Tony Bell: Difference between revisions

From RedwoodCenter
Jump to navigationJump to search
Line 29: Line 29:
(1) Solve the time series density estimation problem  
(1) Solve the time series density estimation problem  


(2) Solve the sensory-motor density estimationproblem
(2) Solve the sensory-motor density estimation problem


(3) Solve the levels density estimation problem
(3) Solve the levels density estimation problem
Line 36: Line 36:
I am working on (1) and I think I've got it.
I am working on (1) and I think I've got it.


The reinforcement literature has nothing relevant to say about these deep problems.
The reinforcement learning literature has nothing relevant to say about these deep problems.


And unfortunately there's no way around it: to really crack this we are going to have to "get real". <br>
And unfortunately there's no way around it: to really crack this we are going to have to "get real". <br>

Revision as of 09:10, 9 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) 699 6502
fax (510) 643-4952
tbell@berkeley.edu

Research Interest

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.
(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.
I really want to crack this, and I think it can be done before too long.
Also, I believe we must solve these problems.

There are 3 steps to uniting physics, biology and machine learning:

(1) Solve the time series density estimation problem

(2) Solve the sensory-motor density estimation problem

(3) Solve the levels density estimation problem

The clues to (2) and (3) lie in (1).
I am working on (1) and I think I've got it.

The reinforcement learning literature has nothing relevant to say about these deep problems.

And unfortunately there's no way around it: to really crack this we are going to have to "get real".
We will have to absorb and augment the emerging non-equilibrium statistical mechanics and (cough) quantum theory.
I know this is not a common view, but still, I think it is correct. Fortunately, both these branches of physics, in their core form, 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.

Here is my CV. (Ignore the stuff about the cyclist journalist - that's not me :)