scholarly journals A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Marc Osswald ◽  
Sio-Hoi Ieng ◽  
Ryad Benosman ◽  
Giacomo Indiveri
Keyword(s):  
Neural Network ◽  
Machine Vision ◽  
Stereo Vision ◽  
Correspondence Problem ◽  
Spiking Neural Network ◽  
Neuromorphic Engineering ◽  
Stereo Correspondence ◽  
Vision Systems ◽  
Neuromorphic Hardware ◽  
Event Based

Abstract Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

scholarly journals Application of deep learning technology for creating intellectual autonomous machines

2020 ◽  
pp. 407-418
Author(s):  
O.S. Bilokon ◽  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Machine Vision ◽  
Network Architecture ◽  
Intellectual Ability ◽  
Input Graph ◽  
Elementary Functions ◽  
Vision Systems ◽  
Gradient Descent Algorithm ◽  
Autonomous Machines

One of the most common tasks that arise in building intelligent machine vision systems for intellectually autonomous machines is the problems of classification and regression. Classification problems are used for the reflexive action of autonomous machines. Prediction tasks can be used to build machine vision systems to provide intelligent autonomous machines with environmental knowledge, which in turn is important for planned predictable movements. Defining a class of task instances is an important procedure for the effective design of deep learning systems. In this context, the possibility of using a multilayered neural network as a regressor to construct elementary functional mappings is explored for further prediction. The study outlines the peculiarities of functioning and configuration of a specialized robotics system, considered in this paper as an intelligent autonomous machine or physical agent, generates a set of data points for elementary functions, analytical modeling and modeling of training systems. Input graph was constructed, neural network architecture was defined, gradient descent algorithm was implemented, and output schedules were finally constructed: learning process, results prediction and comparative graph of predicted results superimposed on the input graph. As a result of the study, an assessment of the machine's intellectual ability to predict was made.

Neuromorphic Memristive Chips: Design and Technology

2021 ◽  
Vol 23 (6) ◽  
pp. 285-294
Author(s):  
N.V. Andreeva ◽  
◽  
V.V. Luchinin ◽  
E.A. Ryndin ◽  
M.G. Anchkov ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Resistive Switching ◽  
Hardware Implementation ◽  
Functional Materials ◽  
Design And Technology ◽  
Spiking Neural Network ◽  
Chip Design ◽  
Neuromorphic Hardware ◽  
Metal Insulator Metal

Memristive neuromorphic chips exploit a prospective class of novel functional materials (memristors) to deploy a new architecture of spiking neural networks for developing basic blocks of brain-like systems. Memristor-based neuromorphic hardware solutions for multi-agent systems are considered as challenges in frontier areas of chip design for fast and energy-efficient computing. As functional materials, metal oxide thin films with resistive switching and memory effects (memristive structures) are recognized as a potential elemental base for new components of neuromorphic engineering, enabling a combination of both data storage and processing in a single unit. A key design issue in this case is a hardware defined functionality of neural networks. The gradient change of resistive properties of memristive elements and its non-volatile memory behavior ensure the possibility of spiking neural network organization with unsupervised learning through hardware implementation of basic synaptic mechanisms, such as Hebb's learning rules including spike — timing dependent plasticity, long-term potentiation and depression. This paper provides an overview of scientific researches carrying out at Saint Petersburg Electrotechnical University "LETI" since 2014 in the field of novel electronic components for neuromorphic hardware solutions of brain-like chip design. Among the most promising concepts developed by ETU "LETI" are: the design of metal-insulator-metal structures exhibiting multilevel resistive switching (gradient tuning of resistive properties and bipolar resistive switching are combined together in a sin¬gle memristive element) for further use as artificial synaptic devices in neuromorphic chips; computing schemes for spatio-temporal pattern recognition based on spiking neural network architecture implementation; breadboard models of analogue circuits of hardware implementation of neuromorphic blocks for brain-like system developing.

Attention in Stereo Vision

2012 ◽  
pp. 65-88 ◽  
Author(s):  
Neil D. B. Bruce ◽  
John K. Tsotsos
Keyword(s):  
Computational Modeling ◽  
Stereo Vision ◽  
Binocular Rivalry ◽  
Computational Models ◽  
Research Effort ◽  
Correspondence Problem ◽  
Stereo Correspondence ◽  
Considerable Research ◽  
The Subject

The stereo correspondence problem is a topic that has been the subject of considerable research effort. What has not yet been considered is an analogue of stereo correspondence in the domain of attention. In this chapter, the authors bring this problem to light, revealing important implications for computational models of attention, and in particular, how these implications constrain the problem of computational modeling of attention. A model is described which addresses attention in the stereo domain, and it is revealed that a variety of behaviors observed in binocular rivalry experiments are consistent with the model’s behavior. Finally, the authors consider how constraints imposed by stereo vision may suggest analogous constraints in other non-stereo feature domains with significant consequence to computational models of attention.

scholarly journals Real-time cortical simulation on neuromorphic hardware

2019 ◽  
Vol 378 (2164) ◽  
pp. 20190160 ◽  
Author(s):  
Oliver Rhodes ◽  
Luca Peres ◽  
Andrew G. D. Rowley ◽  
Andrew Gait ◽  
Luis A. Plana ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Large Scale ◽  
Spiking Neural Network ◽  
Real Time Processing ◽  
Real Time Simulation ◽  
Statistical Measures ◽  
Time Simulation ◽  
Neuromorphic Hardware ◽  
Cortical Microcircuit

Real-time simulation of a large-scale biologically representative spiking neural network is presented, through the use of a heterogeneous parallelization scheme and SpiNNaker neuromorphic hardware. A published cortical microcircuit model is used as a benchmark test case, representing ≈1 mm 2 of early sensory cortex, containing 77 k neurons and 0.3 billion synapses. This is the first hard real-time simulation of this model, with 10 s of biological simulation time executed in 10 s wall-clock time. This surpasses best-published efforts on HPC neural simulators (3 × slowdown) and GPUs running optimized spiking neural network (SNN) libraries (2 × slowdown). Furthermore, the presented approach indicates that real-time processing can be maintained with increasing SNN size, breaking the communication barrier incurred by traditional computing machinery. Model results are compared to an established HPC simulator baseline to verify simulation correctness, comparing well across a range of statistical measures. Energy to solution and energy per synaptic event are also reported, demonstrating that the relatively low-tech SpiNNaker processors achieve a 10 × reduction in energy relative to modern HPC systems, and comparable energy consumption to modern GPUs. Finally, system robustness is demonstrated through multiple 12 h simulations of the cortical microcircuit, each simulating 12 h of biological time, and demonstrating the potential of neuromorphic hardware as a neuroscience research tool for studying complex spiking neural networks over extended time periods. This article is part of the theme issue ‘Harmonizing energy-autonomous computing and intelligence’.

Sign in / Sign up

Export Citation Format

Share Document