Tom Dean, Professor Emeritus at Brown University
Professor Tom Dean is a currently a visiting Scholar at the Wu Tsai Neuroscience, a lecturer in the Computer Science Department at Stanford and a Professor Emeritus at Brown University. He has also been teaching the course CS379C: Computational Models of the Neocortex, for many years at Stanford. Previously, he has worked at various institution including Google. You can find an abbreviated bio of him at https://web.stanford.edu/class/cs379c/archive/2020/resources/autobiox/
Title: On the Role of Search in Brain Inspired Architectures for Automated Programming
In CS379C in the Spring of 2020 we discussed a paper by Josh Merel, Matt Botvinick and Greg Wayne entitled "Hierarchical motor control in mammals and machines". Josh gave an invited lecture on their work that you can find at https://web.stanford.edu/class/cs379c/archive/2020/calendar_invited_talks/lectures/04/23/index.html and joined in discussions with us during the remainder of the quarter. The Merel et al paper focuses on motor control and in our class discussions we investigated what lessons could be learned from their model in developing cognitive architectures for solving problems like automated programming. The SARS-CoV-2 outbreak and shortened quarter were not conducive to class projects requiring substantial coding, but we spent a lot of our time thinking about what such architectures might look like. At the end of the quarter, I asked several students if they were interested in developing a cognitive architecture based on our discussions in class and five of us spent a substantial fraction of the next six months working on the project. In this talk, I will describe the project and the lessons we learned that led to developing a very different perspective than one might expect given our technical leanings at the outset of the project.