EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor.

Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Hyper-Dimensional Computing (HDC) has shown promising results in enabling efficient and robust cognitive learning. In this study, we exploit HDC as an alternative computational model that mimics important brain functionalities toward high-efficiency and noise-tolerant neuromorphic computing. We present EventHD, an end-to-end learning framework based on HDC for robust, efficient learning from neuromorphic sensors. We first introduce a spatial and temporal encoding scheme to map event-based neuromorphic data into high-dimensional space. Then, we leverage HDC mathematics to support learning and cognitive tasks over encoded data, such as information association and memorization. EventHD also provides a notion of confidence for each prediction, thus enabling self-learning from unlabeled data. We evaluate EventHD efficiency over data collected from Dynamic Vision Sensor (DVS) sensors. Our results indicate that EventHD can provide online learning and cognitive support while operating over raw DVS data without using the costly preprocessing step. In terms of efficiency, EventHD provides 14.2× faster and 19.8× higher energy efficiency than state-of-the-art learning algorithms while improving the computational robustness by 5.9×.

Learning to Recognize Actions From Limited Training Examples Using a Recurrent Spiking Neural Model.

A fundamental challenge in machine learning today is to build a model that can learn from few examples. Here, we describe a reservoir based spiking neural model for learning to recognize actions with a limited number of labeled videos. First, we propose a novel encoding, inspired by how microsaccades influence visual perception, to extract spike information from raw video data while preserving the temporal correlation across different frames. Using this encoding, we show that the reservoir generalizes its rich dynamical activity toward signature action/movements enabling it to learn from few training examples. We evaluate our approach on the UCF-101 dataset. Our experiments demonstrate that our proposed reservoir achieves 81.3/87% Top-1/Top-5 accuracy, respectively, on the 101-class data while requiring just 8 video examples per class for training. Our results establish a new benchmark for action recognition from limited video examples for spiking neural models while yielding competitive accuracy with respect to state-of-the-art non-spiking neural models.

Criticality as a Set-Point for Adaptive Behavior in Neuromorphic Hardware.

Neuromorphic hardware are designed by drawing inspiration from biology to overcome limitations of current computer architectures while forging the development of a new class of autonomous systems that can exhibit adaptive behaviors. Several designs in the recent past are capable of emulating large scale networks but avoid complexity in network dynamics by minimizing the number of dynamic variables that are supported and tunable in hardware. We believe that this is due to the lack of a clear understanding of how to design self-tuning complex systems. It has been widely demonstrated that criticality appears to be the default state of the brain and manifests in the form of spontaneous scale-invariant cascades of neural activity. Experiment, theory and recent models have shown that neuronal networks at criticality demonstrate optimal information transfer, learning and information processing capabilities that affect behavior. In this perspective article, we argue that understanding how large scale neuromorphic electronics can be designed to enable emergent adaptive behavior will require an understanding of how networks emulated by such hardware can self-tune local parameters to maintain criticality as a set-point. We believe that such capability will enable the design of truly scalable intelligent systems using neuromorphic hardware that embrace complexity in network dynamics rather than avoiding it.

Synaptic plasticity enables adaptive self-tuning critical networks.

During rest, the mammalian cortex displays spontaneous neural activity. Spiking of single neurons during rest has been described as irregular and asynchronous. In contrast, recent in vivo and in vitro population measures of spontaneous activity, using the LFP, EEG, MEG or fMRI suggest that the default state of the cortex is critical, manifested by spontaneous, scale-invariant, cascades of activity known as neuronal avalanches. Criticality keeps a network poised for optimal information processing, but this view seems to be difficult to reconcile with apparently irregular single neuron spiking. Here, we simulate a 10,000 neuron, deterministic, plastic network of spiking neurons. We show that a combination of short- and long-term synaptic plasticity enables these networks to exhibit criticality in the face of intrinsic, i.e. self-sustained, asynchronous spiking. Brief external perturbations lead to adaptive, long-term modification of intrinsic network connectivity through long-term excitatory plasticity, whereas long-term inhibitory plasticity enables rapid self-tuning of the network back to a critical state. The critical state is characterized by a branching parameter oscillating around unity, a critical exponent close to -3/2 and a long tail distribution of a self-similarity parameter between 0.5 and 1.

A novel analytical characterization for short-term plasticity parameters in spiking neural networks.

Short-term plasticity (STP) is a phenomenon that widely occurs in the neocortex with implications for learning and memory. Based on a widely used STP model, we develop an analytical characterization of the STP parameter space to determine the nature of each synapse (facilitating, depressing, or both) in a spiking neural network based on presynaptic firing rate and the corresponding STP parameters. We demonstrate consistency with previous work by leveraging the power of our characterization to replicate the functional volumes that are integral for the previous network stabilization results. We then use our characterization to predict the precise transitional point from the facilitating regime to the depressing regime in a simulated synapse, suggesting in vitro experiments to verify the underlying STP model. We conclude the work by integrating our characterization into a framework for finding suitable STP parameters for self-sustaining random, asynchronous activity in a prescribed recurrent spiking neural network. The systematic process resulting from our analytical characterization improves the success rate of finding the requisite parameters for such networks by three orders of magnitude over a random search.

A robust and scalable neuromorphic communication system by combining synaptic time multiplexing and MIMO-OFDM.

This paper describes a novel architecture for enabling robust and efficient neuromorphic communication. The architecture combines two concepts: 1) synaptic time multiplexing (STM) that trades space for speed of processing to create an intragroup communication approach that is firing rate independent and offers more flexibility in connectivity than cross-bar architectures and 2) a wired multiple input multiple output (MIMO) communication with orthogonal frequency division multiplexing (OFDM) techniques to enable a robust and efficient intergroup communication for neuromorphic systems. The MIMO-OFDM concept for the proposed architecture was analyzed by simulating large-scale spiking neural network architecture. Analysis shows that the neuromorphic system with MIMO-OFDM exhibits robust and efficient communication while operating in real time with a high bit rate. Through combining STM with MIMO-OFDM techniques, the resulting system offers a flexible and scalable connectivity as well as a power and area efficient solution for the implementation of very large-scale spiking neural architectures in hardware.

HRLSim: a high performance spiking neural network simulator for GPGPU clusters.

Modeling of large-scale spiking neural models is an important tool in the quest to understand brain function and subsequently create real-world applications. This paper describes a spiking neural network simulator environment called HRL Spiking Simulator (HRLSim). This simulator is suitable for implementation on a cluster of general purpose graphical processing units (GPGPUs). Novel aspects of HRLSim are described and an analysis of its performance is provided for various configurations of the cluster. With the advent of inexpensive GPGPU cards and compute power, HRLSim offers an affordable and scalable tool for design, real-time simulation, and analysis of large-scale spiking neural networks.

Analyzing large-scale spiking neural data with HRLAnalysis(™).

The additional capabilities provided by high-performance neural simulation environments and modern computing hardware has allowed for the modeling of increasingly larger spiking neural networks. This is important for exploring more anatomically detailed networks but the corresponding accumulation in data can make analyzing the results of these simulations difficult. This is further compounded by the fact that many existing analysis packages were not developed with large spiking data sets in mind. Presented here is a software suite developed to not only process the increased amount of spike-train data in a reasonable amount of time, but also provide a user friendly Python interface. We describe the design considerations, implementation and features of the HRLAnalysis(™) suite. In addition, performance benchmarks demonstrating the speedup of this design compared to a published Python implementation are also presented. The result is a high-performance analysis toolkit that is not only usable and readily extensible, but also straightforward to interface with existing Python modules.

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity.

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns-both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity.

A scalable neural chip with synaptic electronics using CMOS integrated memristors.

The design and simulation of a scalable neural chip with synaptic electronics using nanoscale memristors fully integrated with complementary metal-oxide-semiconductor (CMOS) is presented. The circuit consists of integrate-and-fire neurons and synapses with spike-timing dependent plasticity (STDP). The synaptic conductance values can be stored in memristors with eight levels, and the topology of connections between neurons is reconfigurable. The circuit has been designed using a 90 nm CMOS process with via connections to on-chip post-processed memristor arrays. The design has about 16 million CMOS transistors and 73 728 integrated memristors. We provide circuit level simulations of the entire chip performing neuronal and synaptic computations that result in biologically realistic functional behavior.

Using a hybrid neuron in physiologically inspired models of the basal ganglia.

Our current understanding of the basal ganglia (BG) has facilitated the creation of computational models that have contributed novel theories, explored new functional anatomy and demonstrated results complementing physiological experiments. However, the utility of these models extends beyond these applications. Particularly in neuromorphic engineering, where the basal ganglia's role in computation is important for applications such as power efficient autonomous agents and model-based control strategies. The neurons used in existing computational models of the BG, however, are not amenable for many low-power hardware implementations. Motivated by a need for more hardware accessible networks, we replicate four published models of the BG, spanning single neuron and small networks, replacing the more computationally expensive neuron models with an Izhikevich hybrid neuron. This begins with a network modeling action-selection, where the basal activity levels and the ability to appropriately select the most salient input is reproduced. A Parkinson's disease model is then explored under normal conditions, Parkinsonian conditions and during subthalamic nucleus deep brain stimulation (DBS). The resulting network is capable of replicating the loss of thalamic relay capabilities in the Parkinsonian state and its return under DBS. This is also demonstrated using a network capable of action-selection. Finally, a study of correlation transfer under different patterns of Parkinsonian activity is presented. These networks successfully captured the significant results of the originals studies. This not only creates a foundation for neuromorphic hardware implementations but may also support the development of large-scale biophysical models. The former potentially providing a way of improving the efficacy of DBS and the latter allowing for the efficient simulation of larger more comprehensive networks.

Efficiently passing messages in distributed spiking neural network simulation.

Efficiently passing spiking messages in a neural model is an important aspect of high-performance simulation. As the scale of networks has increased so has the size of the computing systems required to simulate them. In addition, the information exchange of these resources has become more of an impediment to performance. In this paper we explore spike message passing using different mechanisms provided by the Message Passing Interface (MPI). A specific implementation, MVAPICH, designed for high-performance clusters with Infiniband hardware is employed. The focus is on providing information about these mechanisms for users of commodity high-performance spiking simulators. In addition, a novel hybrid method for spike exchange was implemented and benchmarked.

Learning and prospective recall of noisy spike pattern episodes.

Spike patterns in vivo are often incomplete or corrupted with noise that makes inputs to neuronal networks appear to vary although they may, in fact, be samples of a single underlying pattern or repeated presentation. Here we present a recurrent spiking neural network (SNN) model that learns noisy pattern sequences through the use of homeostasis and spike-timing dependent plasticity (STDP). We find that the changes in the synaptic weight vector during learning of patterns of random ensembles are approximately orthogonal in a reduced dimension space when the patterns are constructed to minimize overlap in representations. Using this model, representations of sparse patterns maybe associated through co-activated firing and integrated into ensemble representations. While the model is tolerant to noise, prospective activity, and pattern completion differ in their ability to adapt in the presence of noise. One version of the model is able to demonstrate the recently discovered phenomena of preplay and replay reminiscent of hippocampal-like behaviors.

Stable learning of functional maps in self-organizing spiking neural networks with continuous synaptic plasticity.

This study describes a spiking model that self-organizes for stable formation and maintenance of orientation and ocular dominance maps in the visual cortex (V1). This self-organization process simulates three development phases: an early experience-independent phase, a late experience-independent phase and a subsequent refinement phase during which experience acts to shape the map properties. The ocular dominance maps that emerge accommodate the two sets of monocular inputs that arise from the lateral geniculate nucleus (LGN) to layer 4 of V1. The orientation selectivity maps that emerge feature well-developed iso-orientation domains and fractures. During the last two phases of development the orientation preferences at some locations appear to rotate continuously through ±180° along circular paths and referred to as pinwheel-like patterns but without any corresponding point discontinuities in the orientation gradient maps. The formation of these functional maps is driven by balanced excitatory and inhibitory currents that are established via synaptic plasticity based on spike timing for both excitatory and inhibitory synapses. The stability and maintenance of the formed maps with continuous synaptic plasticity is enabled by homeostasis caused by inhibitory plasticity. However, a prolonged exposure to repeated stimuli does alter the formed maps over time due to plasticity. The results from this study suggest that continuous synaptic plasticity in both excitatory neurons and interneurons could play a critical role in the formation, stability, and maintenance of functional maps in the cortex.

A spiking neural model for stable reinforcement of synapses based on multiple distal rewards.

In this letter, a novel critic-like algorithm was developed to extend the synaptic plasticity rule described in Florian (2007) and Izhikevich (2007) in order to solve the problem of learning multiple distal rewards simultaneously. The system is augmented with short-term plasticity (STP) to stabilize the learning dynamics, thereby increasing the system's learning capacity. A theoretical threshold is estimated for the number of distal rewards that this system can learn. The validity of the novel algorithm was verified by computer simulations.

A bio-inspired kinematic controller for obstacle avoidance during reaching tasks with real robots.

This paper describes a redundant robot arm that is capable of learning to reach for targets in space in a self-organized fashion while avoiding obstacles. Self-generated movement commands that activate correlated visual, spatial and motor information are used to learn forward and inverse kinematic control models while moving in obstacle-free space using the Direction-to-Rotation Transform (DIRECT). Unlike prior DIRECT models, the learning process in this work was realized using an online Fuzzy ARTMAP learning algorithm. The DIRECT-based kinematic controller is fault tolerant and can handle a wide range of perturbations such as joint locking and the use of tools despite not having experienced them during learning. The DIRECT model was extended based on a novel reactive obstacle avoidance direction (DIRECT-ROAD) model to enable redundant robots to avoid obstacles in environments with simple obstacle configurations. However, certain configurations of obstacles in the environment prevented the robot from reaching the target with purely reactive obstacle avoidance. To address this complexity, a self-organized process of mental rehearsals of movements was modeled, inspired by human and animal experiments on reaching, to generate plans for movement execution using DIRECT-ROAD in complex environments. These mental rehearsals or plans are self-generated by using the Fuzzy ARTMAP algorithm to retrieve multiple solutions for reaching each target while accounting for all the obstacles in its environment. The key aspects of the proposed novel controller were illustrated first using simple examples. Experiments were then performed on real robot platforms to demonstrate successful obstacle avoidance during reaching tasks in real-world environments.

Neuromorphic adaptive plastic scalable electronics: analog learning systems.

Decades of research to build programmable intelligent machines have demonstrated limited utility in complex, real-world environments. Comparing their performance with biological systems, these machines are less efficient by a factor of 1 million1 billion in complex, real-world environments. The Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) program is a multifaceted Defense Advanced Research Projects Agency (DARPA) project that seeks to break the programmable machine paradigm and define a new path for creating useful, intelligent machines. Since real-world systems exhibit infinite combinatorial complexity, electronic neuromorphic machine technology would be preferable in a host of applications, but useful and practical implementations still do not exist. HRL Laboratories LLC has embarked on addressing these challenges, and, in this article, we provide an overview of our project and progress made thus far.

Programming time-multiplexed reconfigurable hardware using a scalable neuromorphic compiler.

Scalability and connectivity are two key challenges in designing neuromorphic hardware that can match biological levels. In this paper, we describe a neuromorphic system architecture design that addresses an approach to meet these challenges using traditional complementary metal-oxide-semiconductor (CMOS) hardware. A key requirement in realizing such neural architectures in hardware is the ability to automatically configure the hardware to emulate any neural architecture or model. The focus for this paper is to describe the details of such a programmable front-end. This programmable front-end is composed of a neuromorphic compiler and a digital memory, and is designed based on the concept of synaptic time-multiplexing (STM). The neuromorphic compiler automatically translates any given neural architecture to hardware switch states and these states are stored in digital memory to enable desired neural architectures. STM enables our proposed architecture to address scalability and connectivity using traditional CMOS hardware. We describe the details of the proposed design and the programmable front-end, and provide examples to illustrate its capabilities. We also provide perspectives for future extensions and potential applications.

Self-organizing spiking neural model for learning fault-tolerant spatio-motor transformations.

In this paper, we present a spiking neural model that learns spatio-motor transformations. The model is in the form of a multilayered architecture consisting of integrate and fire neurons and synapses that employ spike-timing-dependent plasticity learning rule to enable the learning of such transformations. We developed a simple 2-degree-of-freedom robot-based reaching task which involves the learning of a nonlinear function. Computer simulations demonstrate the capability of such a model for learning the forward and inverse kinematics for such a task and hence to learn spatio-motor transformations. The interesting aspect of the model is its capacity to be tolerant to partial absence of sensory or motor inputs at various stages of learning. We believe that such a model lays the foundation for learning other complex functions and transformations in real-world scenarios.

Energy-efficient neuron, synapse and STDP integrated circuits.

Ultra-low energy biologically-inspired neuron and synapse integrated circuits are presented. The synapse includes a spike timing dependent plasticity (STDP) learning rule circuit. These circuits have been designed, fabricated and tested using a 90 nm CMOS process. Experimental measurements demonstrate proper operation. The neuron and the synapse with STDP circuits have an energy consumption of around 0.4 pJ per spike and synaptic operation respectively.