Back to timeline

Research · June 2012

The Google network that found cats

A network with a billion connections, trained on YouTube frames with no labels at all, produced a neuron of its own that responds to cat faces.

Why it matters

Unsupervised learning at sufficient scale generated meaningful concepts by itself, a result that reached every newspaper.

Training ran three days across a thousand machines with sixteen thousand cores. Besides cats the network produced face and human body detectors. The work showed that features need not be specified when data and computation suffice. The same year AlexNet proved the same point on a labelled set with far less hardware, and the cheaper route through graphics processors is the one that became the main line.

Event record

Event date
June 2012
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0222

Presented at ICML in June 2012; preprint December 2011.

Sources

Related events