SMRI Seminar -- Machine learning for the working mathematician

SMRI Seminar: Machine learning for the working mathematician 
Location: Online (see website for link) 

***
Week 14: Thursday 2nd June,  (Note: 4pm Sydney time, online) , 4pm 

Lars Buesing, Searching for Formulas and Algorithms: Symbolic Regression and Program 
Induction

Abstract: In spite of their enormous success as black box function approximators in many 
fields such as computer vision, natural language processing and automated decision 
making, Deep Neural Networks often fall short of providing interpretable models of data. 
In applications where aiding human understanding is the main goal, describing 
regularities in data with compact formuli promises improved interpretability and better 
generalization. In this talk I will introduce the resulting problem of Symbolic 
Regression and its generalization to Program Induction, highlight some learning methods 
from the literature and discuss challenges and limitations of searching for algorithmic 
descriptions of data.
***



Organisers: Joel Gibson, Georg Gottwald, Geordie Williamson.  

This semester we (Georg, Geordie and Joel) are organising a seminar on machine
learning.  This seminar will aim to provide an introduction to ways in which machine
learning (and in particular deep learning) has been used to solve problems in
mathematics.  We aim for a toolbox of simple examples, where one can get an
understanding of what machine learning can and cannot do.  We also hope to organise
tutorials, for people who would like to experiment with code.  

The emphasis will be on techniques in machine learning as tools that we can use, rather
than a source of problems in themselves.  The first six weeks or so will be
introductory, and the second six weeks will feature talks from experts on applications.  

Everyone is welcome! 

Website: https://sites.google.com/view/mlwm-seminar-2022 

[School of Maths & Stats members are also invited to Afternoon Tea in the SMRI Common
Room/Terrace, 2:15-2:45pm Thursdays]