activity
20162026
most citedRecurrent neural circuits for contour detection

17 citations · 74 across the 33 of their papers we have counts for

collaborators
Showing 2023Show all

13 papers · 1 filter

cs.CV2023

Categorizing the Visual Environment and Analyzing the Visual Attention of Dogs

Shreyas Sundara Raman, Madeline H. Pelgrim, Daphna Buchsbaum +1

Dogs have a unique evolutionary relationship with humans and serve many important roles e.g. search and rescue, blind assistance, emotional support. However, few datasets exist to…

cs.CL2023★ 1 cited

Uncovering Intermediate Variables in Transformers using Circuit Probing

Michael A. Lepori, Thomas Serre, Ellie Pavlick

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. It is often…

cs.LG2023

Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning

Lakshmi Narasimhan Govindarajan, Rex G Liu, Drew Linsley +4

Humans learn by interacting with their environments and perceiving the outcomes of their actions. A landmark in artificial intelligence has been the development of deep reinforceme…

cs.LG2023★ 1 cited

NeuroSurgeon: A Toolkit for Subnetwork Analysis

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. Recent work has attempted to understand t…

cs.AI2023

Saliency strikes back: How filtering out high frequencies improves white-box explanations

Sabine Muzellec, Thomas Fel, Victor Boutin +3

Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identifi…

cs.CV2023★ 11 cited

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

Drew Linsley, Ivan F. Rodriguez, Thomas Fel +4

One of the most impactful findings in computational neuroscience over the past decade is that the object recognition accuracy of deep neural networks (DNNs) correlates with their a…