Users reacted positively to Tilde Research and CoreAutoAI's One Layer Deeper Optimizer Competition because it permits advanced techniques such as recurrence, adaptive computation, and depth curricula.
Based on 1 visible X reactions from 3 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@_arohan_ @tilderesearch @CoreAutoAI “Recurrence, adaptive computation, and depth curricula are allowed” indeed they are:)
Find ways to beat this benchmark that tries to understand the limits of deep learning architectures and optimization? We are funding compute, there is a nice way to test it out. Its a single GPU problem. Cracked team @tilderesearch x @CoreAutoAI collaboration.
Users reacted positively to Tilde Research and CoreAutoAI's One Layer Deeper Optimizer Competition because it permits advanced techniques such as recurrence, adaptive computation, and depth curricula.
Based on 1 visible X reactions from 3 accounts; directional sample.
Ask a question below.
Published answers will appear here.