Analog Neural Computing With Super-Resolution Memristor Crossbars

Pilot assisted readout for passive memristor crossbars

The high demands for performance and energy efficiency pose significant challenges for computational systems. Memristor-based crossbar architectures are actively considered as vital rivals for the traditional solutions. Nonetheless, density and energy driven passive array structures, that lack a switching control per cell, suffer from sneak paths that limit the range of accurate operation of th...

Current-mode Memristor Crossbars for Neuromemristive Systems

Motivated by advantages of current-mode design, this brief contribution explores the implementation of weight matrices in neuromemristive systems via current-mode memristor crossbar circuits. After deriving theoretical results for the range and distribution of weights in the current-mode design, it is shown that any weight matrix based on voltage-mode crossbars can be mapped to a current-mode c...

Computing on Analog Neural Nets with Arbitrary Real Weights

Audio Super-resolution Using Neural Nets

We propose a neural network-based technique for enhancing the quality of audio signals such as speech or music by transforming inputs encoded at low sampling rates into higher-quality signals with an increased resolution in the time domain. This amounts to generating the missing samples within the low-resolution signal in a process akin to image super-resolution. On standard speech and music da...

Audio Super Resolution using Neural Networks

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time, it predicts missing samples within a low-resolution signal in an interpolation process similar to image super-resolution. Our method is simple and does not i...