[AI Seminar] Online AI Seminar on Nov 03 (Zoom) -- Aaron Courville -- Emerging and preserving compositional structure through iterated learning -- AI seminar is sponsored by Fortive

[Aayush Bansal]

Aaron Courville (University of Montreal) will be giving an
online seminar on "Emerging and preserving compositional structure through
iterated learning" from 12:00 noon - 01:00 PM ET on Nov 03.

*Zoom Link*:
https://cmu.zoom.us/j/99054050077?pwd=bjQ5OXN1Z09sQ3pVcTJDMVJBbjJkQT09

CMU AI Seminar is sponsored by Fortive.

Following are the details of the talk:

*Title: *Emerging and preserving compositional structure through iterated
learning

*Abstract: *Iterated learning is a theory of how the compositional
structure of human language emerged. The theory holds that
intergenerational language transfer creates learning bottlenecks that
privilege compositional structure. Recent work in the machine learning
community has shown that the iterated learning mechanism can also promote
compositional structure in language emergence in communication between
neural-network-base AI-agents. In this talk, I will describe our recent
efforts at putting iterated learning to work in applications of Neural
Module Network to simple Visual Question Answering and in self-play
training scenarios with dialogue models. We find that applying iterated
learning to the generation of the program that specifies the assembly of
distinct neural network modules leads to higher accuracy in program
prediction and supports systematic generalization to testing question
templates that are not in the training set. In the context of self-play
training of dialogue agents, we find the surprising result that iterated
learning can mitigate language drift.


*Bio:* Aaron Courville is an Associate Professor in the Department of
Computer Science and Operations Research at the Universite de Montreal. He
received his PhD from the Robotics Institute, Carnegie Mellon University.
He is one of the early contributors to Deep Learning, and is a founding
member of Mila and a fellow of the CIFAR program on Learning in Machines
and Brains. Together with Ian Goodfellow and Yoshua Bengio, he co-wrote the
seminal textbook on Deep Learning. His current research interests focus on
the development of DL models and methods. He is particularly interested in
deep generative model and multimodal ML with applications such as computer
vision and natural language processing. Aaron holds a CIFAR Canadian AI
chair and his research is supported in part by Microsoft Research, Samsung,
Hitachi, and a Google Focussed Research Award.

To learn more about the seminar series, please visit the website:
http://www.cs.cmu.edu/~aiseminar/


-- 
Aayush Bansal
http://www.cs.cmu.edu/~aayushb/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20201028/0af4f31c/attachment.html>