Search Results for author:
Found 9 papers, 7 papers with code
Uncovering Intermediate Variables in Transformers using Circuit Probing
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.
Instilling Inductive Biases with Subnetworks
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.
Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations
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.
NeuroSurgeon: A Toolkit for Subnetwork Analysis
Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent.
Break It Down: Evidence for Structural Compositionality in Neural Networks
Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement.
Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis.
Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis
As the name implies, contextualized representations of language are typically motivated by their ability to encode context.
Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs
Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks.
Can you hear me $\textit{now}$? Sensitive comparisons of human and machine perception
The rise of machine-learning systems that process sensory input has brought with it a rise in comparisons between human and machine perception.
