ARTIFICIAL NEURAL NETWORK WITH TRAINABLE ACTIVATION FUNCTIONS AND FRACTIONAL DERIVATIVE VALUES

摘要

Systems, devices and methods can provide a technology that adapts a plurality of weights in a neural network model and adapts a plurality of activation functions in the neural network model. The technology can also output the neural network model in response to one or more conditions that are satisfied by the plurality of weights and the plurality of activation functions. In one example, two or more of the activation functions are different from each other and the activation functions are adapted on a per-neuron basis.