Connectionists: The Learning Salon speaks with Tony Zador, Friday, Sep 25, 4 pm ET

[Brad Wyble]

Come join us in a conversation with Tony Zador at the Learning Salon.
https://www.worldwideneuro.com/seminar-event.html?id=641



A critique of pure learning and what artificial neural networks can learn
from animal brains

   - Anthony M. Zador

*Nature Communications <https://www.nature.com/ncomms>* *volume 10*,
Article number: 3770 (2019) Abstract
Artificial neural networks (ANNs) have undergone a revolution, catalyzed by
better supervised learning algorithms. However, in stark contrast to young
animals (including humans), training such networks requires enormous
numbers of labeled examples, leading to the belief that animals must rely
instead mainly on unsupervised learning. Here we argue that most animal
behavior is not the result of clever learning algorithms—supervised or
unsupervised—but is encoded in the genome. Specifically, animals are born
with highly structured brain connectivity, which enables them to learn very
rapidly. Because the wiring diagram is far too complex to be specified
explicitly in the genome, it must be compressed through a “genomic
bottleneck”. The genomic bottleneck suggests a path toward ANNs capable of
rapid learning.


-- 
Brad Wyble
Associate Professor
Psychology Department
Penn State University

http://wyblelab.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20200923/dc951ce9/attachment.html>