Abstract: A method of monitoring a neural network includes monitoring activity of the neural network. The method also includes detecting a condition based on the activity. The method further includes performing an exception event based on the detected condition.

Abstract: Methods and apparatus are provided for implementing structural plasticity in an artificial nervous system. One example method for altering a structure of an artificial nervous system generally includes determining a synapse in the artificial nervous system for reassignment, determining a first artificial neuron and a second artificial neuron for connecting via the synapse, and reassigning the synapse to connect the first artificial neuron with the second artificial neuron. Another example method for operating an artificial nervous system, generally includes determining a synapse in the artificial nervous system for assignment; determining a first artificial neuron and a second artificial neuron for connecting via the synapse, wherein at least one of the synapse or the first and second artificial neurons are determined randomly or pseudo-randomly; and assigning the synapse to connect the first artificial neuron with the second artificial neuron.

Abstract: Aspects of the present disclosure support techniques for neural pattern sequence completion and neural pattern hierarchical replay. At least a portion of a pattern can be invoked for replay upon referencing the pattern and learning relational aspects between elements of the pattern and the referencing of the pattern using hierarchical levels of neurons.

Abstract: A method for creating and maintaining short-term memory using short-term plasticity, includes changing a gain of a synapse based on pre synaptic spike activity without regard to postsynaptic spike activity. The method also includes calculating the gain based on a continuously updated synaptic state variable associated with the short-term plasticity.

Abstract: Aspects of the present disclosure support techniques for unsupervised neural component replay. A pattern in a plurality of afferent neuron outputs can be first referenced with one or more referencing neurons. One or more relational aspects can be matched, with one or more relational aspect neurons, between the pattern and an output of the one or more referencing neurons. One or more of the plurality of afferent neurons can be induced to output a pattern that is substantially the same as the referenced pattern by the one or more referencing neurons.

Abstract: Aspects of the present disclosure support techniques for neural component memory transfer. A pattern in a plurality of afferent neuron outputs can be first referenced with one or more referencing neurons. One or more first relational aspects can be matched, with one or more first relational aspect neurons, between the referenced pattern and an output of the one or more referencing neurons. The referenced pattern can be transferred to one or more transferee neurons by inducing the plurality of afferent neurons to output a pattern substantially the same as the referenced pattern by the one or more referencing neurons.

Abstract: Methods and apparatus are provided for inferring and accounting for missing post-synaptic events (e.g., a post-synaptic spike that is not associated with any pre-synaptic spikes) at an artificial neuron and adjusting spike-timing dependent plasticity (STDP) accordingly. One example method generally includes receiving, at an artificial neuron, a plurality of pre-synaptic spikes associated with a synapse, tracking a plurality of post-synaptic spikes output by the artificial neuron, and determining at least one of the post-synaptic spikes is associated with none of the plurality of pre-synaptic spikes. According to certain aspects, determining inferring missing post-synaptic events may be accomplished by using a flag, counter, or other variable that is updated on post-synaptic firings. If this post-ghost variable changes between pre-synaptic-triggered adjustments, then the artificial nervous system can determine there was a missing post-synaptic pairing.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for spiking neural computation of general linear systems. One example aspect is a neuron model that codes information in the relative timing between spikes. However, synaptic weights are unnecessary. In other words, a connection may either exist (significant synapse) or not (insignificant or non-existent synapse). Certain aspects of the present disclosure use binary-valued inputs and outputs and do not require post-synaptic filtering. However, certain aspects may involve modeling of connection delays (e.g., dendritic delays). A single neuron model may be used to compute any general linear transformation x=AX+BU to any arbitrary precision. This neuron model may also be capable of learning, such as learning input delays (e.g., corresponding to scaling values) to achieve a target output delay (or output value). Learning may also be used to determine a logical relation of causal inputs.

Abstract: Methods and apparatus are provided for implementing behavioral homeostasis in artificial neurons that use a dynamical spiking neuron model. The homeostatic mechanism may be driven by neuron state, rather than by neuron spiking rate, and this mechanism may drive changes to the neuron temporal dynamics, rather than to contributions of input or weights. As a result, certain aspects of the present disclosure are a more natural fit with spiking neural networks and have many functional and computational advantages. One example method for implementing homeostasis of an artificial nervous system generally includes determining one or more state variables of a neuron model used by an artificial neuron, based at least in part on dynamics of the neuron model; determining one or more conditions based at least in part on the state variables; and adjusting the dynamics based at least in part on the conditions.

Abstract: Certain aspects of the present disclosure support a technique for strategic synaptic failure and learning in spiking neural networks. A synaptic weight for a synaptic connection between a pre-synaptic neuron and a post-synaptic neuron can be first determined (e.g., according to a learning rule). Then, one or more failures of the synaptic connection can be determined based on a set of characteristics of the synaptic connection. The one or more failures can be omitted from computation of a neuronal behavior of the post-synaptic neuron.

Abstract: Certain aspects of the present disclosure support a technique for neural temporal coding, learning and recognition. A method of neural coding of large or long spatial-temporal patterns is also proposed. Further, generalized neural coding and learning with temporal and rate coding is disclosed in the present disclosure.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for spiking neural computation of general linear systems. One example aspect is a neuron model that codes information in the relative timing between spikes. However, synaptic weights are unnecessary. In other words, a connection may either exist (significant synapse) or not (insignificant or non-existent synapse). Certain aspects of the present disclosure use binary-valued inputs and outputs and do not require post-synaptic filtering. However, certain aspects may involve modeling of connection delays (e.g., dendritic delays). A single neuron model may be used to compute any general linear transformation x=AX+BU to any arbitrary precision. This neuron model may also be capable of learning, such as learning input delays (e.g., corresponding to scaling values) to achieve a target output delay (or output value). Learning may also be used to determine a logical relation of causal inputs.

Abstract: Certain aspects of the present disclosure support a technique for neural learning of natural multi-spike trains in spiking neural networks. A synaptic weight can be adapted depending on a resource associated with the synapse, which can be depleted by weight change and can recover over time. In one aspect of the present disclosure, the weight adaptation may depend on a time since the last significant weight change.

Abstract: A method for creating and maintaining short term memory using short term plasticity, includes changing a gain of a synapse based on presynaptic spike activity without regard to postsynaptic spike activity. The method also includes calculating the gain based on a continuously updated synaptic state variable associated with the short term plasticity.

Abstract: A method of approximating delay for postsynaptic potentials includes receiving a postsynaptic potential. The method further includes filtering the postsynaptic potential to approximate a delayed delivery of the postsynaptic potential.

Abstract: A method for transmitting values in a neural network includes obtaining a parameter value. The method also includes encoding the parameter value based on at least one value used by a neuron. The encoding is based on a spike to be transmitted via a spike channel.

Abstract: Certain aspects of the present disclosure relate to a technique for adaptive structural delay plasticity applied in spiking neural networks. With the proposed method of structural delay plasticity, the requirement of modeling multiple synapses with different delays can be avoided. In this case, far fewer potential synapses should be modeled for learning.

Abstract: In accordance with aspects of the disclosure, a method, apparatus, and computer program product are provided for wireless communication. The method, apparatus, and computer program product may be provided for detecting a change in power of received signals and adjusting amplification of the received signals based on the detected change in power prior to transmitting the signals.

Abstract: A method of monitoring a neural network includes monitoring activity of the neural network. The method also includes detecting a condition based on the activity. The method further includes performing an exception event based on the detected condition.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for learning or determining delays between neuron models so that the uncertainty in input spike timing is accounted for in the margin of time between a delayed pre-synaptic input spike and a post-synaptic spike. In this manner, a neural network can correctly match patterns (even in the presence of significant jitter) and correctly distinguish between different noisy patterns. One example method generally includes determining an uncertainty associated with a first pre-synaptic spike time of a first neuron model for a pattern to be learned; and determining a delay based on the uncertainty, such that the delay added to a second pre-synaptic spike time of the first neuron model results in a causal margin of time between the delayed second pre-synaptic spike time and a post-synaptic spike time of a second neuron model.