Local Response Normalization for Deep Learning Explained

Local Response Normalization (LRN) is a technique of brightness normalization that helps convolutional neural network learn from visual inputs. Here it is explained and linked to its biological correspondence "Lateral Inhibition"! ## Table of Content - Introduction: 0:00 - Local Response Normalization Formula: 0:38 - Lateral Inhibition Overview: 3:22 - Lateral Inhibition in the Retina: 4:22 - Conclusion: 10:11 ## References: - AlexNet paper: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf - Lateral Inhibition in outer retina: https://www-ncbi-nlm-nih-gov.proxy3.library.mcgill.ca/pmc/articles/PMC6665510/ - Lateral Inhibition in inner retina: https://www-nature-com.proxy3.library.mcgill.ca/articles/nn1298_714 - Good review of the role of inhibition in the brain: https://www-ncbi-nlm-nih-gov.proxy3.library.mcgill.ca/pmc/articles/PMC3236361/ - How the photoreceptors actually works: https://www-ncbi-nlm-nih-gov.proxy3.library.mcgill.ca/books/NBK10806/ ---- Join the Discord for general discussion: https://discord.gg/QpkxRbQBpf ---- Follow Me Online Here: Twitter: https://twitter.com/CodeThisCodeTh1 GitHub: https://github.com/yacineMahdid LinkedIn: https://www.linkedin.com/in/yacine-mahdid-809425163/ Instagram: https://www.instagram.com/yacine_mahdid/ ___ Have a great week! 👋