Brainchip, Inc.

Conexant Systems, Inc.

Anil Shamrao Mankar

Peter A J Van Der Made

Kristofor D Carlson

Peter Aj Van Der Made

Marco Cheng

Mark R Tennyson

Richard A Ward

Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.

Event-based classification of features in a reconfigurable and temporally coded convolutional spiking neural network

Disclosed herein are system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set synapses associated with a spiking neuron circuit. The embodiment applies a first logical AND function to a first spike bit in the set of spike bits and a first synaptic weight of a first synapse in the set of synapses. The embodiment increments a membrane potential value associated with the spiking neuron circuit based on the applying. The embodiment determines that the membrane potential value associated with the spiking neuron circuit reached a learning threshold value. The embodiment then performs a Spike Time Dependent Plasticity (STDP) learning function based on the determination that the membrane potential value of the spiking neuron circuit reached the learning threshold value.

Spiking neural network

Disclosed herein are system and method embodiments for establishing secure communication with a remote artificial intelligent device. An embodiment operates by capturing an auditory signal from an auditory source. The embodiment coverts the auditory signal into a plurality of pulses having a spatio-temporal distribution. The embodiment identifies an acoustic signature in the auditory signal based on the plurality of pulses using a spatio-temporal neural network. The embodiment modifies synaptic strengths in the spatio-temporal neural network in response to the identifying thereby causing the spatio-temporal neural network to learn to respond to the acoustic signature in the acoustic signal. The embodiment transmits the plurality of pulses to the remote artificial intelligent device over a communications channel thereby causing the remote artificial intelligent device to learn to respond to the acoustic signature, and thereby allowing secure communication to be established with the remote artificial intelligent device based on the auditory signature.

Secure voice signature communications system using local and remote neural network devices

A configurable spiking neural network based accelerator system is provided. The accelerator system may be executed on an expansion card which may be a printed circuit board. The system includes one or more application specific integrated circuits comprising at least one spiking neural processing unit and a programmable logic device mounted on the printed circuit board. The spiking neural processing unit includes digital neuron circuits and digital, dynamic synaptic circuits. The programmable logic device is compatible with a local system bus. The spiking neural processing units contain digital circuits comprises a Spiking Neural Network that handles all of the neural processing. The Spiking Neural Network requires no software programming, but can be configured to perform a specific task via the Signal Coupling device and software executing on the host computer. Configuration parameters include the connections between synapses and neurons, neuron types, neurotransmitter types, and neuromodulation sensitivities of specific neurons.

Neural processor based accelerator system and method

An integrated circuit comprising a relatively simple high voltage tolerant output circuit that may be placed in a high impedance state (i.e., tri-stated) when the voltage at a corresponding signal connection point reaches a predetermined voltage reflecting a logic high level. In one embodiment of the invention, the output circuit is responsive to assertion of a control signal to selectively enter a high impedance state. The control signal is asserted by a control circuit following the detection of a logic high signal of a predetermined duration at the external signal connection point. The predetermined duration may correspond to transmission line delays of a signal line driven by the output circuit. For example, the delay in placing the output circuit in a high impedance state may correspond to the length of time needed to allow transmission line reflections to dissipate to an acceptable level. Disabling the output circuit following such a delay severs the potential current path between the supply voltage of the integrated circuit and an external voltage source coupled to the signal line via a pull-up device.

Growing community of inventors

Mission Viejo, CA, United States of America

Anil Shamrao Mankar