Computer Vision's Giant Leaps - by Jack Lynch - Errata

From feline cortices to self-driving cars

L2R: Feline neuronal activity, the Neurocognitron, and the down-convs of a U-Net. There are a million how-to’s introducing convolutional neural networks, their high-level principles, and their implementation. (In my opinion, the best introductions can be found here, here, and here.) But where did they come from? Let’s run through a few of the boldest steps computer vision took from its inspiration in feline cortices to its application in self-driving cars. These ideas might be older than you think! Hubel, Weisel and the Visual Cortex (1959) The Mighty Neurocognitron (1980) LeCun…

related reading

• Convolutional Neural Networks, Explained | Towards Data Sciencetowardsdatascience.com
• CS231n Deep Learning for Computer Visioncs231n.github.io
• A Beginner's Guide To Understanding Convolutional Neural Networks – Adit Deshpande – Engineering at Forward | UCLA CS '19adeshpande3.github.io
• ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc
• The Decade of Deep Learning | Leo Gaobmk.sh
• A Recipe for Training Neural Networkskarpathy.github.io
• Feature Visualizationdistill.pub
• neural netpeople.eecs.berkeley.edu
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• A Recipe for Training Neural Networkskarpathy.github.io
• AlexNet and ImageNet: The Birth of Deep Learningpinecone.io
• Convolution Vs Correlation | Towards Data Sciencetowardsdatascience.com