Papers for Vision Transformers (ViT) and Mechanistic Interpretability
Papers that give context when exploring mechanistic interpretability on vision transformers.
Papers that give context when exploring mechanistic interpretability on vision transformers.
Thoughts on Montreal after the Bay Area
Presentation on optic flow, PWC-Net, and a possible application to birds and mice for Janelia
Research overview of meta-learning by researcher and institution.
Founding a Deep NLP journal club for women in AI.
Founding a reinforcement learning journal club, welcome to join!
A library of Hopfield networks and undirected neural nets.
On accounting for billions+ of parameters and nonlinearities
Matching similar phrases given two corpuses
When pruning 80% of a neural net does not affect accuracy
Research overview of artificial/biological intelligence by researcher and institution.
scraping quotes from goodreads and creating a database
Text and lyric generation with basic natural language processing.
Facial recognition with collaborative representation-based classification.
A hypothetical proposal to model object categorization in the prefrontal cortex with the goal-driven neural network paradigm.
Basic concepts in neural dynamics explained with Hopfield networks.
Resources for computational neuroscience