Stanford University public Class machine learning: Neural Networks learning-autonomous Driving example (automatic driving example via neural network)

The use of neural networks to achieve autonomous driving, which means that the car through learning to drive themselves.

It is a legend explaining how to realize automatic driving through neural network learning:

The lower left corner is an image of the road ahead that the car sees. Left, you can see a horizontal menu bar (the direction indicated by the number 4), and the white section shows the direction the human driver chooses. The right-hand side corresponds to the right-pressing operation (Arrow 3), and the center is slightly to the left (Arrow 2), which means that at this point the human driver's operation is slowly turning left. The second part of the picture (arrow 5) corresponds to the Learning algorithm to select the driving direction, similar to the white section (arrow 6) shows that the neural network here is the choice of driving direction is a little left, in fact, before the neural network began to learn, you will see the network output is a gray section (arrow 7), The gray area shows that the neural network has been initialized randomly, and we don't know how the car is going when it is initialized, or we don't know where the driving direction is, only after the learning algorithm has been running long enough that the white section appears in the entire gray area, showing a specific direction of travel. This means that the neural network algorithm at this time has chosen a clear direction of travel, not like the beginning of the output of a faint light gray area, but the output of a white section.

Stanford University public Class machine learning: Neural Networks learning-autonomous Driving example (automatic driving example via neural network)