1 code implementation • 7 Nov 2023 • Michael A. Lepori, Thomas Serre, Ellie Pavlick
We apply this method to models trained on simple arithmetic tasks, demonstrating its effectiveness at (1) deciphering the algorithms that models have learned, (2) revealing modular structure within a model, and (3) tracking the development of circuits over training.
1 code implementation • 17 Oct 2023 • Enyan Zhang, Michael A. Lepori, Ellie Pavlick
Our method discovers a functional subnetwork that implements a particular subtask within a trained model and uses it to instill inductive biases towards solutions utilizing that subtask.
no code implementations • 14 Oct 2023 • Alexa R. Tartaglini, Sheridan Feucht, Michael A. Lepori, Wai Keen Vong, Charles Lovering, Brenden M. Lake, Ellie Pavlick
Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli.
1 code implementation • 1 Sep 2023 • Michael A. Lepori, Ellie Pavlick, Thomas Serre
Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent.
1 code implementation • NeurIPS 2023 • Michael A. Lepori, Thomas Serre, Ellie Pavlick
Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement.
1 code implementation • 24 Nov 2020 • Michael A. Lepori
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis.
1 code implementation • COLING 2020 • Michael A. Lepori, R. Thomas McCoy
As the name implies, contextualized representations of language are typically motivated by their ability to encode context.
1 code implementation • ACL 2020 • Michael A. Lepori, Tal Linzen, R. Thomas McCoy
Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks.
no code implementations • 27 Mar 2020 • Michael A. Lepori, Chaz Firestone
The rise of machine-learning systems that process sensory input has brought with it a rise in comparisons between human and machine perception.