News for hackers. Stuff that matters.
Re:Neural network chip built using memristors by p1esk on Thursday May 07, 2015 @03:37AM (#9503741)
Building a hardware convnet is only beneficial when you figured out the exact parameters of the network. Everything is hardwired. Therefore, it's useless if you want to experiment with lots of different parameters, tricks, or architectures to "advance the field".

Moreover, building such a chip is an expensive and long process, and given how fast GPUs are improving, it's not clear that by the time you build it, it will still be competitive.

Finally, if you want to speed up training, try to figure out a better algorithm. For example, humans can learn from very few training examples. Current neural networks need many thousands, or even millions. There's a potential million-fold speed up in training time right here - and to find it, you need the flexibility of the software.

Re:Neural network chip built using memristors by sushirain on Thursday May 07, 2015 @04:34PM (#9508096)
Maybe the brain can do one shot learning only after it has trained for years?
Re:Neural network chip built using memristors by p1esk on Thursday May 07, 2015 @05:25PM (#9508411)
Maybe. We want to reduce the amount of supervised training. I think that's what Hinton is trying to do with his capsules.