Impacts of Mathematical Optimization on Reinforcement Learning
Abstract not provided.
Publications
Introduction to Neural-Inspired Computing & Impacts for Space
Abstract not provided.
Impacts of Mathematical Optimizations on Reinforcement Learning Policy Performance
Abstract not provided.
Whetstone: An accessible platform-independent method for training spiking deep neural networks for neuromorphic processors
Abstract not provided.
Spiking Neuron Implementations of Several Fundamental Machine Learning Algorithms
Abstract not provided.
Neural-Inspired Technologies for Data Processing and Scientific Computing
Abstract not provided.
Whetstone: An Accessible Platform-Independent Method for Training Spiking Deep Neural Networks for Neuromorphic Processors
Abstract not provided.
Reinforcement Learning Policy Performance Impacts of Pruning Quantization and Compression
Abstract not provided.
Neural-Inspired Anomaly Detection
Springer Proceedings in Complexity
Anomaly detection is an important problem in various fields of complex systems research including image processing, data analysis, physical security and cybersecurity. In image processing, it is used for removing noise while preserving image quality, and in data analysis, physical security and cybersecurity, it is used to find interesting data points, objects or events in a vast sea of information. Anomaly detection will continue to be an important problem in domains intersecting with “Big Data”. In this paper we provide a novel algorithm for anomaly detection that uses phase-coded spiking neurons as basic computational elements.
A spike-Timing neuromorphic architecture
2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings
Unlike general purpose computer architectures that are comprised of complex processor cores and sequential computation, the brain is innately parallel and contains highly complex connections between computational units (neurons). Key to the architecture of the brain is a functionality enabled by the combined effect of spiking communication and sparse connectivity with unique variable efficacies and temporal latencies. Utilizing these neuroscience principles, we have developed the Spiking Temporal Processing Unit (STPU) architecture which is well-suited for areas such as pattern recognition and natural language processing. In this paper, we formally describe the STPU, implement the STPU on a field programmable gate array, and show measured performance data.
Sandia Labs ? Neural Sommelier
Abstract not provided.
A Case Study on Neural Inspired Dynamic Memory Management Strategies for High Performance Computing
As high performance computing architectures pursue more computational power there is a need for increased memory capacity and bandwidth as well. A multi-level memory (MLM) architecture addresses this need by combining multiple memory types with different characteristics as varying levels of the same architecture. How to efficiently utilize this memory infrastructure is an unknown challenge, and in this research we sought to investigate whether neural inspired approaches can meaningfully help with memory management. In particular we explored neurogenesis inspired re- source allocation, and were able to show a neural inspired mixed controller policy can beneficially impact how MLM architectures utilize memory.
Studying Adaptive Learning through Game-Theoretic Modeling
Abstract not provided.
Neuroscience Related HW & SW Resources
Steep Deep Spiking Networks
Abstract not provided.
Neural-Inspired Algorithms for HPC - a Memory Management Case Study
Abstract not provided.
Neurogenesis Deep Learning
Abstract not provided.
Neurogenesis deep learning: Extending deep networks to accommodate new classes
Proceedings of the International Joint Conference on Neural Networks
Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.
A novel digital neuromorphic architecture efficiently facilitating complex synaptic response functions applied to liquid state machines
Proceedings of the International Joint Conference on Neural Networks
Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural network weights. Conventional processing architectures are not well suited for simulating neural networks, often requiring large amounts of energy and time. Additionally, synapses in biological neural networks are not binary connections, but exhibit a nonlinear response function as neurotransmitters are emitted and diffuse between neurons. Inspired by neuroscience principles, we present a digital neuromorphic architecture, the Spiking Temporal Processing Unit (STPU), capable of modeling arbitrary complex synaptic response functions without requiring additional hardware components. We consider the paradigm of spiking neurons with temporally coded information as opposed to non-spiking rate coded neurons used in most neural networks. In this paradigm we examine liquid state machines applied to speech recognition and show how a liquid state machine with temporal dynamics maps onto the STPU - demonstrating the flexibility and efficiency of the STPU for instantiating neural algorithms.
Optimization-based computation with spiking neurons
Proceedings of the International Joint Conference on Neural Networks
Considerable effort is currently being spent designing neuromorphic hardware for addressing challenging problems in a variety of pattern-matching applications. These neuromorphic systems offer low power architectures with intrinsically parallel and simple spiking neuron processing elements. Unfortunately, these new hardware architectures have been largely developed without a clear justification for using spiking neurons to compute quantities for problems of interest. Specifically, the use of spiking for encoding information in time has not been explored theoretically with complexity analysis to examine the operating conditions under which neuromorphic computing provides a computational advantage (time, space, power, etc.) In this paper, we present and formally analyze the use of temporal coding in a neural-inspired algorithm for optimization-based computation in neural spiking architectures.
Adaptive Learning Theory
Abstract not provided.
Optimization-based computation with spiking neurons
Abstract not provided.
An Efficient Implementation of a LSM on the Spiking Temporal Processing Unit
Abstract not provided.
An Efficient Implementation of a Liquid State Machine on the Spiking Temporal Processing Unit
Abstract not provided.
Studying Adaptive Learning through Game-Theoretic Modeling
Abstract not provided.
Results 51–75 of 113