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.
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.
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
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
On Oct 21, 2024, at 11:10 AM, James Bower <bowerj@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.
<largepreview.png>
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