Benjamin D. Evans

The paper proposes that spatial encoding and factorisation mechanisms enable efficient genomic encoding of neural network architecture and connectivity.

The paper shows that random inhibitory connectivity in mouse visual cortex explains functional heterogeneity and decorrelates pyramidal cell adaptation.

This paper investigates how capacity constraints in CNNs affect learning of random versus natural data, finding that internal noise most effectively reduces performance on random data to chance levels.

The paper trains a deep convolutional neural network to accurately classify chick embryos from images, achieving high accuracy on both brain and wing tissues.

This paper shows that adding biological filter banks improves DNN robustness to noise and generalisation to out-of-domain images.

This paper estimates disease prevalence using genetic risk scores and evaluates methods for robust prevalence estimation across different scenarios.

This study shows that Vangl2 regulates cytoneme dynamics, affecting Wnt/{beta}-catenin signaling and tissue patterning in vertebrates.