Systems and Methods for Activation Functions for Photonic Neural Networks

Stanford researchers have developed an electro-optic hardware platform for nonlinear activation functions in optical neural networks. By converting a small portion of the input optical signal into an analog electric signal, linear optical neural networks can be made to be non-linear, enabling the network to have greater capability to model complex functions (e.g. machine learning tasks) without loss of processing speed.
This scheme allows for complete nonlinear on-off contrast in transmission at relatively low optical power thresholds and eliminates the requirement of having additional optical sources between each layer of the network. Moreover, the activation function is reconfigurable via electrical bias, allowing it to be programmed or trained to synthesize a variety of nonlinear responses.

Stage of Development