HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition.

This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.

Event-Based Computation of Motion Flow on a Neuromorphic Analog Neural Platform.

Estimating the speed and direction of moving objects is a crucial component of agents behaving in a dynamic world. Biological organisms perform this task by means of the neural connections originating from their retinal ganglion cells. In artificial systems the optic flow is usually extracted by comparing activity of two or more frames captured with a vision sensor. Designing artificial motion flow detectors which are as fast, robust, and efficient as the ones found in biological systems is however a challenging task. Inspired by the architecture proposed by Barlow and Levick in 1965 to explain the spiking activity of the direction-selective ganglion cells in the rabbit's retina, we introduce an architecture for robust optical flow extraction with an analog neuromorphic multi-chip system. The task is performed by a feed-forward network of analog integrate-and-fire neurons whose inputs are provided by contrast-sensitive photoreceptors. Computation is supported by the precise time of spike emission, and the extraction of the optical flow is based on time lag in the activation of nearby retinal neurons. Mimicking ganglion cells our neuromorphic detectors encode the amplitude and the direction of the apparent visual motion in their output spiking pattern. Hereby we describe the architectural aspects, discuss its latency, scalability, and robustness properties and demonstrate that a network of mismatched delicate analog elements can reliably extract the optical flow from a simple visual scene. This work shows how precise time of spike emission used as a computational basis, biological inspiration, and neuromorphic systems can be used together for solving specific tasks.

STICK: Spike Time Interval Computational Kernel, a Framework for General Purpose Computation Using Neurons, Precise Timing, Delays, and Synchrony.

There has been significant research over the past two decades in developing new platforms for spiking neural computation. Current neural computers are primarily developed to mimic biology. They use neural networks, which can be trained to perform specific tasks to mainly solve pattern recognition problems. These machines can do more than simulate biology; they allow us to rethink our current paradigm of computation. The ultimate goal is to develop brain-inspired general purpose computation architectures that can breach the current bottleneck introduced by the von Neumann architecture. This work proposes a new framework for such a machine. We show that the use of neuron-like units with precise timing representation, synaptic diversity, and temporal delays allows us to set a complete, scalable compact computation framework. The framework provides both linear and nonlinear operations, allowing us to represent and solve any function. We show usability in solving real use cases from simple differential equations to sets of nonlinear differential equations leading to chaotic attractors.

Breaking the millisecond barrier on SpiNNaker: implementing asynchronous event-based plastic models with microsecond resolution.

Spike-based neuromorphic sensors such as retinas and cochleas, change the way in which the world is sampled. Instead of producing data sampled at a constant rate, these sensors output spikes that are asynchronous and event driven. The event-based nature of neuromorphic sensors implies a complete paradigm shift in current perception algorithms toward those that emphasize the importance of precise timing. The spikes produced by these sensors usually have a time resolution in the order of microseconds. This high temporal resolution is a crucial factor in learning tasks. It is also widely used in the field of biological neural networks. Sound localization for instance relies on detecting time lags between the two ears which, in the barn owl, reaches a temporal resolution of 5 µs. Current available neuromorphic computation platforms such as SpiNNaker often limit their users to a time resolution in the order of milliseconds that is not compatible with the asynchronous outputs of neuromorphic sensors. To overcome these limitations and allow for the exploration of new types of neuromorphic computing architectures, we introduce a novel software framework on the SpiNNaker platform. This framework allows for simulations of spiking networks and plasticity mechanisms using a completely asynchronous and event-based scheme running with a microsecond time resolution. Results on two example networks using this new implementation are presented.

An Asynchronous Neuromorphic Event-Driven Visual Part-Based Shape Tracking.

Object tracking is an important step in many artificial vision tasks. The current state-of-the-art implementations remain too computationally demanding for the problem to be solved in real time with high dynamics. This paper presents a novel real-time method for visual part-based tracking of complex objects from the output of an asynchronous event-based camera. This paper extends the pictorial structures model introduced by Fischler and Elschlager 40 years ago and introduces a new formulation of the problem, allowing the dynamic processing of visual input in real time at high temporal resolution using a conventional PC. It relies on the concept of representing an object as a set of basic elements linked by springs. These basic elements consist of simple trackers capable of successfully tracking a target with an ellipse-like shape at several kilohertz on a conventional computer. For each incoming event, the method updates the elastic connections established between the trackers and guarantees a desired geometric structure corresponding to the tracked object in real time. This introduces a high temporal elasticity to adapt to projective deformations of the tracked object in the focal plane. The elastic energy of this virtual mechanical system provides a quality criterion for tracking and can be used to determine whether the measured deformations are caused by the perspective projection of the perceived object or by occlusions. Experiments on real-world data show the robustness of the method in the context of dynamic face tracking.

Spatiotemporal features for asynchronous event-based data.

Bio-inspired asynchronous event-based vision sensors are currently introducing a paradigm shift in visual information processing. These new sensors rely on a stimulus-driven principle of light acquisition similar to biological retinas. They are event-driven and fully asynchronous, thereby reducing redundancy and encoding exact times of input signal changes, leading to a very precise temporal resolution. Approaches for higher-level computer vision often rely on the reliable detection of features in visual frames, but similar definitions of features for the novel dynamic and event-based visual input representation of silicon retinas have so far been lacking. This article addresses the problem of learning and recognizing features for event-based vision sensors, which capture properties of truly spatiotemporal volumes of sparse visual event information. A novel computational architecture for learning and encoding spatiotemporal features is introduced based on a set of predictive recurrent reservoir networks, competing via winner-take-all selection. Features are learned in an unsupervised manner from real-world input recorded with event-based vision sensors. It is shown that the networks in the architecture learn distinct and task-specific dynamic visual features, and can predict their trajectories over time.

Asynchronous Event-Based Multikernel Algorithm for High-Speed Visual Features Tracking.

This paper presents a number of new methods for visual tracking using the output of an event-based asynchronous neuromorphic dynamic vision sensor. It allows the tracking of multiple visual features in real time, achieving an update rate of several hundred kilohertz on a standard desktop PC. The approach has been specially adapted to take advantage of the event-driven properties of these sensors by combining both spatial and temporal correlations of events in an asynchronous iterative framework. Various kernels, such as Gaussian, Gabor, combinations of Gabor functions, and arbitrary user-defined kernels, are used to track features from incoming events. The trackers described in this paper are capable of handling variations in position, scale, and orientation through the use of multiple pools of trackers. This approach avoids the N(2) operations per event associated with conventional kernel-based convolution operations with N × N kernels. The tracking performance was evaluated experimentally for each type of kernel in order to demonstrate the robustness of the proposed solution.

Event-based visual flow.

This paper introduces a new methodology to compute dense visual flow using the precise timings of spikes from an asynchronous event-based retina. Biological retinas, and their artificial counterparts, are totally asynchronous and data-driven and rely on a paradigm of light acquisition radically different from most of the currently used frame-grabber technologies. This paper introduces a framework to estimate visual flow from the local properties of events' spatiotemporal space. We will show that precise visual flow orientation and amplitude can be estimated using a local differential approach on the surface defined by coactive events. Experimental results are presented; they show the method adequacy with high data sparseness and temporal resolution of event-based acquisition that allows the computation of motion flow with microsecond accuracy and at very low computational cost.

A framework for plasticity implementation on the SpiNNaker neural architecture.

Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system.