Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems The promise of the technology is to create a brain-like ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed

A Survey of Neuromorphic Computing and Neural Networks in Hardware.

A significant proportion of the electroencephalography (EEG) literature focuses on differences in historically pre-defined frequency bands in the power spectrum that are typically referred to as alpha, beta, gamma, theta and delta waves. Here, we review 184 EEG studies that report differences in frequency bands in the resting state condition (eyes open and closed) across a spectrum of psychiatric disorders including depression, attention deficit-hyperactivity disorder (ADHD), autism, addiction, bipolar disorder, anxiety, panic disorder, post-traumatic stress disorder (PTSD), obsessive compulsive disorder (OCD) and schizophrenia to determine patterns across disorders. Aggregating across all reported results we demonstrate that characteristic patterns of power change within specific frequency bands are not necessarily unique to any one disorder but show substantial overlap across disorders as well as variability within disorders. In particular, we show that the most dominant pattern of change, across several disorder types including ADHD, schizophrenia and OCD, is power increases across lower frequencies (delta and theta) and decreases across higher frequencies (alpha, beta and gamma). However, a considerable number of disorders, such as PTSD, addiction and autism show no dominant trend for spectral change in any direction. We report consistency and validation scores across the disorders and conditions showing that the dominant result across all disorders is typically only 2.2 times as likely to occur in the literature as alternate results, and typically with less than 250 study participants when summed across all studies reporting this result. Furthermore, the magnitudes of the results were infrequently reported and were typically small at between 20% and 30% and correlated weakly with symptom severity scores. Finally, we discuss the many methodological challenges and limitations relating to such frequency band analysis across the literature. These results caution any interpretation of results from studies that consider only one disorder in isolation, and for the overall potential of this approach for delivering valuable insights in the field of mental health.

/pdf/eeg-frequency-bands-in-psychiatric-disorders-a-review-of-362rx42jct.pdf

EEG Frequency Bands in Psychiatric Disorders: A Review of Resting State Studies

Spiking Neural Networks (SNN) were shown to be suitable tools for the processing of spatio-temporal information. However, due to their inherent complexity, the formulation of efficient supervised learning algorithms for SNN is difficult and remains an important problem in the research area. This article presents SPAN - a spiking neuron that is able to learn associations of arbitrary spike trains in a supervised fashion allowing the processing of spatio-temporal information encoded in the precise timing of spikes. The idea of the proposed algorithm is to transform spike trains during the learning phase into analog signals so that common mathematical operations can be performed on them. Using this conversion, it is possible to apply the well-known Widrow-Hoff rule directly to the transformed spike trains in order to adjust the synaptic weights and to achieve a desired input/output spike behavior of the neuron. In the presented experimental analysis, the proposed learning algorithm is evaluated regarding its learning capabilities, its memory capacity, its robustness to noisy stimuli and its classification performance. Differences and similarities of SPAN regarding two related algorithms, ReSuMe and Chronotron, are discussed.

/pdf/span-spike-pattern-association-neuron-for-learning-spatio-2e1zug3bjw.pdf

Span: spike pattern association neuron for learning spatio-temporal spike patterns

Assistive technology for the visually impaired and blind people is a research field that is gaining increasing prominence owing to an explosion of new interest in it from disparate disciplines. The field has a very relevant social impact on our ever-increasing aging and blind populations. While many excellent state-of-the-art accounts have been written till date, all of them are subjective in nature. We performed an objective statistical survey across the various sub-disciplines in the field and applied information analysis and network-theory techniques to answer several key questions relevant to the field. To analyze the field we compiled an extensive database of scientific research publications over the last two decades. We inferred interesting patterns and statistics concerning the main research areas and underlying themes, identified leading journals and conferences, captured growth patterns of the research field; identified active research communities and present our interpretation of trends in the field for the near future. Our results reveal that there has been a sustained growth in this field; from less than 50 publications per year in the mid 1990s to close to 400 scientific publications per year in 2014. Assistive Technology for persons with visually impairments is expected to grow at a swift pace and impact the lives of individuals and the elderly in ways not previously possible.

An insight into assistive technology for the visually impaired and blind people: state-of-the-art and future trends

Electrical recordings in humans and monkeys show attentional enhancement of evoked responses and gamma synchrony in ventral stream cortical areas. Does this synchrony result from intrinsic activity in visual cortex or from inputs from other structures? Using paired recordings in the frontal eye field (FEF) and area V4, we found that attention to a stimulus in their joint receptive field leads to enhanced oscillatory coupling between the two areas, particularly at gamma frequencies. This coupling appeared to be initiated by FEF and was time-shifted by about 8 to 13 milliseconds across a range of frequencies. Considering the expected conduction and synaptic delays between the areas, this time-shifted coupling at gamma frequencies may optimize the postsynaptic impact of spikes from one area upon the other, improving cross-area communication with attention.

High-Frequency, Long-Range Coupling Between Prefrontal and Visual Cortex During Attention

http://www.lambda.ro/research/uploads/media/Detrended%20Fluctuation%20Analysis%20of%20EEG%20signals.pdf

Detrended Fluctuation Analysis of EEG Signals

The hardware implementation of neural networks is a new step in the evolution and use of neural networks in practical applications. The CMAC cerebellar model articulation controller is intended especially for hardware implementation, and this type of network is used successfully in the areas of robotics and control, where the real time capabilities of the network are of particular importance. The implementation of neural networks on FPGA's has several benefits, with emphasis on parallelism and the real time capabilities.This paper discusses the hardware implementation of the CMAC type neural network, the architecture and parameters and the functional modules of the hardware implemented neuro-processor.

Hardware Implementation of CMAC Type Neural Network on FPGA for Command Surface Approximation

Neuromorphic artificial neural networks attempt to understand the essential computations that take place in the dense networks of interconnected neurons making up the central nervous systems in living creatures. This article demonstrates that artificial spiking neural networkscbuilt to resemble the biological modelcencoding information in the timing of single spikes, are capable of computing and learning clusters from realistic data. It shows how a spiking neural network based on spike-time coding can successfully perform unsupervised and supervised clustering on real-world data. A temporal encoding procedure of continuously valued data is developed, together with a hardware implementation oriented new learning rule set. Solutions that make use of embedded soft-core microcontrollers are investigated, to implement some of the most resource-consuming components of the artificial neural network. Details of the implementations are given, with benchmark application evaluation and test bench description. Measurement results are presented, showing real-time and adaptive data processing capabilities, comparing these to related findings in the specific literature.

/pdf/real-time-classification-of-datasets-with-hardware-embedded-18850n6g2s.pdf

Real-time classification of datasets with hardware embedded neuromorphic neural networks

In this paper an overview of different types of assistive technologies is presented. Some of the most important aspects for the visually impaired are the solutions and assistance devices for the daily life. A simple categorization of this type of assistance devices is presented. Another important aspect for the visually impaired people is the indoor/outdoor navigation in dynamically changing environment. The technological advancement made possible the creation of different electronic equipments to help visually impaired/disabled persons in their navigation, such as different navigation systems, obstacle avoidance, object/obstacle localization, orientation assistance systems, in order to extend or change the basic support of guidance dogs and the white cane. In the paper a solution to integrate different assistive technologies is proposed, focusing on navigation and object detection, with the use of intelligent feedback by Human Computer Interfaces (HCI) with implication of Head- related transfer function HRTF functions. The paper is composed of three sections. In the first part a general description of the paper is presented. In the following section, entitled "Assistive technology", two main aspects are discussed: assistive technology for daily life and assistive technology for navigation and orientation of visually impaired. From the assistive systems for daily life, the following most important aspects/subjects are presented: personal care, timekeeping, alarms, food preparation and consumption, environmental control/household appliances, money, finance and shopping. Finally some conclusion is presented. The paper is a comprehensive overview of the literature and it does not contain implementation results.

/pdf/assistive-technologies-for-visually-impaired-people-1d6f2x2b55.pdf

Assistive Technologies for Visually Impaired People

The RBF radial basis function network is intended especially for hardware implementation and this type of network is used successfully in the areas of robotics and control, where the real time capabilities of the network are of particular importance. The implementation of neural networks on FPGA has several benefits, with emphasis on parallelism and the real time capabilities. This paper discusses the hardware implementation of the RBF type neural network, the architecture and parameters and the functional modules of the hardware implemented neuro-processor.

Laszlo Bako

Papers

Detrended Fluctuation Analysis of EEG Signals

Hardware Implementation of CMAC Type Neural Network on FPGA for Command Surface Approximation

Real-time classification of datasets with hardware embedded neuromorphic neural networks

Assistive Technologies for Visually Impaired People

Neural control based on RBF network implemented on FPGA