Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition
27 Jul 2021-
TL;DR: In this article, the spike encoded data is processed through a spiking reservoir with a biologically inspired topology and neuron model, which yields better performance than state-of-the-art convolutional neural networks.
Abstract: Surface electromyogram (sEMG) signals result from muscle movement and hence they are an ideal candidate for benchmarking event-driven sensing and computing. We propose a simple yet novel approach for optimizing the spike encoding algorithm’s hyper-parameters inspired by the readout layer concept in reservoir computing. Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition. The spike encoded data is processed through a spiking reservoir with a biologically inspired topology and neuron model. When trained with the unsupervised activity regulation CRITICAL algorithm to operate at the edge of chaos, the reservoir yields better performance than state-of-the-art convolutional neural networks. The reservoir performance with regulated activity was found to be 89.72% for the Roshambo EMG dataset and 70.6% for the EMG subset of sensor fusion dataset. Therefore, the biologically-inspired computing paradigm, which is known for being power efficient, also proves to have a great potential when compared with conventional AI algorithms.
Citations
More filters
TL;DR: In this article , the authors outline several strides that neuromorphic computing based on spiking neural networks (SNNs) has taken over the recent past, and present their outlook on the challenges that this field needs to overcome to make the bioplausibility route a successful one.
Abstract: Neuromorphic Computing, a concept pioneered in the late 1980s, is receiving a lot of attention lately due to its promise of reducing the computational energy, latency, as well as learning complexity in artificial neural networks. Taking inspiration from neuroscience, this interdisciplinary field performs a multi-stack optimization across devices, circuits, and algorithms by providing an end-to-end approach to achieving brain-like efficiency in machine intelligence. On one side, neuromorphic computing introduces a new algorithmic paradigm, known as Spiking Neural Networks (SNNs), which is a significant shift from standard deep learning and transmits information as spikes (“1” or “0”) rather than analog values. This has opened up novel algorithmic research directions to formulate methods to represent data in spike-trains, develop neuron models that can process information over time, design learning algorithms for event-driven dynamical systems, and engineer network architectures amenable to sparse, asynchronous, event-driven computing to achieve lower power consumption. On the other side, a parallel research thrust focuses on development of efficient computing platforms for new algorithms. Standard accelerators that are amenable to deep learning workloads are not particularly suitable to handle processing across multiple timesteps efficiently. To that effect, researchers have designed neuromorphic hardware that rely on event-driven sparse computations as well as efficient matrix operations. While most large-scale neuromorphic systems have been explored based on CMOS technology, recently, Non-Volatile Memory (NVM) technologies show promise toward implementing bio-mimetic functionalities on single devices. In this article, we outline several strides that neuromorphic computing based on spiking neural networks (SNNs) has taken over the recent past, and we present our outlook on the challenges that this field needs to overcome to make the bio-plausibility route a successful one.
10 citations
14 Jul 2022
TL;DR: It is shown that several encoding methods result in improved performance over the conventional deep learning baseline in certain cases, further demonstrating the power of spike encoding algorithms in the encoding of real-valued signals and that neuromorphic implementation has the potential to outperform state of the art techniques.
Abstract: Spiking Neural Networks are known to be very effective for neuromorphic processor implementations, achieving orders of magnitude improvements in energy efficiency and computational latency over traditional deep learning approaches. Comparable algorithmic performance was recently made possible as well with the adaptation of supervised training algorithms to the context of spiking neural networks. However, information including audio, video, and other sensor-derived data are typically encoded as real-valued signals that are not well-suited to spiking neural networks, preventing the network from leveraging spike timing information. Efficient encoding from real-valued signals to spikes is therefore critical and significantly impacts the performance of the overall system. To efficiently encode signals into spikes, both the preservation of information relevant to the task at hand as well as the density of the encoded spikes must be considered. In this paper, we study four spike encoding methods in the context of a speaker independent digit classification system: Send on Delta, Time to First Spike, Leaky Integrate and Fire Neuron and Bens Spiker Algorithm. We first show that all encoding methods yield higher classification accuracy using significantly fewer spikes when encoding a bio-inspired cochleagram as opposed to a traditional short-time Fourier transform. We then show that two Send On Delta variants result in classification results comparable with a state of the art deep convolutional neural network baseline, while simultaneously reducing the encoded bit rate. Finally, we show that several encoding methods result in improved performance over the conventional deep learning baseline in certain cases, further demonstrating the power of spike encoding algorithms in the encoding of real-valued signals and that neuromorphic implementation has the potential to outperform state of the art techniques.
4 citations
TL;DR: This work proposes a multi-time scale recurrent neuromorphic system based on special double-exponential adaptive threshold (DEXAT) neurons, which achieves state-of-the-art classification accuracy (90%) while using ∼ 53% lesser neurons than best reported prior art on Roshambo EMG dataset.
Abstract: —EMG (Electromyograph) signal based gesture recog- nition can prove vital for applications such as smart wear-ables and bio-medical neuro-prosthetic control. Spiking Neural Networks (SNNs) are promising for low-power, real-time EMG gesture recognition, owing to their inherent spike/event driven spatio-temporal dynamics [1], [3]–[5]. In literature, there are limited demonstrations of neuromorphic hardware implementation (at full chip/board/system scale) for EMG gesture classification. Moreover, most literature attempts exploit primitive SNNs based on LIF (Leaky Integrate & Fire) neurons. In this work, we address the aforementioned gaps with following key contribu- tions: (1) Low-power, high accuracy demonstration of EMG-signal based gesture recognition using neuromorphic Recurrent Spiking Neural Networks (RSNN). In particular, we propose a multi-time scale recurrent neuromorphic system based on special double-exponential adaptive threshold (DEXAT) [2] neurons. Our network achieves state-of-the-art classification accuracy (90%) while using ∼ 53% lesser neurons than best reported prior art on Roshambo EMG dataset [5]. (2) A new multi- channel spike encoder scheme for efficient processing of real-valued EMG data on neuromorphic systems. (3) Unique multi- compartment methodology to implement complex adaptive neurons on Intel’s dedicated neuromorphic Loihi chip is shown. (4) RSNN implementation on Loihi (Nahuku 32) achieves significant energy/latency benefits of ∼ 983X/19X compared to GPU for batch size = 50.
2 citations
DOI•
21 May 2023
TL;DR: In this paper , a Double Exponential Adaptive Threshold (DEXAT) neuron based Recurrent Spiking Neural Network (RSNN) was used for EMG gesture recognition.
Abstract: In this work, we show an efficient Electromyograph (EMG) gesture recognition using Double Exponential Adaptive Threshold (DEXAT) neuron based Recurrent Spiking Neural Network (RSNN). Our network achieves a classification accuracy of 90% while using lesser number of neurons compared to the best reported prior art on Roshambo EMG dataset. Further, to illustrate the benefits of dedicated neuromorphic hardware, we show hardware implementation of DEXAT neuron using multicompartment methodology on Intel's neuromorphic Loihi chip. RSNN implementation on Loihi (Nahuku 32) achieves significant energy/latency benefits of ~983X/19X compared to GPU for batch size = 50.
References
More filters
01 Jul 1992
TL;DR: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented, applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions.
Abstract: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions. The effective number of parameters is adjusted automatically to match the complexity of the problem. The solution is expressed as a linear combination of supporting patterns. These are the subset of training patterns that are closest to the decision boundary. Bounds on the generalization performance based on the leave-one-out method and the VC-dimension are given. Experimental results on optical character recognition problems demonstrate the good generalization obtained when compared with other learning algorithms.
11,211 citations
TL;DR: A new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks, based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry.
Abstract: A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrate-and-fire neurons in real time. We propose a new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks. It does not require a task-dependent construction of neural circuits. Instead, it is based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry. It is shown that the inherent transient dynamics of the high-dimensional dynamical system formed by a sufficiently large and heterogeneous neural circuit may serve as universal analog fading memory. Readout neurons can learn to extract in real time from the current state of such recurrent neural circuit information about current and past inputs that may be needed for diverse tasks. Stable internal states are not required for giving a stable output, since transient internal states can be transformed by readout neurons into stable target outputs due to the high dimensionality of the dynamical system. Our approach is based on a rigorous computational model, the liquid state machine, that, unlike Turing machines, does not require sequential transitions between well-defined discrete internal states. It is supported, as the Turing machine is, by rigorous mathematical results that predict universal computational power under idealized conditions, but for the biologically more realistic scenario of real-time processing of time-varying inputs. Our approach provides new perspectives for the interpretation of neural coding, the design of experiments and data analysis in neurophysiology, and the solution of problems in robotics and neurotechnology.
3,446 citations
TL;DR: This silicon retina provides an attractive combination of characteristics for low-latency dynamic vision under uncontrolled illumination with low post-processing requirements by providing high pixel bandwidth, wide dynamic range, and precisely timed sparse digital output.
Abstract: This paper describes a 128 times 128 pixel CMOS vision sensor. Each pixel independently and in continuous time quantizes local relative intensity changes to generate spike events. These events appear at the output of the sensor as an asynchronous stream of digital pixel addresses. These address-events signify scene reflectance change and have sub-millisecond timing precision. The output data rate depends on the dynamic content of the scene and is typically orders of magnitude lower than those of conventional frame-based imagers. By combining an active continuous-time front-end logarithmic photoreceptor with a self-timed switched-capacitor differencing circuit, the sensor achieves an array mismatch of 2.1% in relative intensity event threshold and a pixel bandwidth of 3 kHz under 1 klux scene illumination. Dynamic range is > 120 dB and chip power consumption is 23 mW. Event latency shows weak light dependency with a minimum of 15 mus at > 1 klux pixel illumination. The sensor is built in a 0.35 mum 4M2P process. It has 40times40 mum2 pixels with 9.4% fill factor. By providing high pixel bandwidth, wide dynamic range, and precisely timed sparse digital output, this silicon retina provides an attractive combination of characteristics for low-latency dynamic vision under uncontrolled illumination with low post-processing requirements.
1,628 citations
TL;DR: The pertinent issues and best practices in EMG pattern recognition are described, the major challenges in deploying robust control are identified, and research directions that may have an effect in the near future are advocated.
Abstract: Using electromyogram (EMG) signals to control upper-limb prostheses is an important clinical option, offering a person with amputation autonomy of control by contracting residual muscles. The dexterity with which one may control a prosthesis has progressed very little, especially when control- ling multiple degrees of freedom. Using pattern recognition to discriminate multiple degrees of freedom has shown great promise in the research literature, but it has yet to transition to a clinically viable option. This article describes the pertinent issues and best practices in EMG pattern recognition, identifies the major challenges in deploying robust control, and advocates research directions that may have an effect in the near future.
837 citations
TL;DR: In 1907, long before the mechanisms responsible for the generation of neuronal action potentials were known, Lapicque developed a neuron model that is still widely used today, and this remarkable achievement stresses that, in neural modeling, studies of function do not necessarily require an understanding of mechanism.
581 citations