M
Massoud Pedram
Researcher at University of Southern California
Publications - 812
Citations - 25236
Massoud Pedram is an academic researcher from University of Southern California. The author has contributed to research in topics: Energy consumption & CMOS. The author has an hindex of 77, co-authored 780 publications receiving 23047 citations. Previous affiliations of Massoud Pedram include University of California, Berkeley & Syracuse University.
Papers
More filters
Journal ArticleDOI
Pre-Defined Sparsity for Low-Complexity Convolutional Neural Networks
TL;DR: In this article, a pre-defined sparse 2D kernels that have support sets that repeat periodically within and across filters are introduced to improve the energy efficiency of deep convolutional neural networks.
Journal ArticleDOI
Factored Edge-Valued Binary Decision Diagrams
Paul Tafertshofer,Massoud Pedram +1 more
TL;DR: A complete matrix package based on FEVBDDs is presented and the introduction of multiplicative edge weights allows us to directly represent the so-called complement edges which are used in OBDDs, thus providing a one to one mapping of all O BDDs to FEV BDDs.
Proceedings ArticleDOI
Optimal control of a grid-connected hybrid electrical energy storage system for homes
TL;DR: The optimal control algorithm for the HEES system is developed, which aims at minimization of the total electricity cost over a billing period under a general electricity energy price function and has polynomial time complexity.
Book ChapterDOI
Edge Valued Binary Decision Diagrams
TL;DR: A canonical and compact data structure, called Edge Valued Binary Decision Diagrams (EVBDD), for representing and manipulating pseudo Boolean functions (PBF), and an extension of EVBDDs which associates both an additive and a multiplicative weight with the true edges of the function graph.
Journal ArticleDOI
Sequence compaction for power estimation: theory and practice
TL;DR: This paper introduces the hierarchical modeling of Markov chains as a flexible framework for capturing not only complex spatiotemporal correlations, but also dynamic changes in the sequence characteristics and introduces and characterize a family of variable-order dynamic Markov models which provide an effective way for accurate modeling of external input sequences that affect the behavior of finite state machines.