Abstract: Systems for neural network computation are provided. A neural network processor comprises a plurality of neural cores. The neural network processor has one or more processor precisions per activation. The processor is configured to accept data having a processor feature dimension. A transformation circuit is coupled to the neural network processor, and is adapted to: receive an input data tensor having an input precision per channel at one or more features; transform the input data tensor from the input precision to the processor precision; divide the input data into a plurality of blocks, each block conforming to one of the processor feature dimensions; provide each of the plurality of blocks to one of the plurality of neural cores. The neural network processor is adapted to compute, by the plurality of neural cores, output of one or more neural network layers.

Abstract: Networks for distributing parameters and data to neural network compute cores. In various embodiments, a neural inference chip comprises a plurality of neural cores and at least one network interconnecting the plurality of neural cores. Each of the plurality of neural cores is adapted to apply a plurality of synaptic weights to a plurality of input activations to produce a plurality of output activations. The at least one network is adapted to simultaneously deliver synaptic weights and/or input activations to the plurality of neural cores.

Abstract: Defect resistant designs for location-sensitive neural network processor arrays are provided. In various embodiments, plurality of neural network processor cores are arrayed in a grid. The grid has a plurality of rows and a plurality of columns. A network interconnects at least those of the plurality of neural network processor cores that are adjacent within the grid. The network is adapted to bypass a defective core of the plurality of neural network processor cores by providing a connection between two non-adjacent rows or columns of the grid, and transparently routing messages between the two non-adjacent rows or columns, past the defective core.

Abstract: Hardware neural network processors, are provided. A neural core includes a weight memory, an activation memory, a vector-matrix multiplier, and a vector processor. The vector-matrix multiplier is adapted to receive a weight matrix from the weight memory, receive an activation vector from the activation memory, and compute a vector-matrix multiplication of the weight matrix and the activation vector. The vector processor is adapted to receive one or more input vector from one or more vector source and perform one or more vector functions on the one or more input vector to yield an output vector. In some embodiments a programmable controller is adapted to configure and operate the neural core.

Abstract: Neural network processing hardware using parallel computational architectures with reconfigurable core-level and vector-level parallelism is provided. In various embodiments, a neural network model memory is adapted to store a neural network model comprising a plurality of layers. Each layer has at least one dimension and comprises a plurality of synaptic weights. A plurality of neural cores is provided. Each neural core includes a computation unit and an activation memory. The computation unit is adapted to apply a plurality of synaptic weights to a plurality of input activations to produce a plurality of output activations. The computation unit has a plurality of vector units. The activation memory is adapted to store the input activations and the output activations. The system is adapted to partition the plurality of cores into a plurality of partitions based on dimensions of the layer and the vector units.

Abstract: Instruction distribution in an array of neural network cores is provided. In various embodiments, a neural inference chip is initialized with core microcode. The chip comprises a plurality of neural cores. The core microcode is executable by the neural cores to execute a tensor operation of a neural network. The core microcode is distributed to the plurality of neural cores via an on-chip network. The core microcode is executed synchronously by the plurality of neural cores to compute a neural network layer.

Abstract: Hardware neural network processors, are provided. A neural core includes a weight memory, an activation memory, a vector-matrix multiplier, and a vector processor. The vector-matrix multiplier is adapted to receive a weight matrix from the weight memory, receive an activation vector from the activation memory, and compute a vector-matrix multiplication of the weight matrix and the activation vector. The vector processor is adapted to receive one or more input vector from one or more vector source and perform one or more vector functions on the one or more input vector to yield an output vector. In some embodiments a programmable controller is adapted to configure and operate the neural core.

Abstract: High dynamic range, high class count, high input rate winner-take-all on neuromorphic hardware is provided. In some embodiments, a plurality of thermometer codes are received by a neurosynaptic core. The plurality of thermometer codes are split into a plurality of intervals. One of the plurality of intervals is selected. A local maximum is determined within the one of the plurality of intervals. A global maximum is determined based on the local maximum.

Abstract: Hardware neural network processors, are provided. A neural core includes a weight memory, an activation memory, a vector-matrix multiplier, and a vector processor. The vector-matrix multiplier is adapted to receive a weight matrix from the weight memory, receive an activation vector from the activation memory, and compute a vector-matrix multiplication of the weight matrix and the activation vector. The vector processor is adapted to receive one or more input vector from one or more vector source and perform one or more vector functions on the one or more input vector to yield an output vector. In some embodiments a programmable controller is adapted to configure and operate the neural core.

Abstract: Neural inference chips for computing neural activations are provided. In various embodiments, the neural inference chip is adapted to: receive an input activation tensor comprising a plurality of input activations; receive a weight tensor comprising a plurality of weights; Booth recode each of the plurality of weights into a plurality of Booth-coded weights, each Booth coded value having an order; multiply the input activation tensor by the Booth coded weights, yielding a plurality of results for each input activation, each of the plurality of results corresponding to the orders of the Booth-coded weights; for each order of the Booth-coded weights, sum the corresponding results, yielding a plurality of partial sums, one for each order; and compute a neural activation from a sum of the plurality of partial sums.

Abstract: A device for controlling neural inference processor cores is provided, including a compound instruction set architecture. The device comprises an instruction memory, which comprises a plurality of instructions for controlling a neural inference processor core. Each of the plurality of instructions comprises a control operation. The device further comprises a program counter. The device further comprises at least one loop counter register. The device is adapted to execute the plurality of instructions. Executing the plurality of instructions comprises: reading an instruction from the instruction memory based on a value of the program counter; updating the at least one loop counter register according to the control operation of the instruction; and updating the program counter according to the control operation of the instruction and a value of the at least one loop counter register.

Abstract: Embodiments of the invention relate to a scalable neural hardware for the noisy-OR model of Bayesian networks. One embodiment comprises a neural core circuit including a pseudo-random number generator for generating random numbers. The neural core circuit further comprises a plurality of incoming electronic axons, a plurality of neural modules, and a plurality of electronic synapses interconnecting the axons to the neural modules. Each synapse interconnects an axon with a neural module. Each neural module receives incoming spikes from interconnected axons. Each neural module represents a noisy-OR gate. Each neural module spikes probabilistically based on at least one random number generated by the pseudo-random number generator unit.

Abstract: Parallel processing among arrays of physical neural cores is provided. An array of neural cores is adapted to compute, in parallel, an output activation tensor of a neural network layer. A network is operatively connected to each of the neural cores. The output activation tensor is distributed across the neural cores. An input activation tensor is distributed across the neural cores. A weight tensor is distributed across the neural cores. Each neural core's computation comprises multiplying elements of a portion of the input activation tensor at that core with elements of a portion of the weight tensor at that core, and storing the summed products in a partial sum corresponding to an element of the output activation tensor. Each element of the output activation tensor is computed by accumulating all of the partial sums corresponding to that element via the network.

Abstract: Embodiments of the invention provide a computer-readable medium of visual saliency estimation comprising receiving an input video of image frames. Each image frame has one or more channels, and each channel has one or more pixels. The computer-readable medium further comprises, for each channel of each image frame, generating corresponding neural spiking data based on a pixel intensity of each pixel of the channel, generating a corresponding multi-scale data structure based on the corresponding neural spiking data, and extracting a corresponding map of features from the corresponding multi-scale data structure. The multi-scale data structure comprises one or more data layers, wherein each data layer represents a spike representation of pixel intensities of a channel at a corresponding scale. The computer-readable medium further comprises encoding each map of features extracted as neural spikes.

Abstract: Hardware placement of neural networks is provided. In various embodiments, a network description is read. The network description describes a spiking neural network. The neural network is trained. An initial placement of the neural network on a plurality of cores is performed. The cores are located on a plurality of chips. Inter-chip communications are measured based on the initial placement. A final placement of the neural network on the plurality of cores is performed based on the inter-chip communications measurements and the initial placement. The final placement reduces inter-chip communication.

Abstract: Embodiments of the invention provide a method comprising receiving a set of features extracted from input data, training a linear classifier based on the set of features extracted, and generating a first matrix using the linear classifier. The first matrix includes multiple dimensions. Each dimension includes multiple elements. Elements of a first dimension correspond to the set of features extracted. Elements of a second dimension correspond to a set of classification labels. The elements of the second dimension are arranged based on one or more synaptic weight arrangements. Each synaptic weight arrangement represents effective synaptic strengths for a classification label of the set of classification labels. The neurosynaptic core circuit is programmed with synaptic connectivity information based on the synaptic weight arrangements. The core circuit is configured to classify one or more objects of interest in the input data.

Abstract: Massively parallel neural inference computing elements are provided. A plurality of multipliers is arranged in a plurality of equal-sized groups. Each of the plurality of multipliers is adapted to, in parallel, apply a weight to an input activation to generate an output. A plurality of adders is operatively coupled to one of the groups of multipliers. Each of the plurality of adders is adapted to, in parallel, add the outputs of the multipliers within its associated group to generate a partial sum. A plurality of function blocks is operatively coupled to one of the plurality of adders. Each of the plurality of function blocks is adapted to, in parallel, apply a function to the partial sum of its associated adder to generate an output value.

Abstract: A multiplexed neural core circuit according to one embodiment comprises, for an integer multiplexing factor T that is greater than zero, T sets of electronic neurons, T sets of electronic axons, where each set of the T sets of electronic axons corresponds to one of the T sets of electronic neurons, and a synaptic interconnection network comprising a plurality of electronic synapses that each interconnect a single electronic axon to a single electronic neuron, where the interconnection network interconnects each set of the T sets of electronic axons to its corresponding set of electronic neurons.

Abstract: Neural inference chips for computing neural activations are provided. In various embodiments, the neural inference chip is adapted to: receive an input activation tensor comprising a plurality of input activations; receive a weight tensor comprising a plurality of weights; Booth recode each of the plurality of weights into a plurality of Booth-coded weights, each Booth coded value having an order; multiply the input activation tensor by the Booth coded weights, yielding a plurality of results for each input activation, each of the plurality of results corresponding to the orders of the Booth-coded weights; for each order of the Booth-coded weights, sum the corresponding results, yielding a plurality of partial sums, one for each order; and compute a neural activation from a sum of the plurality of partial sums.

Abstract: Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.