Machine Learning Acceleration

Catalog description

The remarkable success of machine learning (ML) algorithms has led to the deployment of industrial ML accelerators throughout cloud, mobile, edge and wearables, and from computer vision and speech processing to recommendations and graph learning. Provides a solid understanding of such acceleration systems, including implications of the various hardware and software components on various costs such as latency, energy, area, throughput, power, storage and inference accuracy for ML tasks. Covers acceleration mechanisms for machine learning models, including convolutional and feed-forward neural networks, transformers, graph neural networks, recommendation systems, state-space models. Covers cutting-edge advances such as accelerator systems for federated, on-device and graph learning and industrial case studies. Also covers various important topics in the ML accelerator system design such as execution cost estimation, mapping and hardware exploration, compilers and ISAs for ML accelerators, multi-chip/multi-workload designs, accelerator-aware neural architecture search, and reliability and security of ML accelerators. A background in computer architecture and machine learning is advantageous.