<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
The AI Lunch Series will be hosting Dr. Razvan Pascanu (DeepMind) this Wednesday for a presentation on “Discussion on Continual Learning and Learning Dynamics in Deep Networks”. Additional information can be found at:<span style="margin:0px"> </span><a href="https://www.jlab.org/AI/lunch_series/2020" target="_blank" rel="noopener noreferrer" data-auth="NotApplicable" style="margin:0px">https://www.jlab.org/AI/lunch_series/2020</a> </div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
<br>
</div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
12-1PM, Wednesday, October 28, 2020</div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
Join with Bluejeans:<span style="margin:0px"> <a href="https://bluejeans.com/395185997" target="_blank" rel="noopener noreferrer" data-auth="NotApplicable" style="margin:0px">https://bluejeans.com/395185997</a></span></div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
<br>
</div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
Abstract: I will begin with a brief introduction to, and open problems in, understanding neural networks and discuss several approaches to this problem. Further I will discuss the importance of continual learning for the field. Continual Learning, sometimes
called life-long learning, never-ending learning or open-ended learning, is a topic that has been growing in popularity in the last few years. I will provide an overview of the problem, contrasting sequential learning to multi-task learning and highlight why
multi-task learning can be in practice sub-optimal. I will discuss the main family of approaches to continual learning and discuss recent research in the field. Finally I will provide a few ideas of where the field might go in the near future and open the
floor for discussion.<br>
</div>
<div style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
<br>
</div>
<span style="margin: 0px; font-size: 15px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255); display: inline !important;">If you have questions, contact tennant@jlab.org </span><br>
</div>
</body>
</html>