Analog computing at the edge is an emerging strategy to limit data storage and transmission requirements, as well as energy consumption, and its practical implementation is in its initial stages of development. Translating properties of biological neurons into hardware offers a pathway towards low-power, real-time edge processing. Specifically, resonator neurons offer selectivity to specific frequencies as a potential solution for temporal signal processing. Here, we show a fabricated Complementary Metal-Oxide-Semiconductor (CMOS) mixed-signal Resonate-and-Fire (R&F) neuron circuit implementation that emulates the behavior of these neural cells responsible for controlling oscillations within the central nervous system. We integrate the design with asynchronous handshake capabilities, perform comprehensive variability analyses, and characterize its frequency detection functionality. Our results demonstrate the feasibility of large-scale integration within neuromorphic systems, thereby advancing the exploitation of bio-inspired circuits for efficient edge temporal signal processing.

The ability to detect correlated events in the environment is an important feat of biological neural networks. Neuromorphic computing strives to mimic this ability for efficient sensory processing. For this purpose, we propose a HfO2-based ferroelectric capacitor (FeCap)-complementary metal oxide semiconductor (CMOS) leaky integrate-and-fire (LIF) neuron able to detect highly correlated events exploiting two different temporal dynamics. The possibility to exploit two time constants increases the versatility of the neuron and its dynamic adaptation while offering a compact and elegant solution for detection of both transient and sustained coincidences. Moreover, the time constants are in biologically relevant time scales, which makes the neuron suitable to solve real-time tasks such as keyword spotting or sensory processing. The proposed FeCap-based LIF (FeLIF) neuron enriches the dynamic of a standard LIF neuron fostering the development of advanced event-based analog neuromorphic hardware.

Odour source localization is crucial in life-saving scenarios like pinpointing gas leaks, detecting explosives, searching for earthquake survivors, or locating fires at their origin. The turbulent character of natural environments makes this task very challenging. The absolute concentration of odour plumes carries little meaning and these plumes are only encountered in an intermittent, transient fashion. However, navigation algorithms that are driven by odour encounter events, can successfully find odour sources by extracting spatiotemporal information. The event driven nature of odour plumes motivates a fully event-driven sensing and processing pipeline for robot navigation. Hence, we developed a spiking neural network, implemented on neuromorphic hardware, that can successfully decode odour-puff direction from a pair of enose-systems. This is to our knowledge the first fully event driven neuromorphic system for odour localization.

Hopfield attractor networks are robust distributed models of human memory, but they lack a general mechanism for effecting state-dependent attractor transitions in response to input. We propose construction rules such that an attractor network may implement an arbitrary finite state machine (FSM), where states and stimuli are represented by high-dimensional random vectors and all state transitions are enacted by the attractor network's dynamics. Numerical simulations show the capacity of the model, in terms of the maximum size of implementable FSM, to be linear in the size of the attractor network for dense bipolar state vectors and approximately quadratic for sparse binary state vectors. We show that the model is robust to imprecise and noisy weights, and so a prime candidate for implementation with high-density but unreliable devices. By endowing attractor networks with the ability to emulate arbitrary FSMs, we propose a plausible path by which FSMs could exist as a distributed computational primitive in biological neural networks.

With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a “wake-up” mechanism for subsequent computationally expensive speech recognition. One promising approach is the use of neuromorphic sensors and spiking neural networks (SNNs) implemented in neuromorphic processors for sparse event-driven sensing. However, this requires resource-efficient SNN mechanisms for temporal encoding, which need to consider that these systems process information in a streaming manner, with physical time being an intrinsic property of their operation. In this work, two candidate neurocomputational elements for temporal encoding and feature extraction in SNNs described in recent literature—the spiking time-difference encoder (TDE) and disynaptic excitatory-inhibitory (E-I) elements—are comparatively investigated in a keyword-spotting task on formants computed from spoken digits in the TIDIGITS dataset. While both encoders improve performance over direct classification of the formant features in the training data, enabling a complete binary classification with a logistic regression model, they show no clear improvements on the test set. Resource-efficient keyword spotting applications may benefit from the use of these encoders, but further work on methods for learning the time constants and weights is required to investigate their full potential.

Insects have extraordinary navigational abilities. Monarch butterflies migrate every year to the same forest over hundreds of kilometers, desert ants find their way back to the nest tens of meters away and dung beetles maintain the same heading direction over meters. The performance of these agents has been optimized by evolution over the last 500 million years leading to power-efficient, low-latency and precise sensorimotor systems. Research efforts in the field of neuroscience, biology and robotics are instrumental for uncovering the neural substrate of insect navigation abilities. The development of models of insect navigation tightly coupled with the insect connectome and neurophysiology and their embedding in closed loop systems support the understanding of embodied animal cognition and can advance robotic systems. In this work, we focus on insect navigation because of the efficient insect navigational apparatus. Furthermore, the recent discovery of the central complex, the neuronal center of insect navigation, facilitates the development of new hypotheses about insect navigation. All navigating insects need to perform some kind of goal-directed behavior during which they have to reach a specific goal location or maintain the same movement direction over long distances. Such behavior requires the agent to be aware of its current heading direction, desired heading direction, and the error between them. Building on previous research in the field, we propose a novel model for this error estimation that can in principle be generalized for all navigating insect species. We implement the model in a spiking neural network and test its capabilities on a simulated robotic platform. The precision of the network is comparable to or even better than the biological role model. Thus, our implementation serves as a working hypothesis for how the heading error might be computed in the insect brain. Our model will help to explain navigational behavior in fruit flies, orchid bees, bumble bees and some less researched insect species. Furthermore, its simplicity in comparison to other models and implementation in a spiking neural network makes it very suitable for neuromorphic systems, an emerging field of brain-inspired hardware.

Attractor networks are widely understood to be a re-occurring primitive that underlies cognitive function. Stabilising activity in spiking attractor networks however remains a difficult task, especially when implemented in analog integrated circuits (aIC). We introduce here a novel circuit implementation of a hard Winner-Take-All (hWTA) mechanism, in which competing neurons' refractory circuits are coupled together, and thus their spiking is forced to be mutually exclusive. We demonstrate stable persistent-firing attractor dynamics in a small on-chip network consisting of hWTA-connected neurons and excitatory recurrent synapses. Its utility within larger networks is demonstrated in simulation, and shown to support overlapping attractors and be robust to synaptic weight mismatch. The realised hWTA mechanism is thus useful for stabilising activity in spiking networks composed of unreliable components, without the need for careful parameter tuning.

Neuromorphic systems are a viable alternative to conventional systems for real-time tasks with constrained resources. Their low power consumption, compact hardware realization, and low-latency response characteristics are the key ingredients of such systems. Furthermore, the event-based signal processing approach can be exploited for reducing the computational load and avoiding data loss due to its inherently sparse representation of sensed data and adaptive sampling time. In event-based systems, the information is commonly coded by the number of spikes within a specific temporal window. However, the temporal information of event-based signals can be difficult to extract when using rate coding. In this work, we present a novel digital implementation of the model, called time difference encoder (TDE), for temporal encoding on event-based signals, which translates the time difference between two consecutive input events into a burst of output events. The number of output events along with the time between them encodes the temporal information. The proposed model has been implemented as a digital circuit with a configurable time constant, allowing it to be used in a wide range of sensing tasks that require the encoding of the time difference between events, such as optical flow-based obstacle avoidance, sound source localization, and gas source localization. This proposed bioinspired model offers an alternative to the Jeffress model for the interaural time difference estimation, which is validated in this work with a sound source lateralization proof-of-concept system. The model was simulated and implemented on a field-programmable gate array (FPGA), requiring 122 slice registers of hardware resources and less than 1 mW of power consumption.

Robots and users of hand prosthesis could easily manipulate objects if endowed with the sense of touch. Towards this goal, information about touched objects and surfaces has to be inferred from raw data coming from the sensors. An important cue for objects discrimination is the orientation of edges, that is used both in artificial vision and touch as pre-processing stage. We present a spiking neural network, inspired on the encoding of edges in human first order tactile afferents. The network uses three layers of Leaky Integrate and Fire neurons to distinguish different edge orientations of a bar pressed on the artificial skin of the iCub robot. The architecture is successfully able to discriminate eight different orientations (from 0oto 180o), by implementing a structured model of overlapping receptive fields. We demonstrate that the network can learn the appropriate connectivity through unsupervised spike based learning, and that the number and spatial distribution of sensitive areas within the receptive fields are important in edge orientation discrimination.

Ferroelectric tunneling junctions (FTJ) are considered to be the intrinsically most energy efficient memristors. In this work, specific electrical features of ferroelectric hafnium-zirconium oxide based FTJ devices are investigated. Moreover, the impact on the design of FTJ-based circuits for edge computing applications is discussed by means of two example circuits.

Humans can distinguish fabrics by their textures, even when they are finer than the density of tactile sensors. Evidence suggests that this ability is produced by the nervous system using an active touch strategy. When the finger slides over a texture, the nervous system converts the texture’s spatial period into an equivalent spiking frequency. Many studies focused on modeling the biological encoding part that translates the spatial frequency into a temporal spiking frequency, but few explored the decoding part. In this work, we propose a novel approach based on a spiking neural network able to detect the frequency of an input signal. Inspired by biological evidence, our architecture detects the range in which the encoded frequency dwells and could therefore decode the texture’s spatial period. The network has been designed to be composed of existing neuromorphic spiking primitives. This property enables a straightforward implementation on integrated silicon circuits, allowing the texture decoding at the edge of the sensor.

Neuronal activity of recurrent neural networks (RNNs) experimentally observed in the hippocampus is widely believed to play a key role for mammalian ability to associate concepts and make decisions. For this reason, RNNs have rapidly gained strong interest as computational enabler of brain-inspired cognitive functions in hardware. From the technology viewpoint, nonvolatile memory devices such as phase change memory (PCM) and resistive switching memory (RRAM) have become a key asset to allow for high synaptic density and biorealistic cognitive functionality. In this work, we demonstrate for the first time associative learning and decision making in a hardware Hopfield RNN with 6 spiking neurons and PCM synapses via storage, recall and competition of attractor states. We also experimentally demonstrate the solution of a constraint satisfaction problem (CSP) namely a Sudoku with size 2×2 in hardware and 9×9 in simulation. These results support spiking RNNs with PCM devices for the implementation of decision making capabilities in hardware neuromorphic systems.

The brain is able to solve complex tasks in real time by combining different sensory cues with previously acquired knowledge. Inspired by the brain, we designed a neuromorphic demonstrator which combines auditory and visual input to find an obstacle free direction closest to the sound source. The system consists of two event-based sensors (the eDVS for vision and the NAS for audition) mounted onto a pan-tilt unit and a spiking neural network implemented on the SpiNNaker platform. By combining the different sensory information, the demonstrator is able to point at a sound source direction while avoiding obstacles in real time.

The development of neuromorphic systems capable of mimicking the behavior of the human brain has recently received an increasing deal of interest. However, the building of such artificial systems has been hindered by the lack of commercial technologies with nanoscale integration of synaptic devices as well as the complexity of the biological neural architecture in terms of connectivity, parallelism, and plasticity behavior. In particular, there is a wide consensus on the relevance of recurrent connections in the human brain, and their key role for associative learning and pattern classification. Fundamental primitives of cognitive computing can therefore be demonstrated by means of Recurrent Neural Networks (RNNs). In this work, we design and simulate a Hopfield-type RNN with HfO2 RRAM devices capable of learning via spike-timing dependent plasticity (STDP). We first demonstrate learning and recall of a single attractor state in a 4-neuron RNN. Based on this result, we then simulate signal restoration of two orthogonal patterns in a 64-neuron RNN, thus supporting RRAM-based RNN with cognitive computing functionalities.

Emerging memory devices such as resistive switching memory (RRAM) and phase change memory (PCM) are gaining interest as future synapses for smart neuromorphic systems, capable of learning and inference similar to the human brain. Developing neuromorphic systems with emerging memory technologies requires accurate co-design of devices, synapses, and neural networks, aiming at the replication of the fundamental learning processes in the human brain, such as spike-timing dependent plasticity (STDP) and spike-rate dependent plasticity (SRDP). This work addresses the development of RRAM synapses for unsupervised learning via STDP. This learning scheme is implemented in a simple one-transistor/one-resistor (1T1R) structure capable of long term potentiation and depression with standard memory-grade RRAM devices. 1T1R synapses are implemented in a spiking neural network (SNN) with feedforward architecture, allowing for the hardware demonstration of unsupervised learning. Recurrent SNNs employing the same fundamental STDP rule are then addressed by simulation of associative learning, pattern reconstruction, and recall of spatiotemporal sequences.

Apparent motion of the surroundings on an agent's retina can be used to navigate through cluttered environments, avoid collisions with obstacles, or track targets of interest. The pattern of apparent motion of objects, (i.e., the optic flow), contains spatial information about the surrounding environment. For a small, fast-moving agent, as used in search and rescue missions, it is crucial to estimate the distance to close-by objects to avoid collisions quickly. This estimation cannot be done by conventional methods, such as frame-based optic flow estimation, given the size, power, and latency constraints of the necessary hardware. A practical alternative makes use of event-based vision sensors. Contrary to the frame-based approach, they produce so-called events only when there are changes in the visual scene. We propose a novel asynchronous circuit, the spiking elementary motion detector (sEMD), composed of a single silicon neuron and synapse, to detect elementary motion from an event-based vision sensor. The sEMD encodes the time an object's image needs to travel across the retina into a burst of spikes. The number of spikes within the burst is proportional to the speed of events across the retina. A fast but imprecise estimate of the time-to-travel can already be obtained from the first two spikes of a burst and refined by subsequent interspike intervals. The latter encoding scheme is possible due to an adaptive nonlinear synaptic efficacy scaling. We show that the sEMD can be used to compute a collision avoidance direction in the context of robotic navigation in a cluttered outdoor environment and compared the collision avoidance direction to a frame-based algorithm. The proposed computational principle constitutes a generic spiking temporal correlation detector that can be applied to other sensory modalities (e.g., sound localization), and it provides a novel perspective to gating information in spiking neural networks.

Despite being well established in robotics, classical motor controllers have several disadvantages: they pose a high computational load, therefore requiring powerful devices, they are not easy to tune and they are not suited for neuroprosthetics. In contrast, bio-inspired controller do not transform the output of the controller therefore no delays are introduced and a smooth response is achieved; they also have a high scalability. Finally, the most important feature of bio-inspired controllers is that they could integrate learning features to make them adaptable to new tasks within the same hardware robotic platform. We present the model and simulation of a spiking neural network for low-level motor control. The proposed neural network acts as a motor controller and produces pulsed signals which can be directly interfaced with commercial DC motors. The simulated network is compatible with neuromorphic VLSI implementation and paves the way to the implementation bio-inspired motor controller which are compact, low power, scalable and compatible with neuroprosthetic. The network presented is inspired by the current knowledge about biological motor control: it comprises alpha motoneuron for driving the motor and spindle populations to provide the feedback and close the loop. The spikes from the motoneuron population are time lengthen to a fixed amount of time and supplied to the simulated motor: Pulse Frequency Modulation (PFM) modulation is used. This paper presents the software simulations using the Brian simulator for a position controller. Our controller is a first step toward a novel bio-inspired motor control approach suitable for robotics as well as neuroprosthetic.

A key feature of autonomous systems is the ability to solve computationally intensive tasks while adapting to changes in the environment. The learning capabilities required for this feature are underdeveloped in artificial systems, especially when compared to those of humans and animals. We aim at the implementation of biologically inspired learning algorithms to be embedded in full-custom VLSI spiking neural networks with the long term goal of constructing compact real-time low-power learning systems. Molecular studies have demonstrated a key role of calcium ions for long term synaptic plasticity. These experimental results have inspired mathematical models and hardware implementations of calcium based learning algorithms. Here we present a novel VLSI implementation of a recently proposed calcium-based learning algorithm, its simulation results and comparison with the mathematical model.

Homeostatic intrinsic plasticity is a neurobiological mechanism which adapts a neuron's channel properties over long timescales to achieve a desired average firing rate. This mechanism works to stabilize neural network dynamics. We present simulation results of a neuromorphic circuit implementation of homeostatic intrinsic plasticity using floating-gate transistors. While high voltages are required for tunneling and injection, the control parameter in our implementation is a low voltage, allowing for easy interfacing with typical analog CMOS control circuitry.

The development of fast and mobile drug detection is an important aspect of personalized medicine. It enables the quick assessment of inter-individual differences in drug metabolism and corresponding adjustments of the dose. Recent developments of amperometric biosensors using cytochrome P450 (CYP) show great promise, by lowering the detection limit to physiological range for several drugs via the usage of Multi Walled Carbon Nanotubes (MWCNT). The next challenge is to develop algorithms for processing the resulting sensor data compatible with low-power hardware, which would allow the development of portable battery-powered devices. In this work we pursue a novel approach to this problem. Here we provide a proof of principle by demonstrating how sensor data could be analyzed using a conventional multi-layer perceptron network with error-backpropagation.

We present real-time neuromorphic VLSI circuits that implement the synaptic dynamics of Short Term Plasticity (STP). STP supports useful signal processing computational primitives such as change detection and gain control. Compact circuits implementing these mechanisms play a key role in providing neuromorphic VLSI systems with autonomous adaptation capabilities. We propose two different, flexible, short-term adaptation CMOS circuits for controlling the efficacy of synapses in response to incoming spikes. These circuits can be configured to either implement short-term depression or facilitation, with independent control over the adaptation and recovery rates. Our results demonstrate the dynamic properties of the proposed circuits and their behaviour in the frequency domain.

Several analog and digital brain-inspired electronic systems have been recently proposed as dedicated solutions for fast simulations of spiking neural networks. While these architectures are useful for exploring the computational properties of large-scale models of the nervous system, the challenge of building low-power compact physical artifacts that can behave intelligently in the real world and exhibit cognitive abilities still remains open. In this paper, we propose a set of neuromorphic engineering solutions to address this challenge. In particular, we review neuromorphic circuits for emulating neural and synaptic dynamics in real time and discuss the role of biophysically realistic temporal dynamics in hardware neural processing architectures; we review the challenges of realizing spike-based plasticity mechanisms in real physical systems and present examples of analog electronic circuits that implement them;we describe the computational properties of recurrent neural networks and show how neuromorphic winner-take-all circuits can implement working-memory and decision-making mechanisms. We validate the neuromorphic approach proposed with experimental results obtained from our own circuits and systems, and argue how the circuits and networks presented in this work represent a useful set of components for efficiently and elegantly implementing neuromorphic cognition.

The brain combines and integrates multiple cues to take coherent, context-dependent action using distributed, event-based computational primitives. Computational models that use these principles in software simulations of recurrently coupled spiking neural networks have been demonstrated in the past, but their implementation in hybrid analog/digital Very Large Scale Integration (VLSI) spiking neural networks remains challenging. Here, we demonstrate a distributed spiking neural network architecture comprising multiple neuromorphic VLSI chips able to reproduce these types of cue combination and integration operations. This is achieved by encoding cues as population activities of input nodes in a network of recurrently coupled VLSI Integrate-and-Fire (I&F) neurons. The value of the cue is place-encoded, while its uncertainty is represented by the width of the population activity profile. Relationships among different cues are specified through bidirectional connectivity matrices, shared between the individual input node populations and an intermediate node population. The resulting network dynamics bidirectionally relate not only the values of three variables according to a specified relation, but also their uncertainties. When cues on two populations are specified, the standard deviation of the activity in the unspecified population varies approximately linearly with the widths of the two input cues, and has less than 6% error in position compared to the value specified by the inputs. The results suggest a mechanism for recurrently relating cues such that missing information can both be recovered and assigned a level of certainty.

Axonal delays are used in neural computation to implement faithful models of biological neural systems, and in spiking neural networks models to solve computationally demanding tasks. While there is an increasing number of software simulations of spiking neural networks that make use of axonal delays, only a small fraction of currently existing hardware neuromorphic systems supports them. In this paper we demonstrate a strategy to implement temporal delays in hardware spiking neural networks distributed across multiple Very Large Scale Integration (VLSI) chips. This is achieved by exploiting the inherent device mismatch present in the analog circuits that implement silicon neurons and synapses inside the chips, and the digital communication infrastructure used to configure the network topology and transmit the spikes across chips. We present an example of a recurrent VLSI spiking neural network that employs axonal delays and demonstrate how the proposed strategy efficiently implements them in hardware.

The ongoing motor output of the brain depends on its remarkable ability to rapidly transform and fuse a variety of sensory streams in real-time. The brain processes these data using networks of neurons that communicate by asynchronous spikes, a technology that is dramatically different from conventional electronic systems. We report here a step towards constructing electronic systems with analogous performance to the brain. Our VLSI spiking neural network combines in real-time three distinct sources of input data; each is place-encoded on an individual neuronal population that expresses soft Winner-Take-All dynamics. These arrays are combined according to a user-specified function that is embedded in the reciprocal connections between the soft Winner-Take-All populations and an intermediate shared population. The overall network is able to perform function approximation (missing data can be inferred from the available streams) and cue integration (when all input streams are present they enhance one another synergistically). The network performs these tasks with about 80% and 90% reliability, respectively. Our results suggest that with further technical improvement, it may be possible to implement more complex probabilistic models such as Bayesian networks in neuromorphic electronic systems.

In the past recent years several research groups have proposed neuromorphic Very Large Scale Integration (VLSI) devices that implement event-based sensors or biophysically realistic networks of spiking neurons. It has been argued that these devices can be used to build event-based systems, for solving real-world applications in real-time, with efficiencies and robustness that cannot be achieved with conventional computing technologies. In order to implement complex event-based neuromorphic systems it is necessary to interface the neuromorphic VLSI sensors and devices among each other, to robotic platforms, and to workstations (e.g. for data-logging and analysis). This apparently simple goal requires painstaking work that spans multiple levels of complexity and disciplines: from the custom layout of microelectronic circuits and asynchronous printed circuit boards, to the development of object oriented classes and methods in software; from electrical engineering and physics for analog/digital circuit design to neuroscience and computer science for neural computation and spike-based learning methods. Within this context, we present a framework we developed to simplify the configuration of multi-chip neuromorphic VLSI systems, and automate the mapping of neural network model parameters to neuromorphic circuit bias values.

An increasing number of research groups are developing custom hybrid analog/digital very large scale integration (VLSI) chips and systems that implement hundreds to thousands of spiking neurons with biophysically realistic dynamics, with the intention of emulating brainlike real-world behavior in hardware and robotic systems rather than simply simulating their performance on general-purpose digital computers. Although the electronic engineering aspects of these emulation systems is proceeding well, progress toward the actual emulation of brainlike tasks is restricted by the lack of suitable high-level configuration methods of the kind that have already been developed over many decades for simulations on general-purpose computers. The key difficulty is that the dynamics of the CMOS electronic analogs are determined by transistor biases that do not map simply to the parameter types and values used in typical abstract mathematical models of neurons and their networks. Here we provide a general method for resolving this difficulty. We describe a parameter mapping technique that permits an automatic configuration of VLSI neural networks so that their electronic emulation conforms to a higher-level neuronal simulation. We show that the neurons configured by our method exhibit spike timing statistics and temporal dynamics that are the same as those observed in the software simulated neurons and, in particular, that the key parameters of recurrent VLSI neural networks (e.g., implementing soft winner-take-all) can be precisely tuned. The proposed method permits a seamless integration between software simulations with hardware emulations and intertranslatability between the parameters of abstract neuronal models and their emulation counterparts. Most important, our method offers a route toward a high-level task configuration language for neuromorphic VLSI systems.

Spike-based learning circuits have been typically used in conjunction with linear integrate-and-flre neurons. As a new class of current-mode conductance-based silicon neurons has been recently developed, it is important to evaluate how the spike-based learning circuits perform, when interfaced to these new types of neuron circuits. Here, we describe a VLSI implementation of a current-mode conductance-based neuron, connected to synaptic circuits with spike-based learning capabilities. The conductance-based silicon neuron has built-in spike-frequency adaptation, refractory period mechanisms, and plasticity eligibility control circuits. The synaptic circuits exhibits realistic dynamics in the post-synaptic currents and comprise local spike-based learning circuits, controlled by the global post-synaptic eligibility circuits. We present experimental results which characterize the conductance-based neuron circuit properties and the spike-based learning circuits connected to it.

This demonstration will show a distributed VLSI neuromorphic system implementing the soft Winner-Take-All (WTA) operation using spiking neurons. It also shows how recurrently connected instances of them can have persistent activity states, which can used for state-dependent computation. The live demonstration of this network will show that the position of a localized stimulus can be tracked and remembered along a trajectory initially encoded in the system. The visitors will experience the real-time, fast state-dependent processing of the sensory input occurring in the network.

An increasing number of research groups develop dedicated hybrid analog/digital very large scale integration (VLSI) devices implementing hundreds of spiking neurons with bio-physically realistic dynamics. However, despite the significant progress in their design, there is still little insight in translating circuitry of neural assemblies into desired (non-trivial) function. In this work, we propose to use neural circuits implementing the soft Winner-Take-All (WTA) function. By showing that recurrently connected instances of them can have persistent activity states, which can be used as a form of working memory, we argue that such circuits can perform state-dependent computation. We demonstrate such a network in a distributed neuromorphic system consisting of two multi-neuron chips implementing soft WTA, stimulated by an event-based vision sensor. The resulting network is able to track and remember the position of a localized stimulus along a trajectory previously encoded in the system.

A non–linear dynamic system is called contracting if initial conditions are for- gotten exponentially fast, so that all trajectories converge to a single trajectory. We use contraction theory to derive an upper bound for the strength of recurrent connections that guarantees contraction for complex neural networks. Specifi- cally, we apply this theory to a special class of recurrent networks, often called Cooperative Competitive Networks (CCNs), which are an abstract representation of the cooperative-competitive connectivity observed in cortex. This specific type of network is believed to play a major role in shaping cortical responses and se- lecting the relevant signal among distractors and noise. In this paper, we analyze contraction of combined CCNs of linear threshold units and verify the results of our analysis in a hybrid analog/digital VLSI CCN comprising spiking neurons and dynamic synapses.

The growing interest in pulse-mode processing by neural networks is encouraging the development of hardware implementations of massively parallel, distributed networks of integrate-and-fire (I&F) neurons. We have developed a reconfigurable multi-chip neuronal system for modeling feature selectivity and applied it to oriented visual stimuli. Our system comprises a temporally differentiating imager and a VLSI competitive network of neurons which use an asynchronous address event representation (AER) for communication. Here we describe the overall system, and present experimental data demonstrating the effect of recurrent connectivity on the pulse-based orientation selectivity

Cooperative competitive networks are believed to play a central role in cortical processing and have been shown to exhibit a wide set of useful computational properties. We propose a VLSI implementation of a spiking cooperative competitive network and show how it can perform context dependent computation both in the mean firing rate domain and in spike timing correlation space. In the mean rate case the network amplifies the activity of neurons belonging to the selected stimulus and suppresses the activity of neurons receiving weaker stimuli. In the event correlation case, the recurrent network amplifies with a higher gain the correlation between neurons which receive highly correlated inputs while leaving the mean firing rate unaltered. We describe the network architecture and present experimental data demonstrating its context dependent computation capabilities.

We present a mixed-mode analog/digital VLSI device comprising an array of leaky integrate-and-fire (I&F) neurons, adaptive synapses with spike-timing dependent plasticity, and an asynchronous event based communication infrastructure that allows the user to (re)configure networks of spiking neurons with arbitrary topologies. The asynchronous communication protocol used by the silicon neurons to transmit spikes (events) off-chip and the silicon synapses to receive spikes from the outside is based on the "address-event representation" (AER). We describe the analog circuits designed to implement the silicon neurons and synapses and present experimental data showing the neuron's response properties and the synapses characteristics, in response to AER input spike trains. Our results indicate that these circuits can be used in massively parallel VLSI networks of I&F neurons to simulate real-time complex spike-based learning algorithms.

Electronic neuromorphic devices with on-chip, on-line learning should be able to modify quickly the synaptic couplings to acquire information about new patterns to be stored (synaptic plasticity) and, at the same time, preserve this information on very long time scales (synaptic stability). Here, we illustrate the electronic implementation of a simple solution to this stability-plasticity problem, recently proposed and studied in various contexts. It is based on the observation that reducing the analog depth of the synapses to the extreme (bistable synapses) does not necessarily disrupt the performance of the device as an associative memory, provided that 1) the number of neurons is large enough; 2) the transitions between stable synaptic states are stochastic; and 3) learning is slow. The drastic reduction of the analog depth of the synaptic variable also makes this solution appealing from the point of view of electronic implementation and offers a simple methodological alternative to the technological solution based on floating gates. We describe the full custom analog very large-scale integration (VLSI) realization of a small network of integrate-and-fire neurons connected by bistable deterministic plastic synapses which can implement the idea of stochastic learning. In the absence of stimuli, the memory is preserved indefinitely. During the stimulation the synapse undergoes quick temporary changes through the activities of the pre- and postsynaptic neurons; those changes stochastically result in a long-term modification of the synaptic efficacy. The intentionally disordered pattern of connectivity allows the system to generate a randomness suited to drive the stochastic selection mechanism. We check by a suitable stimulation protocol that the stochastic synaptic plasticity produces the expected pattern of potentiation and depression in the electronic network.