DenRAM: neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays.

An increasing number of studies are highlighting the importance of spatial dendritic branching in pyramidal neurons in the neocortex for supporting non-linear computation through localized synaptic integration. In particular, dendritic branches play a key role in temporal signal processing and feature detection. This is accomplished thanks to coincidence detection (CD) mechanisms enabled by the presence of synaptic delays that align temporally disparate inputs for effective integration. Computational studies on spiking neural networks further highlight the significance of delays for achieving spatio-temporal pattern recognition with pure feed-forward neural networks, without the need of resorting to recurrent architectures. In this work, we present "DenRAM", the first realization of a feed-forward spiking neural network with dendritic compartments, implemented using analog electronic circuits integrated into a 130 nm technology node and coupled with Resistive Random Access Memory (RRAM) technology. DenRAM's dendritic circuits use RRAM devices to implement both delays and synaptic weights in the network. By configuring the RRAM devices to reproduce bio-realistic timescales, and by exploiting their heterogeneity we experimentally demonstrate DenRAM's ability to replicate synaptic delay profiles, and to efficiently implement CD for spatio-temporal pattern recognition. To validate the architecture, we conduct comprehensive system-level simulations on two representative temporal benchmarks, demonstrating DenRAM's resilience to analog hardware noise, and its superior accuracy compared to recurrent architectures with an equivalent number of parameters. DenRAM not only brings rich temporal processing capabilities to neuromorphic architectures, but also reduces the memory footprint of edge devices, warrants high accuracy on temporal benchmarks, and represents a significant step-forward in low-power real-time signal processing technologies.

Mosaic: in-memory computing and routing for small-world spike-based neuromorphic systems.

The brain's connectivity is locally dense and globally sparse, forming a small-world graph-a principle prevalent in the evolution of various species, suggesting a universal solution for efficient information routing. However, current artificial neural network circuit architectures do not fully embrace small-world neural network models. Here, we present the neuromorphic Mosaic: a non-von Neumann systolic architecture employing distributed memristors for in-memory computing and in-memory routing, efficiently implementing small-world graph topologies for Spiking Neural Networks (SNNs). We've designed, fabricated, and experimentally demonstrated the Mosaic's building blocks, using integrated memristors with 130 nm CMOS technology. We show that thanks to enforcing locality in the connectivity, routing efficiency of Mosaic is at least one order of magnitude higher than other SNN hardware platforms. This is while Mosaic achieves a competitive accuracy in a variety of edge benchmarks. Mosaic offers a scalable approach for edge systems based on distributed spike-based computing and in-memory routing.

Flexible Unipolar IGZO Transistor-Based Integrate and Fire Neurons for Spiking Neuromorphic Applications.

In this article, three different implementations of an Axon-Hillock circuit are presented, one of the basic building blocks of spiking neural networks. In this work, we explored the design of such circuits using a unipolar thin-film transistor technology based on amorphous InGaZnO, often used for large-area electronics. All the designed circuits are fabricated by direct material deposition and patterning on top of a flexible polyimide substrate. Axon-Hillock circuits presented in this article consistently show great adaptability of the basic properties of a spiking neuron such as output spike frequency adaptation and output spike width adaptation. Additional degrees of adaptability are demonstrated with each of the Axon-Hillock circuit varieties: neuron circuit threshold voltage adaptation, differentiation between input signal importance, and refractory period modulation. The proposed neuron can change its firing frequency up to three orders of magnitude by varying a single voltage brought to a circuit terminal. This allows the neuron to function, and potentially learn, at vastly different timescales that coincide with the biologically meaningful timescales, going from milliseconds to seconds, relevant for circuits meant for interaction with the environment. Thanks to careful design choices, the average measured power consumption is kept in the nW range, realistically allowing upscaling towards the spiking neural networks in the future. The spiking neuron with refractory period modulation presented in this work has an area of 607.3 µm × 492.2 µm, it experimentally demonstrated firing rates as low as 11.926 mHz, and its energy consumption per spike is ≈ 700 pJ at 30 Hz.

Self-organization of an inhomogeneous memristive hardware for sequence learning.

Learning is a fundamental component of creating intelligent machines. Biological intelligence orchestrates synaptic and neuronal learning at multiple time scales to self-organize populations of neurons for solving complex tasks. Inspired by this, we design and experimentally demonstrate an adaptive hardware architecture Memristive Self-organizing Spiking Recurrent Neural Network (MEMSORN). MEMSORN incorporates resistive memory (RRAM) in its synapses and neurons which configure their state based on Hebbian and Homeostatic plasticity respectively. For the first time, we derive these plasticity rules directly from the statistical measurements of our fabricated RRAM-based neurons and synapses. These "technologically plausible" learning rules exploit the intrinsic variability of the devices and improve the accuracy of the network on a sequence learning task by 30%. Finally, we compare the performance of MEMSORN to a fully-randomly-set-up spiking recurrent network on the same task, showing that self-organization improves the accuracy by more than 15%. This work demonstrates the importance of the device-circuit-algorithm co-design approach for implementing brain-inspired computing hardware.

Neuromorphic object localization using resistive memories and ultrasonic transducers.

Real-world sensory-processing applications require compact, low-latency, and low-power computing systems. Enabled by their in-memory event-driven computing abilities, hybrid memristive-Complementary Metal-Oxide Semiconductor neuromorphic architectures provide an ideal hardware substrate for such tasks. To demonstrate the full potential of such systems, we propose and experimentally demonstrate an end-to-end sensory processing solution for a real-world object localization application. Drawing inspiration from the barn owl's neuroanatomy, we developed a bio-inspired, event-driven object localization system that couples state-of-the-art piezoelectric micromachined ultrasound transducer sensors to a neuromorphic resistive memories-based computational map. We present measurement results from the fabricated system comprising resistive memories-based coincidence detectors, delay line circuits, and a full-custom ultrasound sensor. We use these experimental results to calibrate our system-level simulations. These simulations are then used to estimate the angular resolution and energy efficiency of the object localization model. The results reveal the potential of our approach, evaluated in orders of magnitude greater energy efficiency than a microcontroller performing the same task.

Reconfigurable halide perovskite nanocrystal memristors for neuromorphic computing.

Many in-memory computing frameworks demand electronic devices with specific switching characteristics to achieve the desired level of computational complexity. Existing memristive devices cannot be reconfigured to meet the diverse volatile and non-volatile switching requirements, and hence rely on tailored material designs specific to the targeted application, limiting their universality. "Reconfigurable memristors" that combine both ionic diffusive and drift mechanisms could address these limitations, but they remain elusive. Here we present a reconfigurable halide perovskite nanocrystal memristor that achieves on-demand switching between diffusive/volatile and drift/non-volatile modes by controllable electrochemical reactions. Judicious selection of the perovskite nanocrystals and organic capping ligands enable state-of-the-art endurance performances in both modes - volatile (2 × 106 cycles) and non-volatile (5.6 × 103 cycles). We demonstrate the relevance of such proof-of-concept perovskite devices on a benchmark reservoir network with volatile recurrent and non-volatile readout layers based on 19,900 measurements across 25 dynamically-configured devices.

Utilizing the Switching Stochasticity of HfO2/TiOx-Based ReRAM Devices and the Concept of Multiple Device Synapses for the Classification of Overlapping and Noisy Patterns.

With the arrival of the Internet of Things (IoT) and the challenges arising from Big Data, neuromorphic chip concepts are seen as key solutions for coping with the massive amount of unstructured data streams by moving the computation closer to the sensors, the so-called "edge computing." Augmenting these chips with emerging memory technologies enables these edge devices with non-volatile and adaptive properties which are desirable for low power and online learning operations. However, an energy- and area-efficient realization of these systems requires disruptive hardware changes. Memristor-based solutions for these concepts are in the focus of research and industry due to their low-power and high-density online learning potential. Specifically, the filamentary-type valence change mechanism (VCM memories) have shown to be a promising candidate In consequence, physical models capturing a broad spectrum of experimentally observed features such as the pronounced cycle-to-cycle (c2c) and device-to-device (d2d) variability are required for accurate evaluation of the proposed concepts. In this study, we present an in-depth experimental analysis of d2d and c2c variability of filamentary-type bipolar switching HfO2/TiOx nano-sized crossbar devices and match the experimentally observed variabilities to our physically motivated JART VCM compact model. Based on this approach, we evaluate the concept of parallel operation of devices as a synapse both experimentally and theoretically. These parallel synapses form a synaptic array which is at the core of neuromorphic chips. We exploit the c2c variability of these devices for stochastic online learning which has shown to increase the effective bit precision of the devices. Finally, we demonstrate that stochastic switching features for a pattern classification task that can be employed in an online learning neural network.

Adaptive Extreme Edge Computing for Wearable Devices.

Wearable devices are a fast-growing technology with impact on personal healthcare for both society and economy. Due to the widespread of sensors in pervasive and distributed networks, power consumption, processing speed, and system adaptation are vital in future smart wearable devices. The visioning and forecasting of how to bring computation to the edge in smart sensors have already begun, with an aspiration to provide adaptive extreme edge computing. Here, we provide a holistic view of hardware and theoretical solutions toward smart wearable devices that can provide guidance to research in this pervasive computing era. We propose various solutions for biologically plausible models for continual learning in neuromorphic computing technologies for wearable sensors. To envision this concept, we provide a systematic outline in which prospective low power and low latency scenarios of wearable sensors in neuromorphic platforms are expected. We successively describe vital potential landscapes of neuromorphic processors exploiting complementary metal-oxide semiconductors (CMOS) and emerging memory technologies (e.g., memristive devices). Furthermore, we evaluate the requirements for edge computing within wearable devices in terms of footprint, power consumption, latency, and data size. We additionally investigate the challenges beyond neuromorphic computing hardware, algorithms and devices that could impede enhancement of adaptive edge computing in smart wearable devices.

Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications.

The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors has brought on new opportunities for applying both Deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies including emerging memristive devices, Field Programmable Gate Arrays (FPGAs), and Complementary Metal Oxide Semiconductor (CMOS) can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. The tutorial is augmented with case studies of the vast literature on neural network and neuromorphic hardware as applied to the healthcare domain. We benchmark various hardware platforms by performing a sensor fusion signal processing task combining electromyography (EMG) signals with computer vision. Comparisons are made between dedicated neuromorphic processors and embedded AI accelerators in terms of inference latency and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that various accelerators and neuromorphic processors introduce to healthcare and biomedical domains.

Hand-Gesture Recognition Based on EMG and Event-Based Camera Sensor Fusion: A Benchmark in Neuromorphic Computing.

Hand gestures are a form of non-verbal communication used by individuals in conjunction with speech to communicate. Nowadays, with the increasing use of technology, hand-gesture recognition is considered to be an important aspect of Human-Machine Interaction (HMI), allowing the machine to capture and interpret the user's intent and to respond accordingly. The ability to discriminate between human gestures can help in several applications, such as assisted living, healthcare, neuro-rehabilitation, and sports. Recently, multi-sensor data fusion mechanisms have been investigated to improve discrimination accuracy. In this paper, we present a sensor fusion framework that integrates complementary systems: the electromyography (EMG) signal from muscles and visual information. This multi-sensor approach, while improving accuracy and robustness, introduces the disadvantage of high computational cost, which grows exponentially with the number of sensors and the number of measurements. Furthermore, this huge amount of data to process can affect the classification latency which can be crucial in real-case scenarios, such as prosthetic control. Neuromorphic technologies can be deployed to overcome these limitations since they allow real-time processing in parallel at low power consumption. In this paper, we present a fully neuromorphic sensor fusion approach for hand-gesture recognition comprised of an event-based vision sensor and three different neuromorphic processors. In particular, we used the event-based camera, called DVS, and two neuromorphic platforms, Loihi and ODIN + MorphIC. The EMG signals were recorded using traditional electrodes and then converted into spikes to be fed into the chips. We collected a dataset of five gestures from sign language where visual and electromyography signals are synchronized. We compared a fully neuromorphic approach to a baseline implemented using traditional machine learning approaches on a portable GPU system. According to the chip's constraints, we designed specific spiking neural networks (SNNs) for sensor fusion that showed classification accuracy comparable to the software baseline. These neuromorphic alternatives have increased inference time, between 20 and 40%, with respect to the GPU system but have a significantly smaller energy-delay product (EDP) which makes them between 30× and 600× more efficient. The proposed work represents a new benchmark that moves neuromorphic computing toward a real-world scenario.

Discrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network.

An accurate description of muscular activity plays an important role in the clinical diagnosis and rehabilitation research. The electromyography (EMG) is the most used technique to make accurate descriptions of muscular activity. The EMG is associated with the electrical changes generated by the activity of the motor neurons. Typically, to decode the muscular activation during different movements, a large number of individual motor neurons are monitored simultaneously, producing large amounts of data to be transferred and processed by the computing devices. In this paper, we follow an alternative approach that can be deployed locally on the sensor side. We propose a neuromorphic implementation of a spiking neural network (SNN) to extract spatio-temporal information of EMG signals locally and classify hand gestures with very low power consumption. We present experimental results on the input data stream using a mixed-signal analog/digital neuromorphic processor. We performed a thorough investigation on the performance of the SNN implemented on the chip, by: first, calculating PCA on the activity of the silicon neurons at the input and the hidden layers to show how the network helps in separating the samples of different classes; second, performing classification of the data using state-of-the-art SVM and logistic regression methods and a hardware-friendly spike-based read-out. The traditional algorithm achieved a classification rate of [Formula: see text] and [Formula: see text], respectively, and the spiking learning method achieved [Formula: see text]. The power consumption of the SNN is [Formula: see text], showing the potential of this approach for ultra-low power processing.

A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: from mitigation to exploitation.

Memristive devices represent a promising technology for building neuromorphic electronic systems. In addition to their compactness and non-volatility, they are characterized by their computationally relevant physical properties, such as their state-dependence, non-linear conductance changes, and intrinsic variability in both their switching threshold and conductance values, that make them ideal devices for emulating the bio-physics of real synapses. In this paper we present a spiking neural network architecture that supports the use of memristive devices as synaptic elements and propose mixed-signal analog-digital interfacing circuits that mitigate the effect of variability in their conductance values and exploit their variability in the switching threshold for implementing stochastic learning. The effect of device variability is mitigated using pairs of memristive devices configured in a complementary push-pull mechanism and interfaced to a current-mode normalizer circuit. The stochastic learning mechanism is obtained by mapping the desired change in synaptic weight into a corresponding switching probability that is derived from the intrinsic stochastic behavior of memristive devices. We demonstrate the features of the CMOS circuits and apply the architecture proposed to a standard neural network hand-written digit classification benchmark based on the MNIST data-set. We evaluate the performance of the approach proposed in this benchmark using behavioral-level spiking neural network simulation, showing both the effect of the reduction in conductance variability produced by the current-mode normalizer circuit and the increase in performance as a function of the number of memristive devices used in each synapse.

From Winner-Takes-All to Winners-Share-All: Exploiting the Information Capacity in Temporal Codes.

In this letter, we have implemented and compared two neural coding algorithms in the networks of spiking neurons: Winner-takes-all (WTA) and winners-share-all (WSA). Winners-Share-All exploits the code space provided by the temporal code by training a different combination of [Formula: see text] out of [Formula: see text] neurons to fire together in response to different patterns, while WTA uses a one-hot-coding to respond to distinguished patterns. Using WSA, the maximum value of [Formula: see text] in order to maximize information capacity using [Formula: see text] output neurons was theoretically determined and utilized. A small proof-of-concept classification problem was applied to a spiking neural network using both algorithms to classify 14 letters of English alphabet with an image size of 15 [Formula: see text] 15 pixels. For both schemes, a modified spike-timing-dependent-plasticity (STDP) learning rule has been used to train the spiking neurons in an unsupervised fashion. The performance and the number of neurons required to perform this computation are compared between the two algorithms. We show that by tolerating a small drop in performance accuracy (84% in WSA versus 91% in WTA), we are able to reduce the number of output neurons by more than a factor of two. We show how the reduction in the number of neurons will increase as the number of patterns increases. The reduction in the number of output neurons would then proportionally reduce the number of training parameters, which requires less memory and hence speeds up the computation, and in the case of neuromorphic implementation on silicon, would take up much less area.