← Search

Kyle Aitken

2 accepted papers

2021

The geometry of integration in text classification RNNs

ICLR 2021poster

Despite the widespread application of recurrent neural networks (RNNs), a unified understanding of how RNNs solve particular tasks remains elusive. In particular, it is unclear what dynamical patterns arise in trained RNNs, and how those pat-terns depend on the training dataset or task. This work…

Cited by 14SourcePDFScholar
2021

Understanding How Encoder-Decoder Architectures Attend

NeurIPS 2021poster

Encoder-decoder networks with attention have proven to be a powerful way to solve many sequence-to-sequence tasks. In these networks, attention aligns encoder and decoder states and is often used for visualizing network behavior. However, the mechanisms used by networks to generate appropriate atten…

Cited by 33SourcePDFScholar