scholarly journals Time-Multiplexed Spiking Convolutional Neural Network Based on VCSELs for Unsupervised Image Classification

2021 ◽  
Vol 11 (4) ◽  
pp. 1383
Author(s):  
Menelaos Skontranis ◽  
George Sarantoglou ◽  
Stavros Deligiannidis ◽  
Adonis Bogris ◽  
Charis Mesaritakis
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Biological Networks ◽  
Spatial Information ◽  
Cavity Surface ◽  
Training Technique ◽  
Retina Ganglion Cell ◽  
Vertical Cavity Surface ◽  
Emitting Lasers

In this work, we present numerical results concerning a multilayer “deep” photonic spiking convolutional neural network, arranged so as to tackle a 2D image classification task. The spiking neurons used are typical two-section quantum-well vertical-cavity surface-emitting lasers that exhibit isomorphic behavior to biological neurons, such as integrate-and-fire excitability and timing encoding. The isomorphism of the proposed scheme to biological networks is extended by replicating the retina ganglion cell for contrast detection in the photonic domain and by utilizing unsupervised spike dependent plasticity as the main training technique. Finally, in this work we also investigate the possibility of exploiting the fast carrier dynamics of lasers so as to time-multiplex spatial information and reduce the number of physical neurons used in the convolutional layers by orders of magnitude. This last feature unlocks new possibilities, where neuron count and processing speed can be interchanged so as to meet the constraints of different applications.

scholarly journals Synergistic 2D/3D Convolutional Neural Network for Hyperspectral Image Classification

2020 ◽  
Vol 12 (12) ◽  
pp. 2033 ◽  
Author(s):  
Xiaofei Yang ◽  
Xiaofeng Zhang ◽  
Yunming Ye ◽  
Raymond Y. K. Lau ◽  
Shijian Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Feature Learning ◽  
Hyperspectral Image Classification ◽  
3 Dimensional ◽  
Recent Success ◽  
Hybrid Module

Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hyperspectral images. On the other hand, few approaches make use of both spectral and spatial information simultaneously, which is critical to accurate hyperspectral image classification. This paper presents a novel Synergistic Convolutional Neural Network (SyCNN) for accurate hyperspectral image classification. The SyCNN consists of a hybrid module that combines 2D and 3D CNNs in feature learning and a data interaction module that fuses spectral and spatial hyperspectral information. Additionally, it introduces a 3D attention mechanism before the fully-connected layer which helps filter out interfering features and information effectively. Extensive experiments over three public benchmarking datasets show that our proposed SyCNNs clearly outperform state-of-the-art techniques that use 2D/3D CNNs.

scholarly journals A 3D-2D Convolutional Neural Network and Transfer Learning for Hyperspectral Image Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Douglas Omwenga Nyabuga ◽  
Jinling Song ◽  
Guohua Liu ◽  
Michael Adjeisah
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Transfer Learning ◽  
Spatial Data ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Experimental Result ◽  
Computational Time ◽  
Hyperspectral Image Classification

As one of the fast evolution of remote sensing and spectral imagery techniques, hyperspectral image (HSI) classification has attracted considerable attention in various fields, including land survey, resource monitoring, and among others. Nonetheless, due to a lack of distinctiveness in the hyperspectral pixels of separate classes, there is a recurrent inseparability obstacle in the primary space. Additionally, an open challenge stems from examining efficient techniques that can speedily classify and interpret the spectral-spatial data bands within a more precise computational time. Hence, in this work, we propose a 3D-2D convolutional neural network and transfer learning model where the early layers of the model exploit 3D convolutions to modeling spectral-spatial information. On top of it are 2D convolutional layers to handle semantic abstraction mainly. Toward simplicity and a highly modularized network for image classification, we leverage the ResNeXt-50 block for our model. Furthermore, improving the separability among classes and balance of the interclass and intraclass criteria, we engaged principal component analysis (PCA) for the best orthogonal vectors for representing information from HSIs before feeding to the network. The experimental result shows that our model can efficiently improve the hyperspectral imagery classification, including an instantaneous representation of the spectral-spatial information. Our model evaluation on five publicly available hyperspectral datasets, Indian Pines (IP), Pavia University Scene (PU), Salinas Scene (SA), Botswana (BS), and Kennedy Space Center (KSC), was performed with a high classification accuracy of 99.85%, 99.98%, 100%, 99.82%, and 99.71%, respectively. Quantitative results demonstrated that it outperformed several state-of-the-arts (SOTA), deep neural network-based approaches, and standard classifiers. Thus, it has provided more insight into hyperspectral image classification.

Recent developments in the area of vertical cavity surface emitting lasers

1999 ◽  
Vol 09 (PR2) ◽  
pp. Pr2-3 ◽  
Author(s):  
J. Jacquet ◽  
P. Salet ◽  
A. Plais ◽  
F. Brillouet ◽  
E. Derouin ◽  
...  
Keyword(s):  
Cavity Surface ◽  
Surface Emitting Lasers ◽  
Recent Developments ◽  
Vertical Cavity Surface ◽  
Emitting Lasers ◽  
Vertical Cavity

Detector-enclosed vertical-cavity surface emitting lasers

1993 ◽  
Vol 29 (5) ◽  
pp. 466 ◽  
Author(s):  
K.D. Choquette ◽  
N. Tabatabaie ◽  
R.E. Leibenguth
Keyword(s):  
Cavity Surface ◽  
Surface Emitting Lasers ◽  
Vertical Cavity Surface ◽  
Emitting Lasers ◽  
Vertical Cavity

Optimised proton implantation step for vertical-cavity surface-emitting lasers

1993 ◽  
Vol 29 (10) ◽  
pp. 918-919 ◽  
Author(s):  
P. Ressel ◽  
H. Strusny ◽  
S. Gramlich ◽  
U. Zeimer ◽  
J. Sebastian ◽  
...  
Keyword(s):  
Cavity Surface ◽  
Surface Emitting Lasers ◽  
Vertical Cavity Surface ◽  
Proton Implantation ◽  
Emitting Lasers ◽  
Vertical Cavity
Sign in / Sign up

Export Citation Format

Share Document