Research Manuscript: A Melange of Machine Learning Frameworks for Optimization
Event TypeResearch Manuscript
Hosted in Virtual Platform
DescriptionThe landscape of machine learning systems is evolving very fast, and many optimizations are needed across algorithm, compiler, and hardware accelerator designs. In this session, we highlight frameworks for machine learning system optimization covering four topics: memory-efficient graph neural network design, neural hardware-compiler co-design, energy-efficient unsupervised spiking neural network framework, and Bayesian neural network hardware accelerator.