How Deep Lear ning Works in Three Figures? We understand that machine learning is about mapping inputs to targets . This is done by observing many examples of input and targets. We also know that de ep neural networks do this input-to-target mapping via a deep sequence of simple data transformations. These are layers that these data transformations are lear ned by exposure to examples. How this learning happens? What a layer does to its input data specification is stored in the layer’s weights . The layer's weights in essence are a bunc h of numbers. W e’d say that the transformation implemented by a layer is parameterized by its weights. Sometimes the weights are called parameters of layers. L earning have to means finding a set of values for the weights of all layers in a network. For instance, the network will correctly map example inputs to their associated targets. A deep neural networ k may contain tens of millions of parameters. It is difficult