An accelerator for modern convolutional neural networks applies the Winograd filtering algorithm in a wavelength division multiplexing integrated photonics circuit modulated by a memristor-based analog memory unit.

An accelerator for modern convolutional neural networks applies the Winograd filtering algorithm in a wavelength division multiplexing integrated photonics circuit modulated by a memristor-based analog memory unit.

An imaging device connected to a neural network is provided. An imaging device having a neuron in a neural network includes a plurality of first pixels, a first circuit, a second circuit, and a third circuit. Each of the plurality of first pixels includes a photoelectric conversion element. The plurality of first pixels is electrically connected to the first circuit. The first circuit is electrically connected to the second circuit. The second circuit is electrically connected to the third circuit. Each of the plurality of first pixels generates an input signal of the neuron. The first circuit, the second circuit, and the third circuit function as the neuron. The third circuit includes an interface connected to the neural network.

An optical neural network apparatus that optically implements an artificial neural network includes an input layer, a hidden layer, and an output layer sequentially arranged in a traveling direction of light, wherein the output layer includes an image sensor including a plurality of light sensing pixels arranged in two dimensions, and wherein the input layer or the hidden layer includes at least one passive phase modulator configured to locally modulate a phase of incident light depending on positions on a two dimensional plane.

An optical computing apparatus and system and a computing method are provided. The optical computing apparatus includes a linear operation module, a first delay module, and a coupler. The linear operation module can modulate, based on received electrical signals, optical signals input to the linear operation module; the first delay module may adjust a delay of optical signals output by the linear operation module; and after the first delay module adjusts the delay of the optical signals output by the linear operation module, the coupler may combine a plurality of groups of optical signals successively output by the linear operation module, to output one group of optical signals used to indicate a computing result that is obtained after a multiply-add operation is performed on one group of data and weights.

An optical computing apparatus and system and a computing method are provided. The optical computing apparatus includes a linear operation module, a first delay module, and a coupler. The linear operation module can modulate, based on received electrical signals, optical signals input to the linear operation module; the first delay module may adjust a delay of optical signals output by the linear operation module; and after the first delay module adjusts the delay of the optical signals output by the linear operation module, the coupler may combine a plurality of groups of optical signals successively output by the linear operation module, to output one group of optical signals used to indicate a computing result that is obtained after a multiply-add operation is performed on one group of data and weights.

The present disclosure relates to semiconductor structures and, more particularly, to optical neuro-mimetic devices and methods of manufacture. The structure includes: a plurality of photodetectors and electrical circuitry that converts photocurrent generated from the photodetectors into electrical current and then sums up the electrical current to mimic neural functionality.

The present disclosure relates to semiconductor structures and, more particularly, to optical neuro-mimetic devices and methods of manufacture. The structure includes: a plurality of photodetectors and electrical circuitry that converts photocurrent generated from the photodetectors into electrical current and then sums up the electrical current to mimic neural functionality.

A digital signal modulation method for a photon artificial intelligence computing chip, including: modulating one or more groups of digital electrical signals into optical signals; where the group of digital electrical signals comprises several timing signals being outputted in sequence in a channel within a fixed period; where each timing signal has the same base clock and signal time length; where each timing signal conveying N-bit digital information has 2.sup.N−1 base clocks, the number of the base clocks of a high-level signal or the number of a digital signal “1” in the timing signal is a signal value of the timing signal, and the signal value is equal to a value of the N-bit digital information being transmitted; and where the timing signal is a modulating signal for converting the electrical signal to the optical signal. Compared with the existing calculation scheme based on digital-to-analog conversion and analog signal modulation, the calculation scheme in the present invention avoids using a digital-to-analog converter with a high cost and power consumption, can be directly connected with the digital signals of the electronic chip, and avoids quantization error during the digital-to-analog conversion of digital signals.

Various embodiments provide for computational systems including multiple circuit packages, each circuit package comprising an electronic integrated circuit having multiple processing elements and intra-chip bidirectional photonic channels connecting the processing elements into an electro-photonic network, with inter-chip bidirectional photonic channels connecting the processing elements across the electro-photonic networks of the multiple circuit packages into a larger electro-photonic network.