<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);">
<span style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">The AI Lunch Series will be hosting Robert Geirhos (International Max Planck Research School for Intelligent Systems) this Wednesday for a presentation
on “Neural Networks Love to Cheat: Shortcut Learning in Deep Learning and Beyond”. Additional information can be found at: https://www.jlab.org/AI/lunch_series/2020<br>
</span>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
<br>
</div>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
12-1PM, Wednesday, July 22, 2020<br>
</div>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
Join with Bluejeans: https://bluejeans.com/707697867<br>
</div>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
<br>
</div>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
Abstract: "Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently
come into focus. In this talk I will seek to distill how many of deep learning's problem can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to
transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology and Education, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial
alike. Based on these observations, I propose a set of recommendations for model interpretation and benchmarking."<br>
</div>
<div style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">
<br>
</div>
<span style="margin: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255)">If you have questions, contact tennant@jlab.org.</span><br>
</div>
</body>
</html>