Overview
Explore neural architecture search techniques and their applications in this lecture from MIT's course on TinyML and Efficient Deep Learning Computing. Dive into hardware-aware neural architecture search, which considers hardware performance metrics like latency when designing neural network architectures. Learn about the joint optimization of hardware and neural architectures within a single search loop. Discover various applications leveraging neural architecture search, including the Once-For-All Network approach. Gain insights into efficient machine learning techniques for deploying powerful deep learning applications on resource-constrained devices such as mobile phones and IoT devices. Access accompanying slides and additional course materials to enhance your understanding of these cutting-edge concepts in efficient machine learning.
Syllabus
Lecture 08 - Neural Architecture Search (Part II) | MIT 6.S965
Taught by
MIT HAN Lab