Search

Neural action potentials (APs) are difficult to interpret as signal encoders and/or computational primitives. Their relationships with stimuli and behaviors are obscured by the staggering complexity of nervous systems themselves. We can reduce this complexity by observing that "simpler" neuron-less organisms also transduce stimuli into transient electrical pulses that affect their behaviors. Without a complicated nervous system, APs are often easier to understand as signal/response mechanisms. We review examples of nonneural stimulus transductions in domains of life largely neglected by theoretical neuroscience: bacteria, protozoans, plants, fungi, and neuron-less animals. We report properties of those electrical signals—for example, amplitudes, durations, ionic bases, refractory periods, and particularly their ecological purposes. We compare those properties with those of neurons to infer the tasks and selection pressures that neurons satisfy. Throughout the tree of life, nonneural stimulus transductions time behavioral responses to environmental changes. Nonneural organisms represent the presence or absence of a stimulus with the presence or absence of an electrical signal. Their transductions usually exhibit high sensitivity and specificity to a stimulus, but are often slow compared to neurons. Neurons appear to be sacrificing the specificity of their stimulus transductions for sensitivity and speed. We interpret cellular stimulus transductions as a cell's assertion that it detected something important at that moment in time. In particular, we consider neural APs as fast but noisy detection assertions. We infer that a principal goal of nervous systems is to detect extremely weak signals from noisy sensory spikes under enormous time pressure. We discuss neural computation proposals that address this goal by casting neurons as devices that implement online, analog, probabilistic computations with their membrane potentials. Those proposals imply a measurable relationship between afferent neural spiking statistics and efferent neural membrane electrophysiology. [ABSTRACT FROM AUTHOR]

This paper presents a reconfigurable digital implementation of an event-based binaural cochlear system on a Field Programmable Gate Array (FPGA). It consists of a pair of the Cascade of Asymmetric Resonators with Fast Acting Compression (CAR-FAC) cochlea models and leaky integrate-and-fire (LIF) neurons. Additionally, we propose an event-driven SpectroTemporal Receptive Field (STRF) Feature Extraction using Adaptive Selection Thresholds (FEAST). It is tested on the TIDIGTIS benchmark and compared with current event-based auditory signal processing approaches and neural networks. [ABSTRACT FROM AUTHOR]

To showcase how applications of automatic speech recognition (ASR) technology could help solve challenges in speech-language pathology practice with children with communication disability, and contribute to the realisation of the Sustainable Development Goals (SDGs). ASR technologies have been developed to address the need for equitable, efficient, and accurate assessment and diagnosis of communication disability in children by automating the transcription and analysis of speech and language samples and supporting dual-language assessment of bilingual children. ASR tools can automate the measurement of and help optimise intervention fidelity. ASR tools can also be used by children to engage in independent speech production practice without relying on feedback from speech-language pathologists (SLPs), thus bridging the long-standing gap between recommended and received intervention intensity. These innovative technologies and tools have been generated from interdisciplinary partnerships between SLPs, engineers, data scientists, and linguists. To advance equitable, efficient, and effective speech-language pathology services for children with communication disability, SLPs would benefit from integrating ASR solutions into their clinical practice. Ongoing interdisciplinary research is needed to further advance ASR technologies to optimise children's outcomes. This commentary paper focusses on industry, innovation and infrastructure (SDG 9) and partnerships for the goals (SDG 17). It also addresses SDG 1, SDG 3, SDG 4, SDG 8, SDG 10, SDG 11, and SDG 16. [ABSTRACT FROM AUTHOR]

Earth orbit is a limited natural resource that hosts a vast range of vital space-based systems that support the international community's national, commercial and defence interests. This resource is rapidly becoming depleted with over-crowding in high demand orbital slots and a growing presence of space debris. We propose the Fast Iterative Extraction of Salient targets for Tracking Asynchronously (FIESTA) algorithm as a robust, real-time and reactive approach to optical Space Situational Awareness (SSA) using Event-Based Cameras (EBCs) to detect, localize, and track Resident Space Objects (RSOs) accurately and timely. We address the challenges of the asynchronous nature and high temporal resolution output of the EBC accurately, unsupervised and with few tune-able parameters using concepts established in the neuromorphic and conventional tracking literature. We show this algorithm is capable of highly accurate in-frame RSO velocity estimation and average sub-pixel localization in a simulated test environment to distinguish the capabilities of the EBC and optical setup from the proposed tracking system. This work is a fundamental step toward accurate end-to-end real-time optical event-based SSA, and developing the foundation for robust closed-form tracking evaluated using standardized tracking metrics. [ABSTRACT FROM AUTHOR]

Neuromorphic engineering aims to build (autonomous) systems by mimicking biological systems. It is motivated by the observation that biological organisms—from algae to primates—excel in sensing their environment, reacting promptly to their perils and opportunities. Furthermore, they do so more resiliently than our most advanced machines, at a fraction of the power consumption. It follows that the performance of neuromorphic systems should be evaluated in terms of real-time operation, power consumption, and resiliency to real-world perturbations and noise using task-relevant evaluation metrics. Yet, following in the footsteps of conventional machine learning, most neuromorphic benchmarks rely on recorded datasets that foster sensing accuracy as the primary measure for performance. Sensing accuracy is but an arbitrary proxy for the actual system's goal—taking a good decision in a timely manner. Moreover, static datasets hinder our ability to study and compare closed-loop sensing and control strategies that are central to survival for biological organisms. This article makes the case for a renewed focus on closed-loop benchmarks involving real-world tasks. Such benchmarks will be crucial in developing and progressing neuromorphic Intelligence. The shift towards dynamic real-world benchmarking tasks should usher in richer, more resilient, and robust artificially intelligent systems in the future. [ABSTRACT FROM AUTHOR]

One challenging issue in speaker identification (SID) is to achieve noise-robust performance. Humans can accurately identify speakers, even in noisy environments. We can leverage our knowledge of the function and anatomy of the human auditory pathway to design SID systems that achieve better noise-robust performance than conventional approaches. We propose a text-dependent SID system based on a real-time cochlear model called cascade of asymmetric resonators with fast-acting compression (CARFAC). We investigate the SID performance of CARFAC on signals corrupted by noise of various types and levels. We compare its performance with conventional auditory feature generators including mel-frequency cepstrum coefficients, frequency domain linear predictions, as well as another biologically inspired model called the auditory nerve model. We show that CARFAC outperforms other approaches when signals are corrupted by noise. Our results are consistent across datasets, types and levels of noise, different speaking speeds, and back-end classifiers. We show that the noise-robust SID performance of CARFAC is largely due to its nonlinear processing of auditory input signals. Presumably, the human auditory system achieves noise-robust performance via inherent nonlinearities as well. [ABSTRACT FROM AUTHOR]

We present a biologically inspired sound localisation system for reverberant environments using the Cascade of Asymmetric Resonators with Fast-Acting Compression (CAR-FAC) cochlear model. The system exploits a CAR-FAC pair to pre-process binaural signals that travel through the inherent delay line of the cascade structures, as each filter acts as a delay unit. Following the filtering, each cochlear channel is cross-correlated with all the channels of the other cochlea using a quantised instantaneous correlation function to form a 2-D instantaneous correlation matrix (correlogram). The correlogram contains both interaural time difference and spectral information. The generated correlograms are analysed using a regression neural network for localisation. We investigate the effect of the CAR-FAC nonlinearity on the system performance by comparing it with a CAR only version. To verify that the CAR/CAR-FAC and the quantised instantaneous correlation provide a suitable basis with which to perform sound localisation tasks, a linear regression, an extreme learning machine, and a convolutional neural network are trained to learn the azimuthal angle of the sound source from the correlogram. The system is evaluated using speech data recorded in a reverberant environment. We compare the performance of the linear CAR and nonlinear CAR-FAC models with current sound localisation systems as well as with human performance. [ABSTRACT FROM AUTHOR]

In this work, we present an optical space imaging dataset using a range of event-based neuromorphic vision sensors. The unique method of operation of event-based sensors makes them ideal for space situational awareness (SSA) applications due to the sparseness inherent in space imaging data. These sensors offer significantly lower bandwidth and power requirements making them particularly well suited for use in remote locations and space-based platforms. We present the first publicly-accessible event-based space imaging dataset including recordings using sensors from multiple providers, greatly lowering the barrier to entry for other researchers given the scarcity of such sensors and the expertise required to operate them for SSA applications. The dataset contains both day time and night time recordings, including simultaneous co-collections from different event-based sensors. Recorded at a remote site, and containing 572 labeled targets with a wide range of sizes, trajectories, and signal-to-noise ratios, this real-world event-based dataset represents a challenging detection and tracking task that is not readily solved using previously proposed methods. We propose a highly optimized and robust feature-based detection and tracking method, designed specifically for SSA applications, and implemented via a cascade of increasingly selective event filters. These filters rapidly isolate events associated with space objects, maintaining the high temporal resolution of the sensors. The results from this simple yet highly optimized algorithm on the space imaging dataset demonstrate robust high-speed event-based detection and tracking which can readily be implemented on sensor platforms in space as well as terrestrial environments. [ABSTRACT FROM AUTHOR]

Single Photon Avalanche Diode sensor arrays operating in direct time of flight mode can perform 3D imaging using pulsed lasers. Operating at high frame rates, SPAD imagers typically generate large volumes of noisy and largely redundant spatio-temporal data. This results in communication bottlenecks and unnecessary data processing. In this work, we propose a neuromorphic processing solution to this problem. By processing the spatio-temporal patterns generated by the SPADs in a local, event-based manner, the proposed $128\times 128$ pixel sensor-processor system reduces the size of output data from the sensor by orders of magnitude while increasing the utility of the output data in the context of challenging recognition tasks. To test the proposed system, the first large scale complex SPAD imaging dataset is captured using an existing $32\times 32$ pixel sensor. The generated dataset consists of 24000 recordings and involves high-speed view-invariant recognition of airplanes with background clutter. The frame-based SPAD imaging dataset is converted via several alternative methods into event-based data streams and processed using the proposed $125\times 125$ receptive field neuromorphic processor as well as a range of feature extractor networks and pooling methods. The output of the proposed event generation methods are then processed by an event-based feature extraction and classification system implemented in FPGA hardware. The event-based processing methods are compared to processing the original frame-based dataset via frame-based but otherwise identical architectures. The results show the event-based methods are superior to the frame-based approach both in terms of classification accuracy and output data-rate. [ABSTRACT FROM AUTHOR]

A revolutionary type of imaging device, known as a silicon retina or event-based sensor, has recently been developed and is gaining in popularity in the field of artificial vision systems. These devices are inspired by a biological retina and operate in a significantly different way to traditional CCD-based imaging sensors. While a CCD produces frames of pixel intensities, an event-based sensor produces a continuous stream of events, each of which is generated when a pixel detects a change in log light intensity. These pixels operate asynchronously and independently, producing an event-based output with high temporal resolution. There are also no fixed exposure times, allowing these devices to offer a very high dynamic range independently for each pixel. Additionally, these devices offer high-speed, low power operation and a sparse spatio-temporal output. As a consequence, the data from these sensors must be interpreted in a significantly different way to traditional imaging sensors and this paper explores the advantages this technology provides for space imaging. The applicability and capabilities of event-based sensors for SSA applications are demonstrated through telescope field trials. Trial results have confirmed that the devices are capable of observing resident space objects from LEO through to GEO orbital regimes. Significantly, observations of RSOs were made during both day-time and night-time (terminator) conditions without modification to the camera or optics. The event based sensor's ability to image stars and satellites during day-time hours offers a dramatic capability increase for terrestrial optical sensors. This paper shows the field testing and validation of two different architectures of event-based imaging sensors. An event-based sensor's asynchronous output has an intrinsically low data-rate. In addition to low-bandwidth communications requirements, the low weight, low-power and high-speed make them ideally suitable to meeting the demanding challenges required by space-based SSA systems. Results from these experiments and the systems developed highlight the applicability of event-based sensors to ground and space-based SSA tasks. [ABSTRACT FROM AUTHOR]

In this work, we investigate event-based feature extraction through a rigorous framework of testing. We test a hardware efficient variant of Spike Timing Dependent Plasticity (STDP) on a range of spatio-temporal kernels with different surface decaying methods, decay functions, receptive field sizes, feature numbers, and back end classifiers. This detailed investigation can provide helpful insights and rules of thumb for performance vs. complexity trade-offs in more generalized networks, especially in the context of hardware implementation, where design choices can incur significant resource costs. The investigation is performed using a new dataset consisting of model airplanes being dropped free-hand close to the sensor. The target objects exhibit a wide range of relative orientations and velocities. This range of target velocities, analyzed in multiple configurations, allows a rigorous comparison of time-based decaying surfaces (time surfaces) vs. event index-based decaying surface (index surfaces), which are used to perform unsupervised feature extraction, followed by target detection and recognition. We examine each processing stage by comparison to the use of raw events, as well as a range of alternative layer structures, and the use of random features. By comparing results from a linear classifier and an ELM classifier, we evaluate how each element of the system affects accuracy. To generate time and index surfaces, the most commonly used kernels, namely event binning kernels, linearly, and exponentially decaying kernels, are investigated. Index surfaces were found to outperform time surfaces in recognition when invariance to target velocity was made a requirement. In the investigation of network structure, larger networks of neurons with large receptive field sizes were found to perform best. We find that a small number of event-based feature extractors can project the complex spatio-temporal event patterns of the dataset to an almost linearly separable representation in feature space, with best performing linear classifier achieving 98.75% recognition accuracy, using only 25 feature extracting neurons. [ABSTRACT FROM AUTHOR]

In this paper, we present the implementation of two types of Bayesian inference problems to demonstrate the potential of building probabilistic algorithms in hardware using single set of building blocks with the ability to perform these computations in real time. The first implementation, referred to as the BEAST (Bayesian Estimation and Stochastic Tracker), demonstrates a simple problem where an observer uses an underlying Hidden Markov Model (HMM) to track a target in one dimension. In this implementation, sensors make noisy observations of the target position at discrete time steps. The tracker learns the transition model for target movement, and the observation model for the noisy sensors, and uses these to estimate the target position by solving the Bayesian recursive equation online. We show the tracking performance of the system and demonstrate how it can learn the observation model, the transition model, and the external distractor (noise) probability interfering with the observations. In the second implementation, referred to as the Bayesian INference in DAG (BIND), we show how inference can be performed in a Directed Acyclic Graph (DAG) using stochastic circuits. We show how these building blocks can be easily implemented using simple digital logic gates. An advantage of the stochastic electronic implementation is that it is robust to certain types of noise, which may become an issue in integrated circuit (IC) technology with feature sizes in the order of tens of nanometers due to their low noise margin, the effect of high-energy cosmic rays and the low supply voltage. In our framework, the flipping of random individual bits would not affect the system performance because information is encoded in a bit stream. [ABSTRACT FROM AUTHOR]

The human auditory system has the ability to segregate complex auditory scenes into a foreground component and a background, allowing us to listen to specific speech sounds from a mixture of sounds. Selective attention plays a crucial role in this process, colloquially known as the "cocktail party effect." It has not been possible to build a machine that can emulate this human ability in real-time. Here, we have developed a framework for the implementation of a neuromorphic sound segregation algorithm in a Field Programmable Gate Array (FPGA). This algorithm is based on the principles of temporal coherence and uses an attention signal to separate a target sound stream from background noise. Temporal coherence implies that auditory features belonging to the same sound source are coherently modulated and evoke highly correlated neural response patterns. The basis for this form of sound segregation is that responses from pairs of channels that are strongly positively correlated belong to the same stream, while channels that are uncorrelated or anti-correlated belong to different streams. In our framework, we have used a neuromorphic cochlea as a frontend sound analyser to extract spatial information of the sound input, which then passes through band pass filters that extract the sound envelope at various modulation rates. Further stages include feature extraction and mask generation, which is finally used to reconstruct the targeted sound. Using sample tonal and speech mixtures, we show that our FPGA architecture is able to segregate sound sources in real-time. The accuracy of segregation is indicated by the high signal-to-noise ratio (SNR) of the segregated stream (90, 77, and 55 dB for simple tone, complex tone, and speech, respectively) as compared to the SNR of the mixture waveform (0 dB). This system may be easily extended for the segregation of complex speech signals, and may thus find various applications in electronic devices such as for sound segregation and speech recognition. [ABSTRACT FROM AUTHOR]

We have added a simplified neuromorphic model of Spike Time Dependent Plasticity (STDP) to the previously described Synapto-dendritic Kernel Adapting Neuron (SKAN), a hardware efficient neuron model capable of learning spatio-temporal spike patterns. The resulting neuron model is the first to perform synaptic encoding of afferent signal-to-noise ratio in addition to the unsupervised learning of spatio-temporal spike patterns. The neuron model is particularly suitable for implementation in digital neuromorphic hardware as it does not use any complex mathematical operations and uses a novel shift-based normalization approach to achieve synaptic homeostasis. The neuron’s noise compensation properties are characterized and tested on random spatio-temporal spike patterns as well as a noise corrupted subset of the zero images of the MNIST handwritten digit dataset. Results show the simultaneously learning common patterns in its input data while dynamically weighing individual afferents based on their signal to noise ratio. Despite its simplicity the interesting behaviors of the neuron model and the resulting computational power may also offer insights into biological systems. [ABSTRACT FROM PUBLISHER]

As advances in integrated circuit (IC) fabrication technology reduce feature sizes to dimensions on the order of nanometers, IC designers are facing many of the problems that evolution has had to overcome in order to perform meaningful and accurate computations in biological neural circuits. In this paper, we explore the current state of IC technology including the many new and exciting opportunities “beyond CMOS.” We review the role of noise in both biological and engineered systems and discuss how “stochastic facilitation” can be used to perform useful and precise computation. We explore nondeterministic methodologies for computation in hardware and introduce the concept of stochastic electronics (SE); a new way to design circuits and increase performance in highly noisy and mismatched fabrication environments. This approach is illustrated with several circuit examples whose results demonstrate its exciting potential. [ABSTRACT FROM PUBLISHER]

We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable TP and the use of asynchronous frames for information binding. [ABSTRACT FROM AUTHOR]

The Toxic Substances Control Act (TSCA) has started to have a significant impact on the chemical industry. This act gives the Environmental Protection Agency (EPA) far-reaching authority to regulate the manufacture, processing, use, and disposal of chemicals perceived to be dangerous to the health of mankind and/or to the environment. According to the current list of chemical substances for testing for health and environmental effects [15], benzene-based chemicals are exposed to intense scrutiny and decisions made regarding such chemicals would have serious effects on growth and development of certain sectors of the chemical industry. [ABSTRACT FROM PUBLISHER]

In the United States economy, intermediate petrochemicals rarely find direct consumer use; rather, they serve as raw materials for the manufacture of synthetic fibers, plastics, and resins; synthetic rubber, and thousands of other products. The demand for these end products drives the growth of the intermediate chemicals industry and shapes future technology. It is clear that petrochemical technology assessment requires both an understanding of the technology and of the function the technology is to serve in the economy. [ABSTRACT FROM PUBLISHER]

Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers. The feature extraction method is tested on both the N-MNIST (Neuromorphic-MNIST) benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage. [ABSTRACT FROM AUTHOR]