activity
20162022
most citedRecurrent neural circuits for contour detection

17 citations · 32 across the 4 of their papers we have counts for

collaborators

9 papers

cs.AI20221 cited

Explainability Via Causal Self-Talk

Nicholas A. Roy, Junkyung Kim, Neil Rabinowitz

Explaining the behavior of AI systems is an important problem that, in practice, is generally avoided. While the XAI community has been developing an abundance of techniques, most…

cs.CL202211 cited

Transformers generalize differently from information stored in context vs in weights

Stephanie C. Y. Chan, Ishita Dasgupta, Junkyung Kim +3

Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference tim…

cs.CV20213 cited

Tracking Without Re-recognition in Humans and Machines

Drew Linsley, Girik Malik, Junkyung Kim +3

Imagine trying to track one particular fruitfly in a swarm of hundreds. Higher biological visual systems have evolved to track moving objects by relying on both appearance and moti…

cs.CV202017 cited

Recurrent neural circuits for contour detection

Drew Linsley, Junkyung Kim, Alekh Ashok +1

We introduce a deep recurrent neural network architecture that approximates visual cortical circuits. We show that this architecture, which we refer to as the gamma-net, learns to…

cs.CV2019

Disentangling neural mechanisms for perceptual grouping

Junkyung Kim, Drew Linsley, Kalpit Thakkar +1

Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence. This ability is thought to arise in the brain from computatio…

cs.CV2018

Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks

Drew Linsley, Junkyung Kim, David Berson +1

Recent successes in deep learning have started to impact neuroscience. Of particular significance are claims that current segmentation algorithms achieve "super-human" accuracy in…