17 citations · 56 across the 9 of their papers we have counts for
9 papers
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…
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…
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…
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…
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…
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…
Learning long-range spatial dependencies with horizontal gated-recurrent units
Drew Linsley, Junkyung Kim, Vijay Veerabadran +1
Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, ar…
Same-different problems strain convolutional neural networks
Matthew Ricci, Junkyung Kim, Thomas Serre
The robust and efficient recognition of visual relations in images is a hallmark of biological vision. We argue that, despite recent progress in visual recognition, modern machine…
A Passage-of-time Model of the Cerebellar Purkinje Cell
Matthew Ricci, Junkyung Kim, Fredrik Johansson
The cerebellar Purkinje cell controlling eyeblinks can learn, remember and reproduce the interstimulus interval in a classical conditioning paradigm. Given temporally separated inp…