Building kit for artificial neural networks. Use a single "Layer" sprite to make a classical Rosenblatt perceptron. Duplicate the Layer sprite - several times - and adjust the receivers in the broadcast blocks to create deep neural networks. User the setup script to customize the network's topology and learning rate.data:image/png;base64,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Building kit for artificial neural networks. Use a single "Layer" sprite to make a classical Rosenblatt perceptron. Duplicate the Layer sprite - several times - and adjust the receivers in the broadcast blocks to create deep neural networks. User the setup script to customize the network's topology and learning rate.

draw a list of numbers as vertical lines distributed evenly across the stage.

de:male Balken _ gefüllt _ zentriert _ 0.8single=0.8 pan=1 overlap=1.2false

data:image/png;base64,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0,0,01,0,11,1,00.5