@raphaelmilliere : Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory? 📄 Our new ICML paper investigates this in a synthetic setting! 🧵 1/13 • TwiCopy

Raphaël Millière

@raphaelmilliere

+ Follow

Philosopher of Artificial Intelligence & Cog Science @Macquarie_Uni
Past @Columbia @UniofOxford
Also on other platforms
Blog: artificialcognition.net

ID: 731078318414544896

linkhttp://raphaelmilliere.com calendar_today13-05-2016 11:07:08

2,2K Tweet

10,10K Followers

2,2K Following

Raphaël Millière

@raphaelmilliere

2 months ago

Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory? 📄 Our new ICML paper investigates this in a synthetic setting! 🧵 1/13

thumb_up_off_alt614

chat_bubble_outline8

repeat94

shareShare