Neural Networks Can Herd Cats

Picking images of cats out of YouTube videos was one of the first breakthrough demonstrations of deep learning.

Andrew Ng’s breakthrough work at Google was to take neural networks and make them huge, increasing the layers and the neurons, and then run massive amounts of data through the system to train it. In Ng’s case it was images from 10 million YouTube videos. Ng put the “deep” in deep learning, which describes all the layers in these neural networks.

Today, image recognition by machines trained via deep learning in some scenarios is better than humans, including identifying indicators for cancer in blood and tumors in MRI scans. In the Asian game of Go, Google’s AlphaGo defeated Korean Go master Lee Sedol in five matches. It learned the game and trained for its Go match—it tuned its neural network—by playing against itself over and over and over.²⁶

After the match, the official Korean Go (Paduk) Association awarded AlphaGo the highest Go grandmaster rank—an “honorary 9 dan”—in recognition of AlphaGo’s “sincere efforts” to master Go.²⁷

When did machines become sincere?