Deep Learning

CNN

Convolutional networks slide small filters over an image to learn edges, then shapes, then objects.

A convolution applies the same small filter across the whole image, so a feature learned in one corner is recognised everywhere. Stacking convolutions with pooling builds a hierarchy from edges up to whole objects.

Weight sharing makes them dramatically more efficient than fully connected layers on images, and the same idea transfers to audio spectrograms and to any signal with local structure.

Also in Deep Learning

RNN LSTM Transformers Auto Encoders Deep RL Epochs

Apply

Begin the first module

Become AI native, it is the real deal today, and if it is not for you, you have lost nothing but learnt a new skill.

Apply