Reduction in the number of neurons and axons in a neurosynaptic network while maintaining its functionality is provided. A neural network description describing a neural network is read. One or more functional unit of the neural network is identified. The one or more functional unit of the neural network is optimized. An optimized neural network description is written based on the optimized functional unit.

An understanding model is trained to account for human perception of the perceived relative importance of different tagged items (e.g. slot/intent/domain). Instead of treating each tagged item as equally important, human perception is used to adjust the training of the understanding model by associating a perceived weight with each of the different predicted items. The relative perceptual importance of the different items may be modeled using different methods (e.g. as a simple weight vector, a model trained using features (lexical, knowledge, slot type, . . . ), and the like). The perceptual weight vector and/or or model are incorporated into the understanding model training process where items that are perceptually more important are weighted more heavily as compared to the items that are determined by human perception as less important.

Features are disclosed for identifying randomized latent feature language modeling, such as a recurrent neural network language modeling (RNNLM). Sequences of item identifiers may be provided as the language for training the language model where the item identifiers are the words of the language. To avoid localization bias, the sequences may be randomized prior to or during the training process to provide more accurate prediction models.

A method includes inputting, via a first position adjustment optical structure, adjustment signal light into a second position adjustment optical structure. A first light diffraction element of an optical computing device includes a first computing optical structure constituted by microcells, and the first position adjustment optical structure. A second light diffraction element of the optical computing device includes a second computing optical structure constituted by microcells, and the second position adjustment optical structure. The method includes adjusting, based on the adjustment signal light outputted from the second position adjustment optical structure, a position of the second light diffraction element with respect to the first light diffraction element.

A method includes inputting, via a first position adjustment optical structure, adjustment signal light into a second position adjustment optical structure. A first light diffraction element of an optical computing device includes a first computing optical structure constituted by microcells, and the first position adjustment optical structure. A second light diffraction element of the optical computing device includes a second computing optical structure constituted by microcells, and the second position adjustment optical structure. The method includes adjusting, based on the adjustment signal light outputted from the second position adjustment optical structure, a position of the second light diffraction element with respect to the first light diffraction element.

Systems and methods for distributed training of deep learning models are disclosed. An example local device to train deep learning models includes a reference generator to label input data received at the local device to generate training data, a trainer to train a local deep learning model and to transmit the local deep learning model to a server that is to receive a plurality of local deep learning models from a plurality of local devices, the server to determine a set of weights for a global deep learning model, and an updater to update the local deep learning model based on the set of weights received from the server.

An optical computing device includes a control system, a light field modulation system, an optical computing system, and a light field detection system. The control system converts input data into complex amplitude-light field mapping information that is information representing an amplitude and/or a phase. The light field modulation system represents the input data based on an optical signal that is output based on the complex amplitude-light field mapping information obtained in the conversion procedure. A first computing result is generated based on the optical signal that represents the input data with high precision to complete optical computing.

An optical computing device includes a control system, a light field modulation system, an optical computing system, and a light field detection system. The control system converts input data into complex amplitude-light field mapping information that is information representing an amplitude and/or a phase. The light field modulation system represents the input data based on an optical signal that is output based on the complex amplitude-light field mapping information obtained in the conversion procedure. A first computing result is generated based on the optical signal that represents the input data with high precision to complete optical computing.

Systems and methods relate to selectively arranging a plurality of qubits into a spatial structure to encode a quantum computing problem. Exemplary arrangement techniques can be applied to encode various quantum computing problems. The plurality of qubits can be driven according to various driving techniques into a final state. The final state can be measured to identify an exact or approximate solution to the quantum computing problem.

Systems and methods relate to selectively arranging a plurality of qubits into a spatial structure to encode a quantum computing problem. Exemplary arrangement techniques can be applied to encode various quantum computing problems. The plurality of qubits can be driven according to various driving techniques into a final state. The final state can be measured to identify an exact or approximate solution to the quantum computing problem.