SMS scnews item created by Hannah Bryant at Thu 10 Feb 2022 1418
Type: Seminar
Modified: Thu 10 Feb 2022 1418; Fri 11 Feb 2022 1323; Fri 11 Feb 2022 1324; Mon 21 Feb 2022 1308; Tue 22 Feb 2022 1020; Tue 22 Feb 2022 1022; Tue 22 Feb 2022 1417; Tue 1 Mar 2022 1610; Tue 1 Mar 2022 1612; Wed 23 Mar 2022 1409; Wed 23 Mar 2022 1411; Thu 24 Mar 2022 1313; Mon 28 Mar 2022 1408; Mon 4 Apr 2022 1112; Wed 6 Apr 2022 1526; Wed 6 Apr 2022 1528; Wed 6 Apr 2022 1536; Mon 11 Apr 2022 1006; Mon 11 Apr 2022 1013; Mon 11 Apr 2022 1015; Fri 22 Apr 2022 1651; Wed 27 Apr 2022 1550; Mon 2 May 2022 1024; Mon 9 May 2022 1054; Wed 11 May 2022 1438; Mon 16 May 2022 1216; Thu 19 May 2022 1514; Fri 20 May 2022 1554; Mon 23 May 2022 1056; Tue 31 May 2022 1024
Distribution: World
Expiry: 3 Jun 2022
Calendar1: 24 Feb 2022 1500-1700
CalLoc1: Carslaw 273 & Online
CalTitle1: SMRI Seminar: Machine learning for the working mathematician
Calendar2: 3 Mar 2022 1500-1700
CalLoc2: Carslaw 273 & Online
CalTitle2: SMRI Seminar: Machine learning for the working mathematician - Gibson ’What can and can’t neural networks do’
Calendar3: 10 Mar 2022 1500-1700
CalLoc3: Carslaw 273 & Online
CalTitle3: SMRI Seminar: Machine learning for the working mathematician
Calendar4: 17 Mar 2022 1500-1700
CalLoc4: Carslaw 273 & Online
CalTitle4: SMRI Seminar: Machine learning for the working mathematician
Calendar5: 24 Mar 2022 1500-1700
CalLoc5: Carslaw 273 & Online
CalTitle5: SMRI Seminar: Machine learning for the working mathematician - Williamson ’Geometric Deep Learning’
Calendar6: 31 Mar 2022 1500-1700
CalLoc6: Carslaw 273 & Online
CalTitle6: SMRI Seminar: Machine learning for the working mathematician - Gottwald ’Geometric Deep Learning II’
Calendar7: 7 Apr 2022 1500-1700
CalLoc7: Online via Zoom
CalTitle7: SMRI Seminar: Machine learning for the working mathematician - Zsolt Wagner ’A simple RL setup to find counterexamples to conjectures in mathematics’
Calendar8: 14 Apr 2022 1100-1300
CalLoc8: Online via Zoom
CalTitle8: SMRI Seminar: Machine learning for the working mathematician - Hosseini ’Perspectives on graphical semi-supervised learning’
Calendar9: 28 Apr 2022 1500-1700
CalLoc9: Online via Zoom
CalTitle9: SMRI Seminar: Machine learning for the working mathematician - Simpson ’Learning proofs for the classification of nilpotent semigroups’
Calendar10: 5 May 2022 1600-1800
CalLoc10: Online via Zoom
CalTitle10: SMRI Seminar: Machine learning for the working mathematician
Calendar11: 12 May 2022 0900-1100
CalLoc11: Online via Zoom
CalTitle11: SMRI Seminar: Machine learning for the working mathematician: Halpern-Leinster ’Learning selection strategies in Buchberger’s algorithm’
Calendar12: 19 May 2022 1500-1600
CalLoc12: Online via Zoom
CalTitle12: SMRI Seminar: Machine learning for the working mathematician: Kutyniok ’Deep Learning meets Shearlets: Explainable Hybrid Solvers for Inverse Problems in Imaging Science’
Calendar13: 26 May 2022 1500-1700
CalLoc13: Online via Zoom & Carslaw 273
CalTitle13: SMRI Seminar: Machine learning for the working mathematician: Li ’Deep learning for sequence modelling’
Calendar14: 2 Jun 2022 1600-1800
CalLoc14: Online via Zoom & Carslaw 273
CalTitle14: SMRI Seminar: Machine learning for the working mathematician: Buesing ’Searching for Formulas and Algorithms: Symbolic Regression and Program Induction’
Calendar15: 27 May 2022 1500-1600
CalLoc15: Online via Zoom & Quad S225
CalTitle15: SMRI Seminar: Machine learning for the working mathematician: workshop
Auth: hannahb@staff-10-48-21-142.vpnuser.sydney.edu.au (hbry8683) in SMS-SAML

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!