Tony Bell: Difference between revisions

From RedwoodCenter
Jump to navigationJump to search
 
(One intermediate revision by the same user not shown)
Line 12: Line 12:
== Research Interest ==
== 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.)
(This webpage is under reconstruction. Only a few essential links are posted here.)
 
It's 2010.


Here's my [http://www.snl.salk.edu/~tony Salk web-page] from way back.
Here's my [http://www.snl.salk.edu/~tony Salk web-page] from way back.


Here's me giving a 30 minute talk [http://thesciencenetwork.org/programs/brains-r-us-2/tony-bell Levels, Time and Models] about Levels in Biology. <br>
Here's me giving a 30 minute talk [http://thesciencenetwork.org/programs/brains-r-us-2/tony-bell Levels, Time and Models] about Levels in Biology. <br>
Here's me giving a 85 minute talk [http://vimeo.com/5812603 Emergence and Submergence in the Nervous System]. <br>
It's similar, but more discursive. (The production on the latter is not so good, so here are the [http://redwood.berkeley.edu/tony/papers slides]. <br>
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.<br>
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. <br>
A paper on this [http://www.kosmix.com/topic/tony_bell 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,  <br>
stochastic generative models, mistakenly assume that probabilistic models must be stochastic. If you  believe that "the world is noisy", <br>
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''. <br>
That means we use real biology and real physics to guide us. Computational fantasizing has demonstrated its limits. <br>
We will have to absorb and augment the emerging non-equilibrium statistical mechanics and, in the end, also (cough) quantum theory. <br>
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, <br>
in their core mathematical structure, are relatively simple.


Here's an unsatisfactory paper [http://www.irp.oist.jp/ocnc/2008/bell07.pdf Towards a cross-level theory of neural learning] that explains what I was thinking up till about 2008.
Here's the only paper I have written on the Levels issue. It covers my thinking up till about 2008: <br>
[http://www.irp.oist.jp/ocnc/2008/bell07.pdf Towards a cross-level theory of neural learning]


More later. Please send grant money :)
There are new results on time series analysis coming :)

Latest revision as of 10:50, 14 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

(This webpage is under reconstruction. Only a few essential links are posted here.)

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 the only paper I have written on the Levels issue. It covers my thinking up till about 2008:
Towards a cross-level theory of neural learning

There are new results on time series analysis coming :)