So this is what all the fuss is about. These things gather data and appear to learn. They were inspired by biological neurons, but are really not anything like a real neuron, either in structure or in the way the exact way they learn. We are still learning about their biological details.
Quanta Mag piece on Deep Learning, which describes the basics. Some of the history. This reminds me of when we were first introduced to the idea, and they were just called ANN or Artificial Neural Networks. And there was less worry about the architecture, or how the data would be effectively applied. Now they have matured.
A quite non technical piece that introduces the concept, and a bit of the method.
How to Win at Deep Learning By Pradeep Mutalik In Quanta Magazine
What happens when you increase the number of layers in an artificial neural network? ... "
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment