Abstract: A method of increasing neural network robustness. The method comprises defining an artificial neural network comprising a number of bounded ramp activation functions. The network is trained iteratively in a layer-by-layer fashion. Each iteration increases the slope of the activation functions toward a discrete threshold activation and stops when the activation functions converge to the threshold activation and the network exhibits spiking behavior. Alternatively, weight agnostic neural networks are created, wherein nodes in the networks comprise fixed shared weights. A subset of networks is identified that comprise activation functions compatible with neuromorphic hardware and are tested with a specified number of shared weight values. A score is generated for each combination of network and weight value according to performance and mapping to neuromorphic hardware, and the networks are ranked. The networks are then combined according to ranking to create a new network that exhibits spiking behavior.

Abstract: A method for simulating a random walk using spiking neuromorphic hardware is provided. The method comprises receiving, by a buffer count neuron, spiking inputs from upstream mesh nodes, wherein the inputs include information packets comprising information associated with a simulation of a random walk process. A buffer generator neuron generates spikes until the buffer count reaches a first predefined threshold, after which it sends buffer spiking outputs to a spike count neuron. The spike count neuron counts the buffer spiking outputs, and a spike generator neuron generates spikes until the spike count neuron reaches a second specified threshold. The spike generator neuron then sends counter spiking outputs to a probability neuron, which selects downstream mesh nodes to receive the counter spiking outputs, wherein the spiking outputs include updated information packets. The probability neuron then sends the spiking outputs to the selected downstream nodes.

Abstract: A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.

Abstract: A spiking retina microscope comprising microscope optics and a neuromorphic imaging sensor. The microscope optics are configured to direct a magnified image of a specimen onto the neuromorphic imaging sensor. The neuromorphic imaging sensor comprises a plurality of sensor elements that are configured to generate spike signals in response to integrated light from the magnified image reaching a threshold. The spike signals may be processed by a processor unit to generate a result, such as tracking biological particles in a specimen comprising biological material.

Abstract: A method for simulating a random walk using spiking neuromorphic hardware is provided. The method comprises receiving, by a buffer count neuron, spiking inputs from upstream mesh nodes, wherein the inputs include information packets comprising information associated with a simulation of a random walk process. A buffer generator neuron generates spikes until the buffer count reaches a first predefined threshold, after which it sends buffer spiking outputs to a spike count neuron. The spike count neuron counts the buffer spiking outputs, and a spike generator neuron generates spikes until the spike count neuron reaches a second specified threshold. The spike generator neuron then sends counter spiking outputs to a probability neuron, which selects downstream mesh nodes to receive the counter spiking outputs, wherein the spiking outputs include updated information packets. The probability neuron then sends the spiking outputs to the selected downstream nodes.

Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.

Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space. The method also includes either assigning a corresponding set of ringed neurons in a spiking neural network to a corresponding virtual random walker, or assigning a corresponding set of ringed neurons to a point in the virtual space. Movement of a given virtual random walker is tracked by decoding differences between states of individual neurons in a corresponding given set of ringed neurons. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network.

Abstract: A spiking retina microscope comprising microscope optics and a neuromorphic imaging sensor. The microscope optics are configured to direct a magnified image of a specimen onto the neuromorphic imaging sensor. The neuromorphic imaging sensor comprises a plurality of sensor elements that are configured to generate spike signals in response to integrated light from the magnified image reaching a threshold. The spike signals may be processed by a processor unit to generate a result, such as tracking biological particles in a specimen comprising biological material.

Abstract: A method of increasing neural network robustness. The method comprises defining an artificial neural network comprising a number of bounded ramp activation functions. The network is trained iteratively in a layer-by-layer fashion. Each iteration increases the slope of the activation functions toward a discrete threshold activation and stops when the activation functions converge to the threshold activation and the network exhibits spiking behavior. Alternatively, weight agnostic neural networks are created, wherein nodes in the networks comprise fixed shared weights. A subset of networks is identified that comprise activation functions compatible with neuromorphic hardware and are tested with a specified number of shared weight values. A score is generated for each combination of network and weight value according to performance and mapping to neuromorphic hardware, and the networks are ranked. The networks are then combined according to ranking to create a new network that exhibits spiking behavior.

Abstract: An artificial neural network with a context pathway and a method of identifying a classification of information using an artificial neural network with a context pathway. An artificial neural network comprises up-stream layers and down-stream layers. An output of the up-stream layers is provided as input to the down-stream layers. A first input to the artificial neural network to the up-stream layers is configured to receive input data. A second input to the artificial neural network to the down-stream layers is configured to receive context data. The context data identifies a characteristic of information in the input data. The artificial neural network is configured to identify a classification of the information in the input data at an output of the down-stream layers using the context data.

Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space. The method also includes either assigning a corresponding set of ringed neurons in a spiking neural network to a corresponding virtual random walker, or assigning a corresponding set of ringed neurons to a point in the virtual space. Movement of a given virtual random walker is tracked by decoding differences between states of individual neurons in a corresponding given set of ringed neurons. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network.

Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.

Abstract: A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.