Abstract: 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.

Abstract: A method for creating a dynamic neural function library that relates to Artificial Intelligence systems and devices is provided. Within a dynamic neural network (artificial intelligent device), a plurality of control values are autonomously generated during a learning process and thus stored in synaptic registers of the artificial intelligent device that represent a training model of a task or a function learned by the artificial intelligent device. Control Values include, but are not limited to, values that indicate the neurotransmitter level that is present in the synapse, the neurotransmitter type, the connectome, the neuromodulator sensitivity, and other synaptic, dendric delay and axonal delay parameters. These values form collectively a training model. Training models are stored in the dynamic neural function library of the artificial intelligent device.

Abstract: 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.

Abstract: Embodiments of the present invention provide an artificial neural network system for feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to autonomously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as spike timing dependent plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the labeled output of the second spiking neural network is transmitted to a computing device, such as a central processing unit for post processing.

Abstract: 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.

Abstract: Embodiments of the present invention provide an artificial neural network system for improved machine learning, feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to spontaneously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as Spike Timing Dependent Plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the output of the second spiking neural network is transmitted to a computing device, such as a CPU for post processing.

Abstract: A method for creating a dynamic neural function library that relates to Artificial Intelligence systems and devices is provided. Within a dynamic neural network (artificial intelligent device), a plurality of control values are autonomously generated during a learning process and thus stored in synaptic registers of the artificial intelligent device that represent a training model of a task or a function learned by the artificial intelligent device. Control Values include, but are not limited to, values that indicate the neurotransmitter level that is present in the synapse, the neurotransmitter type, the connectome, the neuromodulator sensitivity, and other synaptic, dendric delay and axonal delay parameters. These values form collectively a training model. Training models are stored in the dynamic neural function library of the artificial intelligent device.

Abstract: The present invention provides a system and method for controlling a device by recognizing voice commands through a spiking neural network. The system comprises a spiking neural adaptive processor receiving an input stream that is being forwarded from a microphone, a decimation filter and then an artificial cochlea. The spiking neural adaptive processor further comprises a first spiking neural network and a second spiking neural network. The first spiking neural network checks for voice activities in output spikes received from artificial cochlea. If any voice activity is detected, it activates the second spiking neural network and passes the output spike of the artificial cochlea to the second spiking neural network that is further configured to recognize spike patterns indicative of specific voice commands. If the first spiking neural network does not detect any voice activity, it halts the second spiking neural network.

Abstract: A hierarchical information processing system is disclosed having a plurality of artificial neurons, comprised of binary logic gates, and interconnected through a second plurality of dynamic artificial synapses, intended to simulate or extend the function of a biological nervous system. The system is capable of approximation, autonomous learning and strengthening of formerly learned input patterns. The system learns by simulated Synaptic Time Dependent Plasticity, commonly abbreviated to STDP. Each artificial neuron consisting of a soma circuit and a plurality of synapse circuits, whereby the soma membrane potential, the soma threshold value, the synapse strength and the Post Synaptic Potential at each synapse are expressed as values in binary registers, which are dynamically determined from certain aspects of input pulse timing, previous strength value and output pulse feedback.

Abstract: An automated analysis system identifies the presence of malicious P-code or N-code programs in a manner that limits the possibility of the malicious code infecting a target computer. The target computer system initializes an analytical virtual P-code engine (AVPE). As initialized, the AVPE comprises software simulating the functionality of a P-code or intermediate language engine as well as machine language facilities simulating the P-code library routines that allow the execution of N-code programs. The AVPE executes a target program so that the target program does not interact with the target computer. The AVPE analyzes the behavior of the target program to identify occurrence of malicious code behavior and to indicate in a behavior pattern the occurrence of malicious code behavior. The AVPE is terminated at the end of the analysis process, thereby removing from the computer system the copy of the target program that was contained within the AVPE.

Abstract: An automated analysis system detects malicious code within a computer system by generating and subsequently analyzing a behavior pattern for each computer program introduced to the computer system. Generation of the behavior pattern is accomplished by a virtual machine invoked within the computer system. An initial analysis may be performed on the behavior pattern to identify infected programs on initial presentation of the program to the computer system. The analysis system also stores behavior patterns and sequences with their corresponding analysis results in a database. Newly infected programs can be detected by analyzing a newly generated behavior pattern for the program with reference to a stored behavior pattern to identify presence of an infection or payload pattern.

Abstract: An analytical virtual machine (AVM) analyzes computer code using a software processor including a register that stores behavior flags indicative of behaviors identified by virtually executing the code within the virtual machine. The AVM includes a sequencer that stores the sequence in which behavior flags are set in the behavior flags register. The AVM analyzes machine performance by emulating execution of the code being analyzed on a fully virtual machine and records the observed behavior. When emulation and analysis are complete, the AVM returns the behavior flags register and sequencer to the real machine and terminates.

Abstract: An automated analysis system identifies the presence of malicious P-code or N-code programs in a manner that limits the possibility of the malicious code infecting a target computer. The target computer system initializes an analytical virtual P-code engine (AVPE). As initialized, the AVPE comprises software simulating the functionality of a P-code or intermediate language engine as well as machine language facilities simulating the P-code library routines that allow the execution of N-code programs. The AVPE executes a target program so that the target program does not interact with the target computer. The AVPE analyzes the behavior of the target program to identify occurrence of malicious code behavior and to indicate in a behavior pattern the occurrence of malicious code behavior. The AVPE is terminated at the end of the analysis process, thereby removing from the computer system the copy of the target program that was contained within the AVPE.

Abstract: An automated analysis system identifies the presence of malicious P-code or N-code programs in a manner that limits the possibility of the malicious code infecting a target computer. The target computer system initializes an analytical virtual P-code engine (AVPE). As initialized, the AVPE comprises software simulating the functionality of a P-code or intermediate language engine as well as machine language facilities simulating the P-code library routines that allow the execution of N-code programs. The AVPE executes a target program so that the target program does not interact with the target computer. The AVPE analyzes the behavior of the target program to identify occurrence of malicious code behavior and to indicate in a behavior pattern the occurrence of malicious code behavior. The AVPE is terminated at the end of the analysis process, thereby removing from the computer system the copy of the target program that was contained within the AVPE.

Abstract: An analytical virtual machine (AVM) analyzes computer code using a software processor including a register that stores behavior flags indicative of behaviors identified by virtually executing the code within the virtual machine. The AVM includes a sequencer that stores the sequence in which behavior flags are set in the behavior flags register. The AVM analyzes machine performance by emulating execution of the code being analyzed on a fully virtual machine and records the observed behavior. When emulation and analysis are complete, the AVM returns the behavior flags register and sequencer to the real machine and terminates.

Abstract: An automated analysis system detects malicious code within a computer system by generating and subsequently analyzing a behavior pattern for each computer program introduced to the computer system. Generation of the behavior pattern is accomplished by a virtual machine invoked within the computer system. An initial analysis may be performed on the behavior pattern to identify infected programs on initial presentation of the program to the computer system. The analysis system also stores behavior patterns and sequences with their corresponding analysis results in a database. Newly infected programs can be detected by analyzing a newly generated behavior pattern for the program with reference to a stored behavior pattern to identify presence of an infection or payload pattern.

Abstract: An automated analysis system identifies the presence of malicious P-code or N-code programs in a manner that limits the possibility of the malicious code infecting a target computer. The target computer system initializes an analytical virtual P-code engine (AVPE). As initialized, the AVPE comprises software simulating the functionality of a P-code or intermediate language engine as well as machine language facilities simulating the P-code library routines that allow the execution of N-code programs. The AVPE executes a target program so that the target program does not interact with the target computer. The AVPE analyzes the behavior of the target program to identify occurrence of malicious code behavior and to indicate in a behavior pattern the occurrence of malicious code behavior. The AVPE is terminated at the end of the analysis process, thereby removing from the computer system the copy of the target program that was contained within the AVPE.

Abstract: An analytical virtual machine (AVM) analyzes computer code using a software processor including a register that stores behavior flags indicative of behaviors identified by virtually executing the code within the virtual machine. The AVM includes a sequencer that stores the sequence in which behavior flags are set in the behavior flags register. The AVM analyzes machine performance by emulating execution of the code being analyzed on a fully virtual machine and records the observed behavior. When emulation and analysis are complete, the AVM returns the behavior flags register and sequencer to the real machine and terminates.