competitive neural networks. IEEE > Transactions on Systems, Man, and Cybernetics, SMC-13, 815-826. > https://lnkd.in/eAFAdvbu > > I was told that Hopfield knew about my work before he published his 1984 > article, without citation. > > Recall that I started my neural networks research in 1957 as a Freshman at > Dartmouth College. > > That year, I introduced the biological neural network paradigm, as well as > the short-term memory (STM), medium-term memory (MTM), and long-term memory > (LTM) laws that are used to this day, including in the Additive Model, to > explain data about how brains make minds. > > See the review in https://lnkd.in/gJZJtP_W . > > When I started in 1957, I knew no one else who was doing neural networks. > That is why my colleagues call me the Father of AI. > > I then worked hard to create a neural networks community, notably a > research center, academic department, the International Neural Network > Society, the journal Neural Networks, multiple international conferences on > neural networks, and Boston-area research centers, while training over 100 > gifted PhD students, postdocs, and faculty to do neural network research. > See the Wikipedia page. > > That is why I did not have time or strength to fight for priority of my > models. > > Recently, I was able to provide a self-contained and non-technical > overview and synthesis of some of my scientific discoveries since 1957, as > well as explanations of the work of many other scientists, in my 2021 > Magnum Opus > > Conscious Mind, Resonant Brain: How Each Brain Makes a Mind > > https://lnkd.in/eiJh4Ti > > ++++++++++++++++++++++++++++++++++++++++++++++++++++ > > THE NOBEL PRIZES IN PHYSICS TO HOPFIELD AND HINTON > FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HINTON > > Here I summarize my concerns about the Hinton award. > > Many authors developed Back Propagation (BP) before Hinton; e.g., Amari > (1967), Werbos (1974), Parker (1982), all before Rumelhart, Hinton, & > Williams (1986). > > BP has serious computational weaknesses: > > It is UNTRUSTWORTHY (because it is UNEXPLAINABLE). > > It is UNRELIABLE (because it can experience CATASTROPHIC FORGETTING. > > It should thus never be used in financial or medical applications. > > BP learning is also SLOW and uses non-biological NONLOCAL WEIGHT TRANSPORT. > > See Figure, right column, top. > > In 1988, I published 17 computational problems of BP: > https://lnkd.in/erKJvXFA > > BP gradually grew out of favor because other models were better. > > Later, huge online databases and supercomputers enabled Deep Learning to > use BP to learn. > > My 1988 article contrasted BP with Adaptive Resonance Theory (ART) which I > first published in 1976: > https://lnkd.in/evkfq22G > > See Figure, right column, bottom. > > ART never had BP’s problems. > > ART is now the most advanced cognitive and neural theory that explains HOW > HUMANS LEARN TO ATTEND, RECOGNIZE, and PREDICT events in a changing world. > > > ART also explains and simulates data from hundreds of psychological and > neurobiological experiments. > > In 1980, I derived ART from a THOUGHT EXPERIMENT about how ANY system can > AUTONOMOUSLY learn to correct predictive errors in a changing world: > https://lnkd.in/eGWE8kJg > > The thought experiment derives ART from a few facts of life that do not > mention mind or brain. > > ART is thus a UNIVERSAL solution of the problem of autonomous error > correction in a changing world. > > That is why ART models can be used in designs for AUTONOMOUS ADAPTIVE > INTELLIGENCE in engineering, technology, and AI. > > ART also proposes a solution of the classical MIND-BODY PROBLEM: > > HOW, WHERE in our brains, and WHY from a deep computational perspective, > we CONSCIOUSLY SEE, HEAR, FEEL, and KNOW about the world, and use our > conscious states to PLAN and ACT to realize VALUED GOALS. > > For details, see > > Conscious Mind, Resonant Brain: How Each Brain Makes a Mind > > https://lnkd.in/eiJh4Ti > > > +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ > > > _______________________________________________ > Comp-neuro mailing list -- comp-neuro(a)lists.cnsorg.org > Mailing list webpage (to subscribe or view archives): > https://www.cnsorg.org/comp-neuro-mailing-list > > To contact admin/moderators, send an email to: > comp-neuro-owner(a)lists.cnsorg.org > To unsubscribe, send an email to comp-neuro-leave(a)lists.cnsorg.org >

Oct. 21, 2024

[Jobs] Postdoc Available in Theoretical Neuroscience

by Michael Furlong

Job Ad – Postdoctoral Researcher in Theoretical Neuroscience Prof Chris Eliasmith, who holds the Canada Research Chair in Theoretical Neuroscience and heads the Computational Neuroscience Research Group (CNRG) in the Centre for Theoretical Neuroscience (CTN) at the University of Waterloo, is seeking a postdoctoral researcher in Theoretical Neuroscience for a fixed-term appointment. Description: The postdoctoral position will be hosted in the CNRG, with a principal focus on neural modeling to build the next version of the Spaun brain model, the world’s largest functional brain model. The project integrates spiking deep neural networks, motor control, probabilistic inference, navigation, perception and cognition to develop a state-of-the-art, large-scale, spiking, whole-brain model. Applicants should have a PhD, with demonstrated skills in at least one of those areas and a willingness to learn about the others. This project leverages the CNRG’s existing expertise in using neural networks for large-scale brain modeling, originally demonstrated in 2012 with the first version of Spaun. A subsequent version in 2018 significantly extended performance. The latest version currently being built by the CNRG will again break new barriers in the scale and sophistication of whole brain models. Unlike past models, it will be embedded in a sophisticated 3D environment, yet retain the ability to perform a wide variety of tasks, from simple perceptual and motor tasks to challenging intelligence tests. Overall, the long-term goal of the project is to advance the state-of-the-art in large-scale brain models. Additional Information: The successful applicant will be housed in the vibrant Centre for Theoretical Neuroscience (CTN), which includes 7 core and 7 affiliated labs focussed on neural modeling and improving our basic understanding of neural computation. The CTN hosts monthly seminars, a yearly ‘Brain Day’ event, a summer school, and regular social activities. The position is for a fixed term of one year, eight months, with extensions contingent on performance and securing additional funding. Salary is $45,000 - 65,000 CAD per year. To apply, please send a full CV, 3 references and cover letter explaining your background and fit for the job to: Dr. Chris Eliasmith at celiasmith(a)uwaterloo.ca.

Oct. 21, 2024

Re: "Experienced" history of Neural Networks

by James Bower

argg I am sorry, typing too fast Could you change: Any equally interesting conflict I witnessed first hand (with no horse in the race), which even at that time was full of similar claims of precedence. I could tell that story too, but instead, I will simply say that Stephen's recent posting made me a bit nostalgic for the days when you were either were in the “email from Stephen claiming prescience club” or not - I thankfully never was. To An equally interesting conflict I witnessed first hand (with no horse in the race), which even at that time was full of similar claims of precedence. I could tell that story too, but instead, I will simply say that Stephen's recent posting made me a bit nostalgic for the days when you were either in the “email from Stephen claiming prescience club” or not - I thankfully never was. Or I can resubmit Sorry for the extra work Jim Dr. James M. Bower Ph.D. 541-499-7502 Simulating a 17th century landed gentry scientist. Also: Affiliate Professor of Biology Southern Oregon University Visiting Professor of Computational Neuroscience Biocomputation Research Group School of Physics, Engineering and Computer Science University of Hertfordshire, UK Linked in <https://www.linkedin.com/in/james-m-bower-130163/> Wikipedia <https://en.wikipedia.org/wiki/James_M._Bower> > On Oct 21, 2024, at 11:15 AM, James Bower <bowerj(a)sou.edu> wrote: > > Any equally interesting conflict I witnessed first hand (with no horse in the race), which even at that time was full of similar claims of precedence. > > I could tell that story too, but instead, I will simply say that Stephen's recent posting made me a bit nostalgic for the days when you were either were in the “email from Stephen claiming prescience club” or not - I thankfully never was.

Oct. 21, 2024

Re: "Experienced" history of Neural Networks

by James Bower

opps, Here is the post with a spelling error corrected. Thank you Jim Being historical myself, I thought I might be appropriate for me to respond briefly to Stephen Grossberg’s recent personal recounting and retelling of history. To Witt, I sometimes, for fun, refer to myself as the pet neurobiologist in the early days of the neural network movement. Here is a recent semi-autobiographical (and thus of course certainly somewhat biased) account of those early days I was recently asked to write, which includes how the CNS meeting (as well as this mailing list) emerged from those days. https://www.researchgate.net/publication/365925517_NIPS_NeurIPS_and_Neurosc… (PDF) (NIPS) NeurIPS and Neuroscience: A personal historical perspective researchgate.net https://www.researchgate.net/publication/365925517_NIPS_NeurIPS_and_Neurosc… Not included in that account where the other abundant political circumstances surrounding the re-emergence of neural networks, including for example, the revelry between the NIPS meeting and the “International Neural Network Society” and their annual meeting referred to in Stephen Grossberg’s recent post. Any equally interesting conflict I witnessed first hand (with no horse in the race), which even at that time was full of similar claims of precedence. I could tell that story too, but instead, I will simply say that Stephen's recent posting made me a bit nostalgic for the days when you were either were in the “email from Stephen claiming prescience club” or not - I thankfully never was. Anyway, for those interested, from my understanding I think this is a pretty good and balanced history of neural networks. https://en.wikipedia.org/wiki/History_of_artificial_neural_networks https://en.wikipedia.org/wiki/History_of_artificial_neural_networks What should be clear from that history, and as also mentioned by Stephen, much of the algorithmic basis for ‘machine learning’ today are based on work done many years ago and therefore that most of the recent innovation in the field is not algorithmic but implementation, given faster and faster computers, cheaper and cheaper memory, and massive amounts of data. Given that, very tricky to assign ‘father or’ or for that matter ‘godfather of’ either. :-) In that light however, one other thing to say, which I could say a lot more about - as will almost certainly be clear in John Hopfield’s Nobel lecture, John was never much interested in the AI implications of his work. From the time I meet him through the rest of his career, he was focused on using the tools he had as a condensed matter physicist to explore questions in biology. In my experience at the time, John was almost uniquely committed to actually understanding the biology, rather than simply imposing his will upon it. That said, there is no question and as I witnessed it myself, publication of “The Hopfield Network” in 1981, re-ignited interest in an approach to AI that had been strongly resisted by the dons of the field at that time, precisely because it was not “explainable” in the then desired sense. Put another way, the role of the engineer in self-learning networks was not to impose their own predisposed assumptions about how to solve a particular problem (sometimes then, unfortunately extended to claims about how the nervous system works), but instead to construct a system that found a solution to the problem. Because of its success machine learning has now become the dominant paradigm in real world AI. But, it is now also increasingly being used as a tool to understand the brain. Too long a discussion for that here, but I have serious concerns about those efforts. In fact, I am giving at talk this week at the University of Oregon on a recent example in the neurobiology of olfaction. It is being webcast, so if anyone is interested, email me and I can send you the URL. In summary then, there is no question in my mind that John Hopfield’s contribution was unique and deserving of the acclaim he is now receiving - but I have to say I feel even better about his award because he never sought it, or expected it, or campaigned to get it, and in fact, is being rewarded for a consequence of his work that was never the real focus of his efforts. Good for you John. Respectfully, Jim Bower Dr. James M. Bower Ph.D. 541-499-7502 Simulating a 17th century landed gentry scientist. Also: Affiliate Professor of Biology Southern Oregon University Visiting Professor of Computational Neuroscience Biocomputation Research Group School of Physics, Engineering and Computer Science University of Hertfordshire, UK Linked in <https://www.linkedin.com/in/james-m-bower-130163/> Wikipedia <https://en.wikipedia.org/wiki/James_M._Bower> > On Oct 21, 2024, at 11:10 AM, James Bower <bowerj(a)sou.edu> wrote: > > Being historical myself, I thought I might be appropriate for me to respond briefly to Stephen Grossberg’s recent personal recounting and retelling of history. > > To Witt, I sometimes, for fun, refer to myself as the pet neurobiologist in the early days of the neural network movement. > > Here is a recent semi-autobiographical (and thus of course cretainly somewhat biased) account of those early days I was recently asked to write, which includes how the CNS meeting (as well as this mailing list) emerged from those days. > > https://www.researchgate.net/publication/365925517_NIPS_NeurIPS_and_Neurosc… > > Not included in that account where the other abundant political circumstances surrounding the re-emergence of neural networks, including for example, the revelry between the NIPS meeting and the “International Neural Network Society” and their annual meeting referred to in Stephen Grossberg’s recent post. > > Any equally interesting conflict I witnessed first hand (with no horse in the race), which even at that time was full of similar claims of precedence. > > I could tell that story too, but instead, I will simply say that Stephen's recent posting made me a bit nostalgic for the days when you were either were in the “email from Stephen claiming prescience club” or not - I thankfully never was. > > Anyway, for those interested, from my understanding I think this is a pretty good and balanced history of neural networks. > > https://en.wikipedia.org/wiki/History_of_artificial_neural_networks > > What should be clear from that history, and as also mentioned by Stephen, much of the algorithmic basis for ‘machine learning’ today are based on work done many years ago and therefore that most of the recent innovation in the field is not algorithmic but implementation, given faster and faster computers, cheaper and cheaper memory, and massive amounts of data. Given that, very tricky to assign ‘father or’ or for that matter ‘godfather of’ either. :-) > > In that light however, one other thing to say, which I could say a lot more about - as will almost certainly be clear in John Hopfield’s Nobel lecture, John was never much interested in the AI implications of his work. From the time I meet him through the rest of his career, he was focused on using the tools he had as a condensed matter physicist to explore questions in biology. In my experience at the time, John was almost uniquely committed to actually understanding the biology, rather than simply imposing his will upon it. > > That said, there is no question and as I witnessed it myself, publication of “The Hopfield Network” in 1981, re-ignited interest in an approach to AI that had been strongly resisted by the dons of the field at that time, precisely because it was not “explainable” in the then desired sense. Put another way, the role of the engineer in self-learning networks was not to impose their own predisposed assumptions about how to solve a particular problem (sometimes then, unfortunately extended to claims about how the nervous system works), but instead to construct a system that found a solution to the problem. > > Because of its success machine learning has now become the dominant paradigm in real world AI. But, it is now also increasingly being used as a tool to understand the brain. Too long a discussion for that here, but I have serious concerns about those efforts. In fact, I am giving at talk this week at the university of oregon on a recent example in the neurobiology of olfaction. > > It is being webcast, so if anyone is interested, email me and I can send you the URL. > > In summary then, there is no question in my mind that John Hopfield’s contribution was unique and deserving of the acclaim he is now receiving - but I have to say I feel even better about his award because he never sought it, or expected it, or campaigned to get it, and in fact, is being rewarded for a consequence of his work that was never the real focus of his efforts. > > Good for you John. > > > Respectfully, > > Jim Bower > > > > > > Dr. James M. Bower Ph.D. > > 541-499-7502 > > Simulating a 17th century landed gentry scientist. > > Also: > > Affiliate Professor of Biology > Southern Oregon University > > Visiting Professor of > Computational Neuroscience > Biocomputation Research Group > School of Physics, Engineering and Computer Science > University of Hertfordshire, UK > > Linked in <https://www.linkedin.com/in/james-m-bower-130163/> > > Wikipedia <https://en.wikipedia.org/wiki/James_M._Bower> > > > > >

Oct. 21, 2024

Re: Some scientific history that I experienced relevant to the recent Nobel Prizes to Hopfield and Hinton

by Grossberg, Stephen

Dear Comp-neuro colleagues, Here are some short summaries of the history of neural network discoveries, as I experienced it, that are relevant to the recent Nobel Prizes to Hopfield and Hinton: ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++THETHE THE NOBEL PRIZES IN PHYSICS TO HOPFIELD AND HINTON FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HOPFIELD Here I summarize my concerns about the Hopfield award. I published articles in 1967 – 1972 in the Proceedings of the National Academy of Sciences that introduced the Additive Model that Hopfield used in 1984. My articles proved global theorems about the limits and oscillations of my Generalized Additive Models. See sites.bu.edu/steveg<http://sites.bu.edu/steveg> for these articles. For example: Grossberg, S. (1971). Pavlovian pattern learning by nonlinear neural networks. Proceedings of the National Academy of Sciences, 68, 828-831. https://lnkd.in/emzwx4Tw This article illustrates that my mathematical results were part of a research program to develop biological neural networks that provide principled mechanistic explanations of psychological and neurobiological data. Later, Michael Cohen and I published a Liapunov function that included the Additive Model and generalizations thereof in 1982 and 1983 before Hopfield (1984) appeared. For example, Cohen, M.A. and Grossberg, S. (1983). Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transactions on Systems, Man, and Cybernetics, SMC-13, 815-826. https://lnkd.in/eAFAdvbu I was told that Hopfield knew about my work before he published his 1984 article, without citation. Recall that I started my neural networks research in 1957 as a Freshman at Dartmouth College. That year, I introduced the biological neural network paradigm, as well as the short-term memory (STM), medium-term memory (MTM), and long-term memory (LTM) laws that are used to this day, including in the Additive Model, to explain data about how brains make minds. See the review in https://lnkd.in/gJZJtP_W . When I started in 1957, I knew no one else who was doing neural networks. That is why my colleagues call me the Father of AI. I then worked hard to create a neural networks community, notably a research center, academic department, the International Neural Network Society, the journal Neural Networks, multiple international conferences on neural networks, and Boston-area research centers, while training over 100 gifted PhD students, postdocs, and faculty to do neural network research. See the Wikipedia page. That is why I did not have time or strength to fight for priority of my models. Recently, I was able to provide a self-contained and non-technical overview and synthesis of some of my scientific discoveries since 1957, as well as explanations of the work of many other scientists, in my 2021 Magnum Opus Conscious Mind, Resonant Brain: How Each Brain Makes a Mind https://lnkd.in/eiJh4Ti ++++++++++++++++++++++++++++++++++++++++++++++++++++ THE NOBEL PRIZES IN PHYSICS TO HOPFIELD AND HINTON FOR MODELS THEY DID NOT DISCOVER: THE CASE OF HINTON Here I summarize my concerns about the Hinton award. Many authors developed Back Propagation (BP) before Hinton; e.g., Amari (1967), Werbos (1974), Parker (1982), all before Rumelhart, Hinton, & Williams (1986). BP has serious computational weaknesses: It is UNTRUSTWORTHY (because it is UNEXPLAINABLE). It is UNRELIABLE (because it can experience CATASTROPHIC FORGETTING. It should thus never be used in financial or medical applications. BP learning is also SLOW and uses non-biological NONLOCAL WEIGHT TRANSPORT. See Figure, right column, top. In 1988, I published 17 computational problems of BP: https://lnkd.in/erKJvXFA BP gradually grew out of favor because other models were better. Later, huge online databases and supercomputers enabled Deep Learning to use BP to learn. My 1988 article contrasted BP with Adaptive Resonance Theory (ART) which I first published in 1976: https://lnkd.in/evkfq22G See Figure, right column, bottom. ART never had BP’s problems. ART is now the most advanced cognitive and neural theory that explains HOW HUMANS LEARN TO ATTEND, RECOGNIZE, and PREDICT events in a changing world. ART also explains and simulates data from hundreds of psychological and neurobiological experiments. In 1980, I derived ART from a THOUGHT EXPERIMENT about how ANY system can AUTONOMOUSLY learn to correct predictive errors in a changing world: https://lnkd.in/eGWE8kJg The thought experiment derives ART from a few facts of life that do not mention mind or brain. ART is thus a UNIVERSAL solution of the problem of autonomous error correction in a changing world. That is why ART models can be used in designs for AUTONOMOUS ADAPTIVE INTELLIGENCE in engineering, technology, and AI. ART also proposes a solution of the classical MIND-BODY PROBLEM: HOW, WHERE in our brains, and WHY from a deep computational perspective, we CONSCIOUSLY SEE, HEAR, FEEL, and KNOW about the world, and use our conscious states to PLAN and ACT to realize VALUED GOALS. For details, see Conscious Mind, Resonant Brain: How Each Brain Makes a Mind https://lnkd.in/eiJh4Ti +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Oct. 21, 2024

Arduino for Neuroscience Workshop, Brighton, Nov 20-22th

by Mateusz Kostecki

Hello! We are happy to announce the first Cambridge Open Lab Workshop, organised in collaboration with the Open Research Technologies Hub. Learn how to apply Arduino in your research! Arduino is a powerful device that you can use to build and program thousands of devices – from weather stations, through smart house applications to drones and robots. It has also recently became a powerful tool used in laboratory – you can use it to control lasers, build automated mazes or stimulus delivery systems for behavioural experiments – and much more. It is easy to learn and doesn’t require previous experience with programming. During our workshop, you will learn everything you need to start building your own devices. We will guide you through the topics ranging from basic electronics, diodes, trough motors and servos to sensors of all types. You will learn how to use Arduino to control different research devices and synchronize them! After the workshop, you will be able to write complex Arduino programs and have a knowledge of electronics that will allow you to design devices used in your lab. Topics: - Basic electronics – from electrons to laws - Controlling devices with Arduino – diodes, motors, servos - Writing code to control lasers in optogenetic experiments - Synchronizing devices with Arduino - Sensing environment – light, temperature, and distance sensors - Wireless communication - Writing complex code in Arduino The workshop will take place at University of Sussex Library, Brighton, Nov 20-22 2024 from 9 AM to 6 PM. The cost of the workshop is GBP 150. Registration form can be found here - https://nenckiopenlab.org/arduino-cam/. The deadline for registration is Oct 30th. Best, Mateusz Kostecki -- --- Mateusz Kostecki PhD Student Knapska Laboratory Nencki Institute 02-093 Warsaw, Pasteura 3, Poland https://twitter.com/mtkostecki https://evolvingbehavior.blog/

Oct. 21, 2024

COSYNE 2025: Abstract submission closes soon; Cosyne DEIA Committee

by Tomas Hromadka

==================================================== Computational and Systems Neuroscience 2025 (Cosyne) MAIN MEETING 27 March - 30 March 2025 Montreal, Canada WORKSHOPS 31 March - 01 April 2025 Mont-Tremblant, Canada www.cosyne.org ==================================================== IMPORTANT DATES Abstract submission is now open. Abstract submission deadline: 23 October 2024 11:59pm PST ---------------------------------------------------- COSYNE MEETING & WORKSHOPS ---------------------------------------------------- The annual Cosyne meeting provides an inclusive forum for the exchange of empirical and theoretical approaches to problems in systems neuroscience, in order to understand how neural systems function. The MAIN MEETING is single-track. A set of invited talks is selected by the Executive Committee, and additional talks and posters are selected by the Program Committee, based on submitted abstracts. The WORKSHOPS feature in-depth discussion of current topics of interest, in a small group setting. Cosyne topics include but are not limited to: neural basis of behavior, sensory and motor systems, circuitry, learning, neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, neuromodulation, and computation with spiking networks. We would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. When preparing an abstract, authors should be aware that not all abstracts can be accepted for the meeting. Abstracts will be selected based on the clarity with which they convey the substance, significance, and originality of the work to be presented. ---------------------------------------------------- COSYNE DEIA COMMITTEE ---------------------------------------------------- Join our 2025 DEIA Committee for @CosyneMeeting!!! The Cosyne DEIA Committee is dedicated to fostering inclusivity. We’re seeking 4 new members to contribute to the planning of the 2025 conference and drive inclusive practices. All career stages are encouraged to join (e.g., faculty, postdocs, and graduate students). For questions, contact the committee co-chairs, Luke Sjulson (@lukesjulson, luke [at] sjulsonlab.org) or Denise Cai (@denisejcai, denisecai [at] gmail.com) The application deadline is 15 November 2024. Join us and make a lasting impact—apply today! https://forms.gle/gqSNuZj2Cb68UevN9 ----------------------------------------------------- COSYNE 2025 COMMITTEES ----------------------------------------------------- ORGANIZING COMMITTEE General Chairs: Bing Brunton (U Washington) and Chandramouli Chandrasekaran (Boston U) Program Chairs: Tatiana Engel (CSHL) and Kevin Franks (Duke) Workshop Chairs: SueYeon Chung (NYU) and Guillaume Lajoie (MILA/U Montreal) Tutorial Chair: Talmo Pereira (Salk) DEIA Committee: Denise Cai (Mount Sinai) and Luke Sjulson (Albert Einstein) Undergraduate Travel Chairs: Kimberly Stachenfeld (DeepMind) and Marcelo Mattar (NYU) Fundraising Chair: Michael Long (NYU) Social Media Chair: Sabera Talukder (Caltech) Audio-Video Media Chair: Carlos Stein Brito (Chamaplimaud) Poster Design: Maja Bialon PROGRAM COMMITTEE Tatiana Engel (CSHL) Co-chair Kevin Franks (Duke) Co-chair Mikio Aoi (UCSD) Arkarup Banerjee (CSHL) Marcus Benna (UCSD) Adrian Bondy (Princeton) Timothy Buschman (Princeton) Celine Cammarata (Duke) Alex Cayco Gajic (Ecole Normale Superieure) Hannah Choi (Gatech) Benjamin Cowley (CSHL) Carina Curto (Brown) Brian DePasquale (Boston U) Sridhar Devarajan (Indian Inst Sci) Laura Driscoll (Stanford) Ann Duan (UCL) Lea Duncker (Stanford) Annegret Falkner (Princeton) Arseny Finkelstein (Tel Aviv U) Rainer Friedrich (Friedrich Miescher Institute) Juan Gallego (Imperial) Matthew Golub (U Washington) Bilal Haider (Georgia Tech) Kiah Hardcastle (Harvard) Ann Hermundstad (Janelia) Michele Insanally (U Pitt) Monika Jadi (Yale) Jonathan Kao (UCLA) Kohitij Kar (York U) Ann Kennedy (Northwestern) Guillaume Lajoie (MILA) Anna Levina (U Tubingen) Laura Lewis (MIT) Camilo Libedinsky (National U Singapore) Ashok Litwin-Kumar (Columbia) Laureline Logiaco (MIT) Emily Mace (Max Planck) Francesca Mastrogiuseppe (Champalimaud) Luca Mazzucato (U Oregon) Jorge Mejias (U Amsterdam) Jonathan Michaels (York U) Eilif Muller (U Montreal) James Murray (U Oregon) Hendrikje Nienborg (NIH) Gouki Okazawa (Chinese Acad Sci) Marino Pagan (U Edinburgh) Hannah Payne (Columbia) Talmo Pereira (Salk) Erin Rich (Mount Sinai) Ben Scott (Boston U) Nicholas Steinmetz (U Washington) Carsen Stringer (HHMI) Marie Suver (Vanderbilt) Tatjana Tchumatchenko (U Bonn) John Tuthill (U Washington) Ali Weber (Bryn Mawr) Brady Weissbourd (MIT) Alex Williams (NYU) Klaus Wimmer (CRM) Brad Wyble (Penn State) EXECUTIVE COMMITTEE Stephanie Palmer (U Chicago) Anne-Marie Oswald (U Pittsburgh) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) CONTACT meeting [at] cosyne.org ----------------------------------------------------- COSYNE MAILING LISTS ----------------------------------------------------- Please consider adding yourself to Cosyne mailing lists (groups) to receive email updates with various Cosyne-related information and join in helpful discussions. See Cosyne.org -> About-> Mailing lists for details.

Oct. 20, 2024

Post-doctoral Fellow Position available in National University of Singapore

by sc.phua＠nus.edu.sg

Postdoctoral Fellow Position in the Neuron Signaling Laboratory, NUS, Singapore We are actively seeking a Postdoctoral Fellow to join us in the following project (This position will be co-supervised with a PI from the Biomedical Engineering Department): Investigating a transcriptional role of primary cilia in striatal neural computation mediating cognitive flexibility Qualifications: The candidate should hold or is going to obtain a PhD in one of the disciplines below: - Biomedical engineering, systems neuroscience, computational neuroscience or related fields. - At least one first-author research publication in a peer-reviewed journal Skills: - Strong motivation and leadership in pursuing challenging scientific questions - An ability to work well with interdisciplinary colleagues - Experience in mentoring and training junior researchers - Excellent written and interpersonal communication skills - Good time and resource management skills Experience: - High proficiency in Python/Matlab (essential requirement) •⁠ ⁠⁠Preferably experience working with neural data (spikes, calcium imaging) at scale •⁠ ⁠⁠Some background in machine learning with strong grounding in statistical methods •⁠ ⁠⁠Familiarity with techniques for dimensionality reduction - Expertise in in vivo brain recording techniques, e.g. microendoscopy, electrophysiology, fiber photometry - Expertise in rodent stereotaxic surgeries Candidates should email (i) a description of research interests, (ii) a CV and (iii) the names of 3 references to Dr. Phua at sc.phua(a)nus.edu.sg . The position is available immediately but we will wait for the candidate with the ideal combination of skills and interests.

Oct. 19, 2024