Explore knowledge distillation techniques in this lecture from MIT's EfficientML.ai course (6.5940, Fall 2023). Delve into the concept of transferring knowledge from a large, complex model to a smaller, more efficient one. Learn how this process can maintain performance while reducing computational requirements. Examine various distillation methods, their applications in machine learning, and their impact on model efficiency. Gain insights from Prof. Song Han's expertise in the field of efficient machine learning. Access comprehensive slides and additional resources to enhance your understanding of this crucial topic in AI optimization.
Overview
Syllabus
EfficientML.ai Lecture 9 - Knowledge Distillation (MIT 6.5940, Fall 2023)
Taught by
MIT HAN Lab
Related Courses
-
Quantization for Efficient Machine Learning - Part II
-
Pruning and Sparsity in Machine Learning - Part II (EfficientML.ai Lecture 4)
-
EfficientML.ai: Introduction to Efficient Machine Learning - Lecture 1
-
EfficientML.ai: Introduction to Efficient Machine Learning - Lecture 1
-
EfficientML.ai: Introduction to Efficient Machine Learning - Lecture 1
-
Pruning and Sparsity in Machine Learning - Lecture 3
