SMRI Seminar: Charton -- Can language models learn arithmetic?

SMRI Seminar:
'Can language models learn arithmetic?'

Francois Charton, Research Engineer at FAIR, Meta

Thursday 17 April, 13:00 - 14:00 AEST
SMRI Seminar Room (Macleay Building A12 Room 301)

Abstract: Language models have become surprisingly good at many tasks, from text 
summarization to image generation, and speech recognition. Yet, they are still 
embarrassingly weak on basic arithmetic operations, like integer multiplication. 
I present recent results demonstrating that language models (transformers) can 
indeed learn complex calculations, and sometimes capture some of the underlying 
mathematics. This research demonstrates the importance of the distribution of 
training examples in deep learning.



(Please join us afterwards for SMRI afternoon tea on the SMRI terrace 2-2:45pm)