Difference between revisions of "Tony Bell"

From RedwoodCenter
Jump to navigationJump to search
Line 12: Line 12:
 
== Research Interest ==
 
== Research Interest ==
  
(This revision to my webpage is under construction, so many of the links are not there yet. Give me a few days.)
+
(I'm sorry. This revision to my webpage is under construction, so many of the links are not there yet. Give me a few days.)
  
 
It's 2010.
 
It's 2010.
Line 47: Line 47:
  
 
Here's an unsatisfactory paper [http://redwood.berkeley.edu/tony/papers Towards a cross-level theory of neural learning] that explains what I was thinking up till about 2008.
 
Here's an unsatisfactory paper [http://redwood.berkeley.edu/tony/papers Towards a cross-level theory of neural learning] that explains what I was thinking up till about 2008.
 
Here's my [http://www.kosmix.com/topic/tony_bell CV]. (Ignore the stuff about the cyclist journalist - that's not me.)
 
  
 
More later. Please send grant money :)
 
More later. Please send grant money :)

Revision as of 07:11, 10 September 2010

Tony.jpg

Anthony J. Bell Ph.D.
Redwood Center for Theoretical Neuroscience
UC Berkeley
132 Barker, MC #3190
Berkeley, CA 94720-3190
phone (415) 568-0346
fax (510) 643-4952
tbell@berkeley.edu

Research Interest

(I'm sorry. This revision to my webpage is under construction, so many of the links are not there yet. Give me a few days.)

It's 2010.

Here's my Salk web-page from way back.

Here's me giving a 30 minute talk Levels, Time and Models about Levels in Biology.
Here's me giving a 85 minute talk Emergence and Submergence in the Nervous System.
It's similar, but more discursive. (The production on the latter is not so good, so here are the slides.
Also, if you wait a few minutes in, the audio drastically improves.)

What am I doing? If you watch either of these you will see, at least, where I am starting from.
There are 3 steps to uniting physics, biology and machine learning:

(1) Solve the time series density estimation problem properly (this will be very useful).

(2) Solve the sensory-motor density estimation problem

(3) Solve the levels density estimation problem

The clues to (2) and (3) lie in (1). The clues to (1) lie in non-equilibrium statistical mechanics. We are working on (1) and I think we've got it.
A paper on this Learning out of equilibrium will be ready shortly. Email me if you want it when it's ready.

The reinforcement learning literature, while elegant, has nothing relevant to say about these deep problems. And in my view,
stochastic generative models, mistakenly assume that probabilistic models must be stochastic. If you believe that "the world is noisy",
you are confusing your uncertainty with something called "noise in the system", a completely undefined concept.

Unfortunately there's no way around it: to really crack this we are going to have to get real.

That means we use real biology and real physics to guide us. Computational fantasizing has demonstrated its limits.
We will have to absorb and augment the emerging non-equilibrium statistical mechanics and, in the end, also (cough) quantum theory.
I know these are radical views, but still, after a lot of thought, I believe them to be correct. Fortunately, both these branches of physics,
in their core mathematical structure, are relatively simple.

Here's an unsatisfactory paper Towards a cross-level theory of neural learning that explains what I was thinking up till about 2008.

More later. Please send grant money :)