← Search

Joshua Brendan Melander

2 accepted papers

2026

Causal Interpretation of Neural Network Computations with Contribution Decomposition (CODEC)

ICLR 2026poster

Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct a…

Cited by 0SourcecodeScholar
2023

Information Geometry of the Retinal Representation Manifold

NeurIPS 2023poster

The ability for the brain to discriminate among visual stimuli is constrained by their retinal representations. Previous studies of visual discriminability have been limited to either low-dimensional artificial stimuli or pure theoretical considerations without a realistic encoding model. Here we pr…

Cited by 6SourcePDFScholar