Tesco
The Deep Learning Revolution
Book

The Deep Learning Revolution

Artificial Intelligence Meets Human Intelligence

Terrence J. Sejnowski
MIT Press, 2018

Read or listen offline

  • 0.5×
  • 0.75×
  • 1×
  • 1.25×
  • 1.5×
  • 1.75×
1×

Editorial Rating

8

Qualities

  • Scientific
  • Visionary
  • Concrete Examples

Recommendation

Artificial neural networks can learn. Artificial intelligence luminary Terrence J. Sejnowski details his and his colleagues’ deep-learning research achievements during their three-decade campaign against the notion that computers can’t simulate brains. By combining discoveries in neuroscience and biology with new learning algorithms, researchers can use the brain to teach networks and then use the networks to teach people about their brains. “Deep learning” – a form of machine learning – will dominate the 21st century, answering the most puzzling questions about consciousness and challenging everyone to keep learning.

Take-Aways

  • “Deep learning” is based on artificial neural networks, which simulate how the brain learns through experience.
  • The first artificial neural network involved a “perceptron,” which weighs inputs and outputs, similar to how a brain neuron functions.
  • The Hopfield net and the Boltzmann machine expanded artificial neural networks and made them more efficient.

About the Author

Terrence J. Sejnowski, PhD, teaches at the Salk Institute for Biological Studies, where he is director of the Computational Neurobiology Laboratory, and is director of the Crick-Jacobs Center for Theoretical and Computational Biology.

Comment on this summary or Comenzar discusión