A Neural Network That Just Makes Random Predictions

The AI researchers worked out a way to build a network and to build the predictive network. If an output was wrong, they had to tweak all of these things manually to try to make it make it more right. But this guy named Jeff Hinton came up with applying what's called back propagation to the network. And depending on how wrong that prediction is from the known output from the truth, it goes back through each layer and each node of the network and just tweaks each node to make the prediction a little bit less wrong.