Fwd: Thesis Proposal - Oct. 2, 2020 - Otilia Stretcu - Curriculum Learning

[Artur Dubrawski]

appears quite relevant to a few of us

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Fri, Sep 25, 2020 at 12:40 PM
Subject: Thesis Proposal - Oct. 2, 2020 - Otilia Stretcu - Curriculum
Learning
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, Rich Caruana <
rcaruana at microsoft.com>


*Thesis Proposal*

Date: October 2, 2020
Time: 3:30pm (EDT)
Speaker: Otilia Stretcu

Zoom Meeting:
https://cmu.zoom.us/j/94122713476?pwd=VlFqOWYrRkFQMnZaSE0vTXFtT3pRdz09
Meeting ID: 941 2271 3476
Passcode: 866793

*Title: Curriculum Learning*

Abstract:
AI researchers often disagree about the best strategy to train a machine
learning system, but there is one belief that is generally agreed upon:
humans are still much better learners than machines. Unlike AI systems,
humans do not learn difficult new tasks (e.g., solving differential
equations) from scratch, by looking at independent and identically
distributed examples of the task being performed by someone else. Instead,
new skills are often built progressively, starting with easier tasks and
gradually becoming able to perform harder ones. Curriculum Learning (CL) is
a line of work that tries to incorporate this human approach to learning
into machine learning. In this thesis we aim to discover the problem
settings in which different forms of CL are beneficial, and the types of
benefits they provide. Our completed work in machine translation and image
classification already showcases two different settings in which CL is
successful. Next, we plan to take this work further and tackle some
problems that are even more challenging for modern machine learning
systems, such as function composition and learning to do math with neural
networks. If successful, this work could help CL eventually become the
standard method for training systems, bringing machine learning one step
closer to human intelligence.

* Thesis Committee*:
Tom Mitchell, Co-Chair
Barnabás Póczos, Co-Chair
Ruslan Salakhutdinov
Rich Caruana, Microsoft Research
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20200925/e6785535/attachment.html>