conftrace_

bias parameter

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

max pooling (1) clarke subderivative (1) prediction head (1) word frequency (1) logit adjustment (1) long-tailed learning (1) transformer language model (1) activation function (1) automatic differentiation (1) text generation (1)

Papers

What does automatic differentiation compute for neural networks? ICLR 2024 Transformer Language Models Handle Word Frequency in Prediction Head ACL 2023