Can a Fruit Fly Learn Word Embeddings?

2 code implementations • ICLR 2021 • Yuchen Liang, Chaitanya K. Ryali, Benjamin Hoover, Leopold Grinberg, Saket Navlakha, Mohammed J. Zaki, Dmitry Krotov

In this work we study a mathematical formalization of this network motif and apply it to learning the correlational structure between words and their context in a corpus of unstructured text, a common natural language processing (NLP) task.

Document Classification Word Embeddings +2

Bio-Inspired Hashing for Unsupervised Similarity Search

no code implementations • ICML 2020 • Chaitanya K. Ryali, John J. Hopfield, Leopold Grinberg, Dmitry Krotov

Building on inspiration from FlyHash and the ubiquity of sparse expansive representations in neurobiology, our work proposes a novel hashing algorithm BioHash that produces sparse high dimensional hash codes in a data-driven manner.

Local Unsupervised Learning for Image Analysis

no code implementations • NeurIPS Workshop Neuro_AI 2019 • Leopold Grinberg, John Hopfield, Dmitry Krotov

Local Hebbian learning is believed to be inferior in performance to end-to-end training using a backpropagation algorithm.