deep neural network
An artificial neural network with more than two hidden layers between its input and output, enabling it to learn complex representations from large datasets.
As defined in 68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense
Where it comes up · 3
- Gerd Gigerenzer on How to Stay Smart in a Smart World2 claims
- 68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense2 claims
- Lex Fridman Podcast #14 - Kyle Vogt1 claim
Most important claims · 5 of 5Search all claims for “deep neural network” →
- Deep neural networks trained on big data with fast parallel computers have achieved huge success but only in narrow areas such as speech recognition, object recognition, and face recognition, and people are increasingly seeing their limitations.68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense
- Deep neural networks are statistical machines that excel at finding correlations—essentially a powerful version of non-linear multiple regression or discriminant analysis—and finding correlations is not the greatest ability of the human mind, which instead is strong in causal stories.Gerd Gigerenzer on How to Stay Smart in a Smart World
- Artificial intelligence as instantiated in deep neural networks lacks common sense—it cannot easily learn concepts the way a child can (a child grasps 'school bus' in one or two pointings, while a network needs 10,000 images), nor does it possess intuitive psychology or intuitive physics, making common sense a major unsolved challenge in AI.Gerd Gigerenzer on How to Stay Smart in a Smart World
- A deep neural network is simply a neural network with more than two hidden layers; the word 'deep' refers to architectural depth, not profundity of thought.68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense
- Vogt's first lane-following prototype ran on a 233 MHz Pentium and was likely written in interpreted BASIC, which left no computational room for deep neural networks at the time.Lex Fridman Podcast #14 - Kyle Vogt