Evolving Neural Programs for Continuous Learning

Speaker: Dennis Wilson , Institut de Recherche en Informatique de Toulouse, Toulouse France

Date: Wednesday, June 21, 2017

Time: 3:00 PM to 4:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Seminar Room D507

Event Type:

Room Description:

Host: Una-May O'Reilly

Contact: Nicole Hoffman, nicolem@csail.mit.edu

Relevant URL: d9w.xyz

Speaker URL: None

Speaker Photo:
None

Reminders to: csail-related@csail.mit.edu, seminars@csail.mit.edu

Reminder Subject: TALK: Evolving Neural Programs for Continuous Learning

Abstract:
Artificial neural networks (ANNs) have recently made large advances in the field of continuous control tasks. Both on-policy and off-policy reinforcement learning (RL) algorithms which train ANNs have shown impressive results in tasks such as classic RL control tasks, robotic control, and video game playing with pixel input. However, these training methods are limited by their inability to generalize to different tasks after learning a specific task, termed catastrophic forgetting, and their need for a large set of training examples. These key features of continuous learning, the ability to learn new skills while retaining previous knowledge and the ability to learn on a small set of examples, are found in biologic neural networks and contemporary neuroscience has greatly advanced understanding of some of their underlying mechanisms. In this talk, I will examine existing artificial neural models, ranging from deep learning to evolutionary and developmental methods, as they relate to continuous learning. I will then discuss an evolutionary model, currently under development, which explores existing neural models and discovers new models for competition in an open continuous learning environment that assesses the catastrophic forgetting and learning rate of each model.

Bio:
Dennis G Wilson '14 is currently a PhD candidate at the Institut de Recherche en Informatique de Toulouse studying artificial neural development. During their time at MIT, they worked for three years as a UROP in the Anyscale Learning For All group in CSAIL, applying evolutionary strategies and developmental models to the complex problem of wind farm layout optimization. Their current work and more can be found at d9w.xyz.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Nicole Hoffman Email at Thursday, June 01, 2017 at 12:05 PM.