263 citations · 814 across the 19 of their papers we have counts for
21 papers
Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning
Syon Mansur, Joel Zylberberg
End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers of a neural network. Prior stud…
Signal-Noise Factorization Isolates Nuisance Variation into Removable Subspaces
Sakin Kirti, Joel Zylberberg
Recent theoretical work identified fundamental properties of representation geometry that shape inference ability of deep neural networks. These include signal-noise factorization…
Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
Alex Heyman, Joel Zylberberg
Large language models have recently made great strides in reasoning task performance through chain-of-thought (CoT) strategies trained via reinforcement learning; however, these "r…
Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring
Alex Heyman, Joel Zylberberg
Contemporary large language models are powerful problem-solving tools, but they exhibit weaknesses in their reasoning abilities which ongoing research seeks to mitigate. We investi…
Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks
Alex Murphy, Joel Zylberberg, Alona Fyshe
Centred Kernel Alignment (CKA) has recently emerged as a popular metric to compare activations from biological and artificial neural networks (ANNs) in order to quantify the alignm…
Finding Shared Decodable Concepts and their Negations in the Brain
Cory Efird, Alex Murphy, Joel Zylberberg +1
Prior work has offered evidence for functional localization in the brain; different anatomical regions preferentially activate for certain types of visual input. For example, the f…