Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “neuronal network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

From IMT Device Measurements to Network-Level Consequences: When Learning Suppresses Beyond-LIF Neuron Dynamics

Emerging neuromorphic devices such as insulator--metal transition (IMT) devices exhibit complex temporal dynamics, including slow internal state memory, hysteresis, and burst-like firing, which are poorly captured by conventional leaky integrate-and-fire (LIF) neurons. However, it remains unclear when such dynamics influence learning and inference at the network level, particularly under commonly used unsupervised plasticity rules. We present a controlled, full-stack co-design study spanning experimental characterization of individual IMT devices, compact neuron model development, and large-scale spiking network simulations with identical architectures and learning rules. Rather than optimizing benchmark accuracy, our goal is to diagnose when neuron-level dynamics survive learning and competition, and when they are suppressed, to inform the co-design of devices, networks, and learning rules that can exploit beyond-LIF complexity.

42 ENGINEERING↗
NASA NTRS1990

Sensitivity of feedforward neural networks to weight errors

An analysis is made of the sensitivity of feedforward layered networks of Adaline elements (threshold logic units) to weight errors. An approximation is derived which expresses the probability of error for an output neuron of a large network (a network with many neurons per layer) as a function of the percentage change in the weights. As would be expected, the probability of error increases with the number of layers in the network and with the percentage change in the weights. The probability of error is essentially independent of the number of weights per neuron and of the number of neurons per layer, as long as these numbers are large (on the order of 100 or more).

Stevenson, Maryhelen↗
DOE OSTI2021

Small footprint optoelectrodes using ring resonators for passive light localization

The combination of electrophysiology and optogenetics enables the exploration of how the brain operates down to a single neuron and its network activity. Neural probes are in vivo invasive devices that integrate sensors and stimulation sites to record and manipulate neuronal activity with high spatiotemporal resolution. State-of-the-art probes are limited by tradeoffs involving their lateral dimension, number of sensors, and ability to access independent stimulation sites. Here, we realize a highly scalable probe that features three-dimensional integration of small-footprint arrays of sensors and nanophotonic circuits to scale the density of sensors per cross-section by one order of magnitude with respect to state-of-the-art devices. For the first time, we overcome the spatial limit of the nanophotonic circuit by coupling only one waveguide to numerous optical ring resonators as passive nanophotonic switches. With this strategy, we achieve accurate on-demand light localization while avoiding spatially demanding bundles of waveguides and demonstrate the feasibility with a proof-of-concept device and its scalability towards high-resolution and low-damage neural optoelectrodes.

42 ENGINEERING↗
NASA NTRS1991

On the capacity of ternary Hebbian networks

Networks of ternary neurons storing random vectors over the set -1,0,1 by the so-called Hebbian rule are considered. It is shown that the maximal number of stored patterns that are equilibrium states of the network with probability tending to one as N tends to infinity is at least on the order of (N exp 2-1/alpha)/K, where N is the number of neurons, K is the number of nonzero elements in a pattern, and t = alpha x K, alpha between 1/2 and 1, is the threshold in the neuron function. While, for small K, this bound is similar to that obtained for fully connected binary networks, the number of interneural connections required in the ternary case is considerably smaller. Similar bounds, incorporating error probabilities, are shown to guarantee, in the same probabilistic sense, the correction of errors in the nonzero elements and in the location of these elements.

Baram, Yoram↗
NASA NTRSDate not supplied

SPIKE-Dx : A Low-Power High-Throughput Fault Diagnostics Tool using Spiking Neural Networks for Constrained Systems

Diagnostic systems are important for many aerospace systems, which are severely limited in available power, like cubesats or UAVs. Therefore, traditional diagnostics systems cannot be used due to their substantial footprint and constraints. In this paper, we present our very low power diagnostic tool SPIKE-DX to monitor critical systems with constrained computational and energy resources. This is made possible through spiking neural networks (SNNs), which are executable within optimized simulation environments and further implemented on on cutting-edge neuromorphic hardware. Based upon FMEA (Failure Mode and Effect Analysis) framework, Diagnostic Bayesian Networks (DBNs) can be constructed that provide powerful means for diagnostic reasoning. In this paper, we describe such DBNs and a method to automatically translate the DBN into highly structured networks of spiking neurons for execution in SPIKE-DX.

Spiking Neural Networks↗
NASA NTRS1991

A neural network architecture for implementation of expert systems for real time monitoring

Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.

Ramamoorthy, P. A.↗
DOE OSTI2020

Trainability of ReLU networks and Data-dependent Initialization

Here, in this paper, we study the trainability of rectified linear unit (ReLU) networks at initialization. A ReLU neuron is said to be dead if it only outputs a constant for any input. Two death states of neurons are introduced–tentative and permanent death. A network is then said to be trainable if the number of permanently dead neurons is sufficiently small for a learning task. We refer to the probability of a randomly initialized network being trainable as trainability. We show that a network being trainable is a necessary condition for successful training, and the trainability serves as an upper bound of training success rates. In order to quantify the trainability, we study the probability distribution of the number of active neurons at initialization. In many applications, overspecified or overparameterized neural networks are successfully employed and shown to be trained effectively. With the notion of trainability, we show that overparameterization is both a necessary and a sufficient condition for achieving a zero training loss. Furthermore, we propose a data-dependent initialization method in an overparameterized setting. Numerical examples are provided to demonstrate the effectiveness of the method and our theoretical findings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

The membrane periodic skeleton is an actomyosin network that regulates axonal diameter and conduction

Neurons have a membrane periodic skeleton (MPS) composed of actin rings interconnected by spectrin. Here, combining chemical and genetic gain- and loss-of-function assays, we show that in rat hippocampal neurons the MPS is an actomyosin network that controls axonal expansion and contraction. Using super-resolution microscopy, we analyzed the localization of axonal non-muscle myosin II (NMII). We show that active NMII light chains are colocalized with actin rings and organized in a circular periodic manner throughout the axon shaft. In contrast, NMII heavy chains are mostly positioned along the longitudinal axonal axis, being able to crosslink adjacent rings. NMII filaments can play contractile or scaffolding roles determined by their position relative to actin rings and activation state. We also show that MPS destabilization through NMII inactivation affects axonal electrophysiology, increasing action potential conduction velocity. In summary, our findings open new perspectives on axon diameter regulation, with important implications in neuronal biology.

Costa, Ana Rita↗
DOE OSTI2021

Global transcriptome profile of the developmental principles of in vitro iPSC-to-motor neuron differentiation

Abstract Background Human induced pluripotent stem cells (iPSC) have opened new avenues for regenerative medicine. Consequently, iPSC-derived motor neurons have emerged as potentially viable therapies for spinal cord injuries and neurodegenerative disorders including Amyotrophic Lateral Sclerosis. However, direct clinical application of iPSC bears in itself the risk of tumorigenesis and other unforeseeable genetic or epigenetic abnormalities. Results Employing RNA-seq technology, we identified and characterized gene regulatory networks triggered by in vitro chemical reprogramming of iPSC into cells with the molecular features of motor neurons (MNs) whose function in vivo is to innervate effector organs. We present meta-transcriptome signatures of 5 cell types: iPSCs, neural stem cells, motor neuron progenitors, early motor neurons, and mature motor neurons. In strict response to the chemical stimuli, along the MN differentiation axis we observed temporal downregulation of tumor growth factor-β signaling pathway and consistent activation of sonic hedgehog, Wnt/β-catenin, and Notch signaling. Together with gene networks defining neuronal differentiation (neurogenin 2, microtubule-associated protein 2, Pax6, and neuropilin-1), we observed steady accumulation of motor neuron-specific regulatory genes, including Islet-1 and homeobox protein HB9. Interestingly, transcriptome profiling of the differentiation process showed that Ca 2+ signaling through cAMP and LPC was downregulated during the conversion of the iPSC to neural stem cells and key regulatory gene activity of the pathway remained inhibited until later stages of motor neuron formation. Pathways shaping the neuronal development and function were well-represented in the early motor neuron cells including, neuroactive ligand-receptor interactions, axon guidance, and the cholinergic synapse formation. A notable hallmark of our in vitro motor neuron maturation in monoculture was the activation of genes encoding G-coupled muscarinic acetylcholine receptors and downregulation of the ionotropic nicotinic acetylcholine receptors expression. We observed the formation of functional neuronal networks as spontaneous oscillations in the extracellular action potentials recorded on multi-electrode array chip after 20 days of differentiation. Conclusions Detailed transcriptome profile of each developmental step from iPSC to motor neuron driven by chemical induction provides the guidelines to novel therapeutic approaches in the re-construction efforts of muscle innervation.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1993

Generalized Adaptive Artificial Neural Networks

Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.

Tawel, Raoul↗
NASA NTRS1995

Fault Tolerant Characteristics of Artificial Neural Network Electronic Hardware

The fault tolerant characteristics of analog-VLSI artificial neural network (with 32 neurons and 532 synapses) chips are studied by exposing them to high energy electrons, high energy protons, and gamma ionizing radiations under biased and unbiased conditions. The biased chips became nonfunctional after receiving a cumulative dose of less than 20 krads, while the unbiased chips only started to show degradation with a cumulative dose of over 100 krads. As the total radiation dose increased, all the components demonstrated graceful degradation. The analog sigmoidal function of the neuron became steeper (increase in gain), current leakage from the synapses progressively shifted the sigmoidal curve, and the digital memory of the synapses and the memory addressing circuits began to gradually fail. From these radiation experiments, we can learn how to modify certain designs of the neural network electronic hardware without using radiation-hardening techniques to increase its reliability and fault tolerance.

Artificial Neural Network↗
NASA NTRS1990

Neural computation of arithmetic functions

An area of application of neural networks is considered. A neuron is modeled as a linear threshold gate, and the network architecture considered is the layered feedforward network. It is shown how common arithmetic functions such as multiplication and sorting can be efficiently computed in a shallow neural network. Some known results are improved by showing that the product of two n-bit numbers and sorting of n n-bit numbers can be computed by a polynomial-size neural network using only four and five unit delays, respectively. Moreover, the weights of each threshold element in the neural networks require O(log n)-bit (instead of n-bit) accuracy. These results can be extended to more complicated functions such as multiple products, division, rational functions, and approximation of analytic functions.

Siu, Kai-Yeung↗
NASA NTRS1989

Limitations of opto-electronic neural networks

Consideration is given to the limitations of implementing neurons, weights, and connections in neural networks for electronics and optics. It is shown that the advantages of each technology are utilized when electronically fabricated neurons are included and a combination of optics and electronics are employed for the weights and connections. The relationship between the types of neural networks being constructed and the choice of technologies to implement the weights and connections is examined.

Yu, Jeffrey↗
NASA NTRS1991

Electronic neural network for dynamic resource allocation

A VLSI implementable neural network architecture for dynamic assignment is presented. The resource allocation problems involve assigning members of one set (e.g. resources) to those of another (e.g. consumers) such that the global 'cost' of the associations is minimized. The network consists of a matrix of sigmoidal processing elements (neurons), where the rows of the matrix represent resources and columns represent consumers. Unlike previous neural implementations, however, association costs are applied directly to the neurons, reducing connectivity of the network to VLSI-compatible 0 (number of neurons). Each row (and column) has an additional neuron associated with it to independently oversee activations of all the neurons in each row (and each column), providing a programmable 'k-winner-take-all' function. This function simultaneously enforces blocking (excitatory/inhibitory) constraints during convergence to control the number of active elements in each row and column within desired boundary conditions. Simulations show that the network, when implemented in fully parallel VLSI hardware, offers optimal (or near-optimal) solutions within only a fraction of a millisecond, for problems up to 128 resources and 128 consumers, orders of magnitude faster than conventional computing or heuristic search methods.

Thakoor, A. P.↗
NASA NTRS1987

Electronic implementation of associative memory based on neural network models

An electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with the help of asymmetrical extra connections are discussed. The stability of the matrix memory system incorporating a unique local inhibition scheme is analyzed in terms of local minimization of an energy function. The memory's stability, dynamic behavior, and recall capability are investigated using a 32-'neuron' electronic neural network memory with a 1024-programmable binary connection matrix.

Moopenn, A.↗
DOE OSTI2022

Nonconvex regularization for sparse neural networks

Convex ℓ 1 regularization using an infinite dictionary of neurons has been suggested for constructing neural networks with desired approximation guarantees, but can be affected by an arbitrary amount of over-parametrization. This can lead to a loss of sparsity and result in networks with too many active neurons for the given data, in particular if the number of data samples is large. As a remedy, in this paper, a nonconvex regularization method is investigated in the context of shallow ReLU networks: We prove that in contrast to the convex approach, any resulting (locally optimal) network is finite even in the presence of infinite data (i.e., if the data distribution is known and the limiting case of infinite samples is considered). Moreover, here we show that approximation guarantees and existing bounds on the network size for finite data are maintained.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Efficiently modeling neural networks on massively parallel computers

Neural networks are a very useful tool for analyzing and modeling complex real world systems. Applying neural network simulations to real world problems generally involves large amounts of data and massive amounts of computation. To efficiently handle the computational requirements of large problems, we have implemented at Los Alamos a highly efficient neural network compiler for serial computers, vector computers, vector parallel computers, and fine grain SIMD computers such as the CM-2 connection machine. This paper describes the mapping used by the compiler to implement feed-forward backpropagation neural networks for a SIMD (Single Instruction Multiple Data) architecture parallel computer. Thinking Machines Corporation has benchmarked our code at 1.3 billion interconnects per second (approximately 3 gigaflops) on a 64,000 processor CM-2 connection machine (Singer 1990). This mapping is applicable to other SIMD computers and can be implemented on MIMD computers such as the CM-5 connection machine. Our mapping has virtually no communications overhead with the exception of the communications required for a global summation across the processors (which has a sub-linear runtime growth on the order of O(log(number of processors)). We can efficiently model very large neural networks which have many neurons and interconnects and our mapping can extend to arbitrarily large networks (within memory limitations) by merging the memory space of separate processors with fast adjacent processor interprocessor communications. This paper will consider the simulation of only feed forward neural network although this method is extendable to recurrent networks.

Farber, Robert M.↗