1 code implementation • ICML 2020 • Daniel Kunin, Aran Nayebi, Javier Sagastuy-Brena, Surya Ganguli, Jonathan M. Bloom, Daniel L. K. Yamins
The neural plausibility of backpropagation has long been disputed, primarily for its use of non-local weight transport $-$ the biologically dubious requirement that one neuron instantaneously measure the synaptic weights of another.
1 code implementation • 28 Jan 2019 • Jonathan M. Bloom
We detail distributed algorithms for scalable, secure multiparty linear regression and feature selection at essentially the same speed as plaintext regression.
2 code implementations • 23 Jan 2019 • Daniel Kunin, Jonathan M. Bloom, Aleksandrina Goeva, Cotton Seed
Autoencoders are a deep learning model for representation learning.
no code implementations • 28 Dec 2012 • Jonathan M. Bloom
We prove several combinatorial results on path algebras over discrete structures related to directed graphs.
Geometric Topology Combinatorics Symplectic Geometry