scholarly journals Brain-inspired global-local learning incorporated with neuromorphic computing

2022 ◽  
Vol 13 (1) ◽  
Author(s):  
Yujie Wu ◽  
Rong Zhao ◽  
Jun Zhu ◽  
Feng Chen ◽  
Mingkun Xu ◽  
...  
Keyword(s):  
Great Promise ◽  
Local Learning ◽  
Global Learning ◽  
Neuronal Dynamics ◽  
Neuromorphic Computing ◽  
Vision Sensors ◽  
Learning Capabilities ◽  
Meta Learning ◽  
Learning Scenarios ◽  
Many Core

AbstractThere are two principle approaches for learning in artificial intelligence: error-driven global learning and neuroscience-oriented local learning. Integrating them into one network may provide complementary learning capabilities for versatile learning scenarios. At the same time, neuromorphic computing holds great promise, but still needs plenty of useful algorithms and algorithm-hardware co-designs to fully exploit its advantages. Here, we present a neuromorphic global-local synergic learning model by introducing a brain-inspired meta-learning paradigm and a differentiable spiking model incorporating neuronal dynamics and synaptic plasticity. It can meta-learn local plasticity and receive top-down supervision information for multiscale learning. We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors. It achieves significantly higher performance than single-learning methods. We further implement the model in the Tianjic neuromorphic platform by exploiting algorithm-hardware co-designs and prove that the model can fully utilize neuromorphic many-core architecture to develop hybrid computation paradigm.

Online self-evolving fuzzy controller with global learning capabilities

2010 ◽  
Vol 1 (4) ◽  
pp. 225-239 ◽  
Author(s):  
Ana Belén Cara ◽  
Héctor Pomares ◽  
Ignacio Rojas ◽  
Zsófia Lendek ◽  
Robert Babuška
Keyword(s):  
Fuzzy Controller ◽  
Global Learning ◽  
Learning Capabilities

scholarly journals Spiking neural networks for computer vision

2018 ◽  
Vol 8 (4) ◽  
pp. 20180007 ◽  
Author(s):  
Michael Hopkins ◽  
Garibaldi Pineda-García ◽  
Petruţ A. Bogdan ◽  
Steve B. Furber
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Network Architecture ◽  
Visual Scene ◽  
Vision Systems ◽  
Biological Vision ◽  
Vision Sensors ◽  
Learning Capabilities ◽  
Spatio Temporal ◽  
Event Based

State-of-the-art computer vision systems use frame-based cameras that sample the visual scene as a series of high-resolution images. These are then processed using convolutional neural networks using neurons with continuous outputs. Biological vision systems use a quite different approach, where the eyes (cameras) sample the visual scene continuously, often with a non-uniform resolution, and generate neural spike events in response to changes in the scene. The resulting spatio-temporal patterns of events are then processed through networks of spiking neurons. Such event-based processing offers advantages in terms of focusing constrained resources on the most salient features of the perceived scene, and those advantages should also accrue to engineered vision systems based upon similar principles. Event-based vision sensors, and event-based processing exemplified by the SpiNNaker (Spiking Neural Network Architecture) machine, can be used to model the biological vision pathway at various levels of detail. Here we use this approach to explore structural synaptic plasticity as a possible mechanism whereby biological vision systems may learn the statistics of their inputs without supervision, pointing the way to engineered vision systems with similar online learning capabilities.

scholarly journals Detection of Falls from Non-Invasive Thermal Vision Sensors Using Convolutional Neural Networks

Proceedings ◽  
2018 ◽  
Vol 2 (19) ◽  
pp. 1236 ◽  
Author(s):  
Javier Quero ◽  
Matthew Burns ◽  
Muhammad Razzaq ◽  
Chris Nugent ◽  
Macarena Espinilla
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Low Cost ◽  
Non Invasive ◽  
Vision Sensors ◽  
Learning Capabilities ◽  
Augmentation Techniques ◽  
Thermal Vision ◽  
The Impact

In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect falls from non-invasive thermal vision sensors. First, we include an agile data collection to label images in order to create a dataset that describes several cases of single and multiple occupancy. These cases include standing inhabitants and target situations with a fallen inhabitant. Second, we provide data augmentation techniques to increase the learning capabilities of the classification and reduce the configuration time. Third, we have defined 3 types of CNN to evaluate the impact that the number of layers and kernel size have on the performance of the methodology. The results show an encouraging performance in single-occupancy contexts, with up to 92 % of accuracy, but a 10 % of reduction in accuracy in multiple-occupancy. The learning capabilities of CNNs have been highlighted due to the complex images obtained from the low-cost device. These images have strong noise as well as uncertain and blurred areas. The results highlight that the CNN based on 3-layers maintains a stable performance, as well as quick learning.

scholarly journals ROA: A Rapid Learning Scheme for In-Situ Memristor Networks

2021 ◽  
Vol 4 ◽  
Author(s):  
Wenli Zhang ◽  
Yaoyuan Wang ◽  
Xinglong Ji ◽  
Yujie Wu ◽  
Rong Zhao
Keyword(s):  
Great Promise ◽  
Uncertain Environments ◽  
Dynamic Learning ◽  
Learning Scheme ◽  
Offline Learning ◽  
Meta Learning ◽  
Potential Applications ◽  
One Step ◽  
On Chip

Memristors show great promise in neuromorphic computing owing to their high-density integration, fast computing and low-energy consumption. However, the non-ideal update of synaptic weight in memristor devices, including nonlinearity, asymmetry and device variation, still poses challenges to the in-situ learning of memristors, thereby limiting their broad applications. Although the existing offline learning schemes can avoid this problem by transferring the weight optimization process into cloud, it is difficult to adapt to unseen tasks and uncertain environments. Here, we propose a bi-level meta-learning scheme that can alleviate the non-ideal update problem, and achieve fast adaptation and high accuracy, named Rapid One-step Adaption (ROA). By introducing a special regularization constraint and a dynamic learning rate strategy for in-situ learning, the ROA method effectively combines offline pre-training and online rapid one-step adaption. Furthermore, we implemented it on memristor-based neural networks to solve few-shot learning tasks, proving its superiority over the pure offline and online schemes under noisy conditions. This method can solve in-situ learning in non-ideal memristor networks, providing potential applications of on-chip neuromorphic learning and edge computing.

Are HOLZ lines kinematic in off-zone-axis orientation?

1993 ◽  
Vol 51 ◽  
pp. 692-693
Author(s):  
J. M. Zuo ◽  
A. L. Weickenmeier ◽  
R. Holmestad ◽  
J. C. H. Spence
Keyword(s):  
Structure Determination ◽  
Standard Procedure ◽  
High Order ◽  
Zone Axis ◽  
Great Promise ◽  
Line Position ◽  
Measured Intensity ◽  
Constant Intensity ◽  
Axis Orientation ◽  
Diffraction Condition

The application of high order reflections in a weak diffraction condition off the zone axis center, including those in high order laue zones (HOLZ), holds great promise for structure determination using convergent beam electron diffraction (CBED). It is believed that in this case the intensities of high order reflections are kinematic or two-beam like. Hence, the measured intensity can be related to the structure factor amplitude. Then the standard procedure of structure determination in crystallography may be used for solving unknown structures. The dynamic effect on HOLZ line position and intensity in a strongly diffracting zone axis is well known. In a weak diffraction condition, the HOLZ line position may be approximated by the kinematic position, however, it is not clear whether this is also true for HOLZ intensities. The HOLZ lines, as they appear in CBED patterns, do show strong intensity variations along the line especially near the crossing of two lines, rather than constant intensity along the Bragg condition as predicted by kinematic or two beam theory.

Sign in / Sign up

Export Citation Format

Share Document