Neural Networks for Transforming Signals

摘要

A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trined to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.

主权项

1. A method for transforming input signals, comprising the steps of:
defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters; defining an iterative inference procedure derived from the model and the set of model parameters; unfolding the iterative inference procedure into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers; forming a neural network by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer; training the neural network to obtain a trained neural network; and transforming the input signals using the trained neural network to obtain output signals, wherein the steps are performed in a processor.