← Search

Bryan M. Li

2 accepted papers

2024

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos

NeurIPS 2024poster

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Ma…

Cited by 3SourcePDFScholar
2018

Unsupervised Cipher Cracking Using Discrete GANs

ICLR 2018poster

This work details CipherGAN, an architecture inspired by CycleGAN used for inferring the underlying cipher mapping given banks of unpaired ciphertext and plaintext. We demonstrate that CipherGAN is capable of cracking language data enciphered using shift and Vigenere ciphers to a high degree of fide…