Pruning and Sparsity in Machine Learning - Part II - Lecture 4

Dive into advanced concepts of pruning and sparsity in machine learning with this lecture from MIT's 6.5940 course. Explore cutting-edge techniques for model compression and efficiency optimization as Prof. Song Han delves deeper into the subject. Learn about the latest research and practical applications of pruning methods to create more efficient neural networks. Gain insights into advanced sparsity techniques that can significantly reduce model size and computational requirements without sacrificing performance. Enhance your understanding of efficient machine learning algorithms and their implementation in real-world scenarios. Access accompanying slides for a comprehensive learning experience in this hour-long session from the MIT HAN Lab.

EfficientML.ai Lecture 4 - Pruning and Sparsity Part II (MIT 6.5940, Fall 2024)