Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.