Computing Representations for Lie Algebraic Networks

1 code implementation • 1 Jun 2020 • Noah Shutty, Casimir Wierzynski

First, we relax the requirement for explicit Lie group representations with a novel algorithm that finds representations of arbitrary Lie groups given only the structure constants of the associated Lie algebra.

Object Tracking

Design of optical neural networks with component imprecisions

1 code implementation • 13 Dec 2019 • Michael Y. -S. Fang, Sasikanth Manipatruni, Casimir Wierzynski, Amir Khosrowshahi, Michael R. DeWeese

For the benefit of designing scalable, fault resistant optical neural networks (ONNs), we investigate the effects architectural designs have on the ONNs' robustness to imprecise components.

nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data

2 code implementations • 12 Aug 2019 • Fabian Boemer, Anamaria Costache, Rosario Cammarota, Casimir Wierzynski

The proposed framework leverages the CKKS scheme, whose support for real numbers is friendly to data science, and a client-aided model using a two-party approach to compute activation functions.

Cryptography and Security

nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

2 code implementations • 23 Oct 2018 • Fabian Boemer, Yixing Lao, Casimir Wierzynski

Homomorphic encryption (HE)--the ability to perform computations on encrypted data--is an attractive remedy to increasing concerns about data privacy in the field of machine learning.

Cryptography and Security