316 citations
- Rutgers, The State University of New JerseyUS111 papers
- Fermi National Accelerator LaboratoryUS44 papers
- California Institute of TechnologyUS41 papers
- University of California, Santa BarbaraUS37 papers
- University of Minnesota SystemUS36 papers
- Carnegie Mellon UniversityUS35 papers
- Centro de Investigaciones Energéticas, Medioambientales y TecnológicasES35 papers
- Unidades Centrales Científico-TécnicasES35 papers
- University of California, DavisUS34 papers
- University of California, RiversideUS34 papers
- Florida Department of StateUS33 papers
- Johns Hopkins UniversityUS33 papers
4 papers · 1 filter
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
Jinqi Xiao, Chengming Zhang, Yu Gong +5
Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model comple…
A hybrid model-based and learning-based approach for classification using limited number of training samples
Alireza Nooraiepour, Waheed U. Bajwa, Narayan B. Mandayam
The fundamental task of classification given a limited number of training data samples is considered for physical systems with known parametric statistical models. The standalone l…
Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulations
Geoffrey Fox, Shantenu Jha
We present a taxonomy of research on Machine Learning (ML) applied to enhance simulations together with a catalog of some activities. We cover eight patterns for the link of ML to…
Sparse Online Learning via Truncated Gradient
John Langford, Lihong Li, Tong Zhang
We propose a general method called truncated gradient to induce sparsity in the weights of online learning algorithms with convex loss functions. This method has several essential…