Sunday, May 9, 2021

How Many Computers to Identify a Cat? 16,000

The New York Times: Researchers from Google’s X Lab connected 16,000 processors into one of the largest neural networks for machine learning ever created. Modeled on the human brain, the system was capable of teaching itself new things, so the researchers turned it loose on images from YouTube to see what it would learn. Like a lot of humans, the neural network spent a lot of time looking at cats. Eventually, it taught itself to recognize cats–and 19,999 other items–with surprising accuracy.

“We never told it during the training, ‘This is a cat,'” explained Google fellow Jeff Dean. “It basically invented the concept of a cat.”

Similar articles

Latest Articles

Top 10 Professional Services...

These are some of the best PSA tools for organizations of all sizes. What Is Professional Services Automation Software? Professional services automation (PSA) software aims to...

What is Data Aggregation?

Data aggregation is the process where raw data is gathered and presented in a summarized format for statistical analysis. The data may be gathered...

Dell APEX: Our...

One of the missteps IBM made last century was collapsing their sales model, which was services based, to generate a short-term revenue spike. Up...

Companies that Scaled Technology...

NEW YORK — Companies that “doubled down” on their investment in mostly data-heavy technology during the COVID-19 pandemic have seen their revenue grow five...