Skip to main content

Knowledge Distillation in Neural Networks - Explained!

CodeEmporiumMarch 16, 202613:25ai_ml_education

Summary

This video explains Knowledge Distillation in neural networks, detailing what it is, why it's used, and how it functions. It's highly relevant for students learning advanced AI/ML concepts, providing in-depth knowledge on model compression and optimization techniques.

Description

In this video, we take a look at Knowledge Distillation. What is it? Why do we have it? How does it work? ABOUT ME โญ• Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1 ๐Ÿ“š Medium Blog: https://medium.com/@dataemporium ๐Ÿ’ป Github: https://github.com/ajhalthor ๐Ÿ‘” LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/ RESOURCES [1 ๐Ÿ“š] Slides: https://link.excalidraw.com/p/readonly/rBinJxKL9ogituDfxqJn [2 ๐Ÿ“š] 2006 paper that introduced Model Compression: https://www.cs.cornell.edu/~caruana/compression.kdd06.pdf?utm_source=chatgpt.com [3 ๐Ÿ“š] 2014 paper that transfers dark knowledge: https://arxiv.org/pdf/1312.6184 [4 ๐Ÿ“š] 2015 paper on knowledge distillation (main paper): https://arxiv.org/pdf/1503.02531 PLAYLISTS FROM MY CHANNEL โญ• Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS--NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8 Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc โญ• Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE โญ• ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ โญ• Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74 โญ• The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h โญ• Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V โญ• Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD MATH COURSES (7 day free trial) ๐Ÿ“• Mathematics for Machine Learning: https://imp.i384100.net/MathML ๐Ÿ“• Calculus: https://imp.i384100.net/Calculus ๐Ÿ“• Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics ๐Ÿ“• Bayesian Statistics: https://imp.i384100.net/BayesianStatistics ๐Ÿ“• Linear Algebra: https://imp.i384100.net/LinearAlgebra ๐Ÿ“• Probability: https://imp.i384100.net/Probability OTHER REL