SEARCH · Engineering Papers
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.
A new neural network architecture and a hardware implementable learning algorithm is proposed. The algorithm, called cascade error projection (CEP), handles lack of precision and circuit noise better than existing algorithms.
One of the most important contributions to neural networks comes from Kohonen, Helsinki/Espoo, Finland, who had the idea of self-organizating maps in 1981. He verified his idea by an algorithm of which many applications make use of. The impetus for this idea came from biology, a field where the Europeans have always been very active at several research laboratories. The challenge was to model the self-organization found in the brain. Today one goal is the development of more sophisticated neurons which model the biological neurons more exactly. They should come to a better performance of neural nets with only a few complex neurons instead of many simple ones. A lot of application concepts arise from this idea: Kohonen himself applied it to speech recognition, but the project did not overcome much more than the recognition of the numerals one to ten at that time. A more promising application for self-organizing maps is process control and process monitoring. Several proposals were made which concern parameter classification of semiconductor technologies, design of integrated circuits, and control of chemical processes. Self-organizing maps were applied to robotics. The neural concept was introduced into electric power systems. At Dortmund we are working on a system which has to monitor the quality and the reliability of gears and electrical motors in equipment installed in coal mines. The results are promising and the probability to apply the system in the field is very high. A special feature of the system is that linguistic rules which are embedded in a fuzzy controller analyze the data of the self-organizing map in regard to life expectation of the gears. It seems that the fuzzy technique will introduce the technology of neural networks in a tandem mode. These technologies together with the genetic algorithms start to form the attractive field of computational intelligence.
This paper discusses the motivation, opportunities, and problems associated with implementing digital logic at very low voltages, including the challenge of making use of the available real estate in 3D multichip modules, energy requirements of very large neural networks, energy optimization metrics and their impact on system design, modeling problems, circuit design constraints, possible fabrication process modifications to improve performance, and barriers to practical implementation.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
This paper discusses the application of neural network pattern analysis algorithms to the IC fault diagnosis problem. A fault diagnostic is a decision rule combining what is known about an ideal circuit test response with information about how it is distorted by fabrication variations and measurement noise. The rule is used to detect fault existence in fabricated circuits using real test equipment. Traditional statistical techniques may be used to achieve this goal, but they can employ unrealistic a priori assumptions about measurement data. Our approach to this problem employs an adaptive pattern analysis technique based on feedforward neural networks. During training, a feedforward network automatically captures unknown sample distributions. This is important because distributions arising from the nonlinear effects of process variation can be more complex than is typically assumed. A feedforward network is also able to extract measurement features which contribute significantly to making a correct decision. Traditional feature extraction techniques employ matrix manipulations which can be particularly costly for large measurement vectors. In this paper we discuss a software system which we are developing that uses this approach. We also provide a simple example illustrating the use of the technique for fault detection in an operational amplifier.
Arrays of electrodes integrated with chip-scale packages and silicon-based integrated circuits have been proposed for use as medical electronic implants, including neuro-prosthetic devices that might be implanted in brains of patients who suffer from strokes, spinal-cord injuries, or amyotrophic lateral sclerosis. The electrodes of such a device would pick up signals from neurons in the cerebral cortex, and the integrated circuit would perform acquisition and preprocessing of signal data. The output of the integrated circuit could be used to generate, for example, commands for a robotic arm. Electrode arrays capable of acquiring electrical signals from neurons already exist, but heretofore, there has been no convenient means to integrate these arrays with integrated-circuit chips. Such integration is needed in order to eliminate the need for the extensive cabling now used to pass neural signals to data-acquisition and -processing equipment outside the body. The proposed integration would enable progress toward neuro-prostheses that would be less restrictive of patients mobility. An array of electrodes would comprise a set of thin wires of suitable length and composition protruding from and supported by a fine-pitch micro-ball grid array or chip-scale package (see figure). The associated integrated circuit would be mounted on the package face opposite the probe face, using the solder bumps (the balls of the ball grid array) to make the electrical connections between the probes and the input terminals of the integrated circuit. The key innovation is the insertion of probe wires of the appropriate length and material into the solder bumps through a reflow process, thereby fixing the probes in place and electrically connecting them with the integrated circuit. The probes could be tailored to any distribution of lengths and made of any suitable metal that could be drawn into fine wires. Furthermore, the wires could be coated with an insulating layer using anodization or other processes, to achieve the correct electrical impedance. The probe wires and the packaging materials must be biocompatible using such materials as lead-free solders. For protection, the chip and package can be coated with parylene.
Winner-take-all (WTA) neural networks using pulse-firing processing elements are introduced. In the pulse-firing WTA (PWTA) networks described, input and activation signal shunting is controlled by one shared lateral inhibition signal. This organization yields an O(n) area complexity that is convenient for integrated circuit implementation. Appropriately specified network parameters allow for the accurate continuous evaluation of inputs using a signal representation compatible with established pulse-firing neural network implementations.
Nonvolatile memory elements packed densely. Electrically-erasable, programmable, read-only memory matrices made with newly-synthesized organic material of variable electrical resistivity. Material, polypyrrole doped with tetracyanoquinhydrone (TCNQ), changes reversibly between insulating or higher-resistivity state and conducting or low-resistivity state. Thin film of conductive polymer separates layer of row conductors from layer of column conductors. Resistivity of film at each intersection and, therefore, resistance of memory element defined by row and column, increased or decreased by application of suitable switching voltage. Matrix circuits made with this material useful for experiments in associative electronic memories based on models of neural networks.
Neural algorithm for simulation of class of nonlinear wave phenomena devised. Numerically solves special one-dimensional case of Korteweg-deVries equation. Intended to be executed rapidly by neural network implemented as charge-coupled-device/charge-injection device, very-large-scale integrated-circuit analog data processor of type described in "CCD/CID Processors Would Offer Greater Precision" (NPO-18972).
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.
An iterative, simulation-based design procedure for a neural network chip is introduced. For this design procedure, the goal is to produce a chip layout for a neural network in which the weights are determined by transistor gate width-to-length ratios. In a given iteration, the current layout is simulated using the circuit simulator SPICE, and layout adjustments are made based on conventional gradient-decent methods. After the iteration converges, the chip is fabricated. Monte Carlo analysis is used to predict the effect of statistical fabrication process variations on the overall performance of the neural network chip.
The architecture for competitive assignment is described with attention given to the VLSI design and critical circuits fabricated in complementary metal-oxide semiconductor. The local application of association costs to processing units reduces the connectivity to the number of VLSI-compatible processing units. 'Hysteretic annealing' is discussed and when compared to mean-field annealing is found to enhance processing-unit gain and provide near-optimal solutions in about 150 microsec.
The human circadian timing system regulates the temporal organization of several endocrine functions, including the production of melatonin (via a neural pathway that includes the spinal cord), TSH, and cortisol. In traumatic spinal cord injury, afferent and efferent circuits that influence the basal production of these hormones may be disrupted. We studied five subjects with chronic spinal cord injury (three tetraplegic and two paraplegic, all neurologically complete injuries) under stringent conditions in which the underlying circadian rhythmicity of these hormones could be examined. Melatonin production was absent in the three tetraplegic subjects with injury to their lower cervical spinal cord and was of normal amplitude and timing in the two paraplegic subjects with injury to their upper thoracic spinal cord. The amplitude and the timing of TSH and cortisol rhythms were robust in the paraplegics and in the tetraplegics. Our results indicate that neurologically complete cervical spinal injury results in the complete loss of pineal melatonin production and that neither the loss of melatonin nor the loss of spinal afferent information disrupts the rhythmicity of cortisol or TSH secretion.
Circuit-chip area used more efficiently. Proposed gate structure selectively allows and restricts access to blocks of memory in electronic neural-type network. By breaking memory into independent blocks, gate greatly simplifies problem of reading from and writing to memory. Since blocks not used simultaneously, share operational amplifiers that prompt and read information stored in memory cells. Fewer operational amplifiers needed, and chip area occupied reduced correspondingly. Cost per bit drops as result.
Hopfield neural networks proposed for demodulating quadrature phase-shift-keyed (QPSK) signals carrying digital information. Networks solve nonlinear integral equations prior demodulation circuits cannot solve. Consists of set of N operational amplifiers connected in parallel, with weighted feedback from output terminal of each amplifier to input terminals of other amplifiers. Used to solve signal processing problems. Implemented as analog very-large-scale integrated circuit that achieves rapid convergence. Alternatively, implemented as digital simulation of such circuit. Also used to improve phase estimation performance over that of phase-locked loop.
Proposed optical apparatus generates rectangular pattern of light and dark areas, brightnesses of which represent elements of matrix product of two vectors. Photorefractive effect gives rise to four-wave mixing, which generates output beam modulated spatially by matrix product xy(SupT). Optical multipliers used as real-time analog tensor generators, components of neural networks, and generators of patterns to steer electromagnetic beams by diffraction or to effect temporary interconnections in very-large-scale integrated circuits.
Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern-analysis and pattern-recognition computational systems. These neurons are represented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a computational parallelism inherent in spiking-neuron geometry. Networks of SVM neurons offer advantages of speed and computational efficiency, relative to traditional artificial neural networks. The SVM also overcomes some of the limitations of prior spiking-neuron models. There are numerous potential pattern-recognition, tracking, and data-reduction (data preprocessing) applications for these SVM neural networks on Earth and in exploration of remote planets. Spiking neurons imitate biological neurons more closely than do the neurons of traditional artificial neural networks. A spiking neuron includes a central cell body (soma) surrounded by a tree-like interconnection network (dendrites). Spiking neurons are so named because they generate trains of output pulses (spikes) in response to inputs received from sensors or from other neurons. They gain their speed advantage over traditional neural networks by using the timing of individual spikes for computation, whereas traditional artificial neurons use averages of activity levels over time. Moreover, spiking neurons use the delays inherent in dendritic processing in order to efficiently encode the information content of incoming signals. Because traditional artificial neurons fail to capture this encoding, they have less processing capability, and so it is necessary to use more gates when implementing traditional artificial neurons in electronic circuitry. Such higher-order functions as dynamic tasking are effected by use of pools (collections) of spiking neurons interconnected by spike-transmitting fibers. The SVM includes adaptive thresholds and submodels of transport of ions (in imitation of such transport in biological neurons). These features enable the neurons to adapt their responses to high-rate inputs from sensors, and to adapt their firing thresholds to mitigate noise or effects of potential sensor failure. The mathematical derivation of the SVM starts from a prior model, known in the art as the point soma model, which captures all of the salient properties of neuronal response while keeping the computational cost low. The point-soma latency time is modified to be an exponentially decaying function of the strength of the applied potential. Choosing computational efficiency over biological fidelity, the dendrites surrounding a neuron are represented by simplified compartmental submodels and there are no dendritic spines. Updates to the dendritic potential, calcium-ion concentrations and conductances, and potassium-ion conductances are done by use of equations similar to those of the point soma. Diffusion processes in dendrites are modeled by averaging among nearest-neighbor compartments. Inputs to each of the dendritic compartments come from sensors. Alternatively or in addition, when an affected neuron is part of a pool, inputs can come from other spiking neurons. At present, SVM neural networks are implemented by computational simulation, using algorithms that encode the SVM and its submodels. However, it should be possible to implement these neural networks in hardware: The differential equations for the dendritic and cellular processes in the SVM model of spiking neurons map to equivalent circuits that can be implemented directly in analog very-large-scale integrated (VLSI) circuits.