Google Tech Talks November, 29 2007 In the 1980's, new learning algorithms for neural networks promised to solve difficult classification tasks, like speech or object recognition, by learning many layers of non-linear features. The results were disappointing for two reasons: There was never enough labeled data to learn millions of complicated features and the learning was much too slow in deep
![The Next Generation of Neural Networks](https://cdn-ak-scissors.b.st-hatena.com/image/square/66dc02a9f9aa08e979fe8f75955fe9557c5e19fc/height=288;version=1;width=512/https%3A%2F%2Fi.ytimg.com%2Fvi%2FAyzOUbkUf3M%2Fhqdefault.jpg)