scholarly journals ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Yihan Lin ◽  
Wei Ding ◽  
Shaohua Qiang ◽  
Lei Deng ◽  
Guoqi Li
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Speed ◽  
Large Scale ◽  
Spiking Neural Networks ◽  
Image Motion ◽  
Network Algorithms ◽  
Event Stream ◽  
Discrete Gradient ◽  
Neuromorphic Vision

With event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neuromorphic cameras like dynamic vision sensors (DVS). In this work, we propose a fast and effective algorithm termed Omnidirectional Discrete Gradient (ODG) to convert the popular computer vision dataset ILSVRC2012 into its event-stream (ES) version, generating about 1,300,000 frame-based images into ES-samples in 1,000 categories. In this way, we propose an ES-dataset called ES-ImageNet, which is dozens of times larger than other neuromorphic classification datasets at present and completely generated by the software. The ODG algorithm implements image motion to generate local value changes with discrete gradient information in different directions, providing a low-cost and high-speed method for converting frame-based images into event streams, along with Edge-Integral to reconstruct the high-quality images from event streams. Furthermore, we analyze the statistics of ES-ImageNet in multiple ways, and a performance benchmark of the dataset is also provided using both famous deep neural network algorithms and spiking neural network algorithms. We believe that this work shall provide a new large-scale benchmark dataset for SNNs and neuromorphic vision.

scholarly journals Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

Photonics ◽  
2021 ◽  
Vol 8 (9) ◽  
pp. 363
Author(s):  
Qi Zhang ◽  
Zhuangzhuang Xing ◽  
Duan Huang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Integrated Circuits ◽  
Energy Efficient ◽  
High Speed ◽  
Large Scale ◽  
Matrix Operation ◽  
Optical Neural Networks ◽  
Optical Neural Network ◽  
Random Initialization

We demonstrate a pruned high-speed and energy-efficient optical backpropagation (BP) neural network. The micro-ring resonator (MRR) banks, as the core of the weight matrix operation, are used for large-scale weighted summation. We find that tuning a pruned MRR weight banks model gives an equivalent performance in training with the model of random initialization. Results show that the overall accuracy of the optical neural network on the MNIST dataset is 93.49% after pruning six-layer MRR weight banks on the condition of low insertion loss. This work is scalable to much more complex networks, such as convolutional neural networks and recurrent neural networks, and provides a potential guide for truly large-scale optical neural networks.

A Developmental Method for Evolving Large-Scale Spiking Neural Networks

2012 ◽  
Vol 35 (12) ◽  
pp. 2633 ◽  
Author(s):  
Xiang-Hong LIN ◽  
Tian-Wen ZHANG ◽  
Gui-Cang ZHANG
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Spiking Neural Networks

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Dynamic statistical evaluation of safety emergency management in coal enterprises based on neural network algorithms

2020 ◽  
Vol 39 (4) ◽  
pp. 5521-5534
Author(s):  
Ying Liu ◽  
Zhongqi Fan ◽  
Hongliang Qi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Emergency Management ◽  
Coal Mine ◽  
Evaluation System ◽  
Statistical Evaluation ◽  
Specific Situation ◽  
Network Algorithms ◽  
Management Capability ◽  
Coal Enterprises

By establishing the evaluation system of emergency management capability for coal mine enterprises, we can identify the problems and shortcomings in coal mine emergency management, improve and improve its emergency management capability for coal mine emergencies. In this paper, the authors analyze the dynamic statistical evaluation of safety emergency management in coal enterprises based on neural network algorithms. Neural networks can form any form of topological structure through neurons, so they can directly simulate fuzzy reasoning in structure, that is to say, the equivalent structure of neural networks and fuzzy systems can be formed. This paper constructs the index system based on accident causes, and verifies the scientific rationality of the system. On this basis, according to the specific situation of coal mine emergency management, we design the evaluation criteria of coal mine emergency management capability evaluation index. Because coal mine accidents have the characteristics of complexity, variability and sudden dynamic, it is necessary to adjust and improve the accidents dynamically at any time. The model combines qualitative and quantitative indicators, and can make an overall evaluation of coal mine emergency management capability. It has the characteristics of clear results and strong fitting of simulation results.

scholarly journals Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2852
Author(s):  
Parvathaneni Naga Srinivasu ◽  
Jalluri Gnana SivaSai ◽  
Muhammad Fazal Ijaz ◽  
Akash Kumar Bhoi ◽  
Wonjoon Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Skin Disease ◽  
Network Architecture ◽  
Large Scale ◽  
Short Term Memory ◽  
Convolutional Networks ◽  
Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

scholarly journals Biological modelling of a computational spiking neural network with neuronal avalanches

2017 ◽  
Vol 375 (2096) ◽  
pp. 20160286 ◽  
Author(s):  
Xiumin Li ◽  
Qing Chen ◽  
Fangzheng Xue
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Critical State ◽  
Spike Timing ◽  
Spiking Neural Networks ◽  
Mathematical Methods ◽  
Computational Accuracy ◽  
Active Neuron ◽  
Computational Performance ◽  
Neuronal Avalanches

In recent years, an increasing number of studies have demonstrated that networks in the brain can self-organize into a critical state where dynamics exhibit a mixture of ordered and disordered patterns. This critical branching phenomenon is termed neuronal avalanches. It has been hypothesized that the homeostatic level balanced between stability and plasticity of this critical state may be the optimal state for performing diverse neural computational tasks. However, the critical region for high performance is narrow and sensitive for spiking neural networks (SNNs). In this paper, we investigated the role of the critical state in neural computations based on liquid-state machines, a biologically plausible computational neural network model for real-time computing. The computational performance of an SNN when operating at the critical state and, in particular, with spike-timing-dependent plasticity for updating synaptic weights is investigated. The network is found to show the best computational performance when it is subjected to critical dynamic states. Moreover, the active-neuron-dominant structure refined from synaptic learning can remarkably enhance the robustness of the critical state and further improve computational accuracy. These results may have important implications in the modelling of spiking neural networks with optimal computational performance. This article is part of the themed issue ‘Mathematical methods in medicine: neuroscience, cardiology and pathology’.

scholarly journals Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Changming Wu ◽  
Heshan Yu ◽  
Seokhyeong Lee ◽  
Ruoming Peng ◽  
Ichiro Takeuchi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Phase Change ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Phase Change Materials ◽  
Refractive Index Change ◽  
Optical Computing ◽  
Machine Learning Algorithms ◽  
Matrix Vector Multiplication

AbstractNeuromorphic photonics has recently emerged as a promising hardware accelerator, with significant potential speed and energy advantages over digital electronics for machine learning algorithms, such as neural networks of various types. Integrated photonic networks are particularly powerful in performing analog computing of matrix-vector multiplication (MVM) as they afford unparalleled speed and bandwidth density for data transmission. Incorporating nonvolatile phase-change materials in integrated photonic devices enables indispensable programming and in-memory computing capabilities for on-chip optical computing. Here, we demonstrate a multimode photonic computing core consisting of an array of programable mode converters based on on-waveguide metasurfaces made of phase-change materials. The programmable converters utilize the refractive index change of the phase-change material Ge2Sb2Te5 during phase transition to control the waveguide spatial modes with a very high precision of up to 64 levels in modal contrast. This contrast is used to represent the matrix elements, with 6-bit resolution and both positive and negative values, to perform MVM computation in neural network algorithms. We demonstrate a prototypical optical convolutional neural network that can perform image processing and recognition tasks with high accuracy. With a broad operation bandwidth and a compact device footprint, the demonstrated multimode photonic core is promising toward large-scale photonic neural networks with ultrahigh computation throughputs.

A fully automated method of human identification based on dental panoramic radiographs using a convolutional neural network

2021 ◽  
Author(s):  
Young Hyun Kim ◽  
Eun-Gyu Ha ◽  
Kug Jin Jeon ◽  
Chena Lee ◽  
Sang-Sun Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Speed ◽  
Large Scale ◽  
Oral Surgery ◽  
Human Identification ◽  
Running Time ◽  
Automated Method ◽  
Image Characteristics ◽  
Proposed Model

Objectives: This study aimed to develop a fully automated human identification method based on a convolutional neural network (CNN) with a large-scale dental panoramic radiograph (DPR) dataset. Methods: In total, 2,760 DPRs from 746 subjects who had 2 to 17 DPRs with various changes in image characteristics due to various dental treatments (tooth extraction, oral surgery, prosthetics, orthodontics, or tooth development) were collected. The test dataset included the latest DPR of each subject (746 images) and the other DPRs (2,014 images) were used for model training. A modified VGG16 model with two fully connected layers was applied for human identification. The proposed model was evaluated with rank-1, –3, and −5 accuracies, running time, and gradient-weighted class activation mapping (Grad-CAM)–applied images. Results: This model had rank-1,–3, and −5 accuracies of 82.84%, 89.14%, and 92.23%, respectively. All rank-1 accuracy values of the proposed model were above 80% regardless of changes in image characteristics. The average running time to train the proposed model was 60.9 sec per epoch, and the prediction time for 746 test DPRs was short (3.2 sec/image). The Grad-CAM technique verified that the model automatically identified humans by focusing on identifiable dental information. Conclusion: The proposed model showed good performance in fully automatic human identification despite differing image characteristics of DPRs acquired from the same patients. Our model is expected to assist in the fast and accurate identification by experts by comparing large amounts of images and proposing identification candidates at high speed.

scholarly journals Application of the neural network computing technology for calculating the interval-index characteristics of a minimally redundant modular code

2019 ◽  
Vol 62 (6) ◽  
pp. 652-660
Author(s):  
A. F. Chernyavsky ◽  
A. A. Kolyada ◽  
S. Yu. Protasenya
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Speed ◽  
Theoretical Estimate ◽  
Structural Complexity ◽  
Fold Increase ◽  
Number System ◽  
Parallel Structure ◽  
Network Computing ◽  
Time Expenditures

The article is devoted to the problem of creation of high-speed neural networks (NN) for calculation of interval-index characteristics of a minimally redundant modular code. The functional base of the proposed solution is an advanced class of neural networks of a final ring. These neural networks perform position-modular code transformations of scalable numbers using a modified reduction technology. A developed neural network has a uniform parallel structure, easy to implement and requires the time expenditures of the order (3[log2b]+ [log2k]+6tsum  close to the lower theoretical estimate. Here b and k is the average bit capacity and the number of modules respectively; t sum is the duration of the two-place operation of adding integers. The refusal from a normalization of the numbers of the modular code leads to a reduction of the required set of NN of the finite ring on the (k – 1) component. At the same time, the abnormal configuration of minimally redundant modular coding requires an average k-fold increase in the interval index module (relative to the rest of the bases of the modular number system). It leads to an adequate increase in hardware expenses on this module. Besides, the transition from normalized to unregulated coding reduces the level of homogeneity of the structure of the NN for calculating intervalindex characteristics. The possibility of reducing the structural complexity of the proposed NN by using abnormal intervalindex characteristics is investigated.

scholarly journals Comparison of the efficiency of neural network algorithms in recognition and classification problems

2020 ◽  
Vol 224 ◽  
pp. 01025
Author(s):  
Alexey Beskopylny ◽  
Alexandr Lyapin ◽  
Nikita Beskopylny ◽  
Elena Kadomtseva
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computation Time ◽  
Classification Problems ◽  
Handwritten Digit Recognition ◽  
Network Algorithms ◽  
Digit Recognition ◽  
Labour Intensity ◽  
Handwritten Digit ◽  
Accuracy Of Results

The article is devoted to the problem of comparing the effectiveness of feedforward (FF) and convolutional neural networks (CNN) algorithms in the problems of handwritten digit recognition and classification. In recent years, the attention of many researchers to the FF and CNN algorithms has given rise to many hybrid models focused on solving specific problems. At the same time, the efficiency of each algorithm in terms of accuracy and labour intensity remains unclear. It is shown that in classical problems, FFs can have advantages over CNN in terms of labour intensity with the same accuracy of results. Using the handwritten digits data from the MNIST database as an example, it is shown that FF algorithms provide greater accuracy and require less computation time than CNN.

Sign in / Sign up

Export Citation Format

Share Document