AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is Back Propagation Going Away?
Jeff Hinton suggests that we need to throw away back propagation and start all over. What could an alternative direction of training neural networks look like? I don't know that backprop is going to go away entirely, but it's not on the critical path to research for improving AI. We might find some way of customizing one of these algorithms to do something really interesting at the level of cognition or short-term memory.