Aidan N Gomez
5 papers · 2017–2022 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Conference Polyglot (2) ๐ Academic Marathon (5) ๐ Interdisciplinary Bridge ๐บ๏ธ Taxonomy Completionist (14) ๐งญ Keyword Pioneer
๐ฃ
Hot Topic Early Bird
๐
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICML (2)
Top co-authors
Keywords
transformer architecture
(1)
sample efficiency
(1)
autoregressive transformer
(1)
self-attention mechanism
(1)
curriculum learning
(1)
attention mechanism
(1)
machine translation
(1)
gradient computation
(1)
convolutional neural network
(1)
non-parametric model
(1)
memory efficiency
(1)
data selection
(1)
tabular datum
(1)
protein language model
(1)
residual network
(1)
training acceleration
(1)
deep learning architecture
(1)
generalization loss
(1)
redundant datum
(1)
neural network
(1)
Papers
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
ICML 2022
Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval
ICML 2022
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
NIPS 2021
Attention is All you Need
NIPS 2017
The Reversible Residual Network: Backpropagation Without Storing Activations
NIPS 2017