Data Pinning and Back Propagation Memory Optimization for Deep Learning on GPU

2018 ◽  
Author(s):  
Cing-Fu Jhu ◽  
Pangfeng Liu ◽  
Jan-Jan Wu
Keyword(s):  
Deep Learning ◽  
Back Propagation ◽  
Memory Optimization

An Anatomy of a Hybrid Color Descriptor with a Neural Network Model to Enhance the Retrieval Accuracy of an Image Retrieval System

2019 ◽  
Vol 13 ◽  
Author(s):  
Shikha Bhardwaj ◽  
Gitanjali Pandove ◽  
Pawan Kumar Dahiya
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Retrieval ◽  
Hybrid System ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Retrieval Accuracy ◽  
Color Descriptor ◽  
Benchmark Datasets ◽  
Color Moment

Background: In order to retrieve a particular image from vast repository of images, an efficient system is required and such an eminent system is well-known by the name Content-based image retrieval (CBIR) system. Color is indeed an important attribute of an image and the proposed system consist of a hybrid color descriptor which is used for color feature extraction. Deep learning, has gained a prominent importance in the current era. So, the performance of this fusion based color descriptor is also analyzed in the presence of Deep learning classifiers. Method: This paper describes a comparative experimental analysis on various color descriptors and the best two are chosen to form an efficient color based hybrid system denoted as combined color moment-color autocorrelogram (Co-CMCAC). Then, to increase the retrieval accuracy of the hybrid system, a Cascade forward back propagation neural network (CFBPNN) is used. The classification accuracy obtained by using CFBPNN is also compared to Patternnet neural network. Results: The results of the hybrid color descriptor depict that the proposed system has superior results of the order of 95.4%, 88.2%, 84.4% and 96.05% on Corel-1K, Corel-5K, Corel-10K and Oxford flower benchmark datasets respectively as compared to many state-of-the-art related techniques. Conclusion: This paper depict an experimental and analytical analysis on different color feature descriptors namely, Color moment (CM), Color auto-correlogram (CAC), Color histogram (CH), Color coherence vector (CCV) and Dominant color descriptor (DCD). The proposed hybrid color descriptor (Co-CMCAC) is utilized for the withdrawal of color features with Cascade forward back propagation neural network (CFBPNN) is used as a classifier on four benchmark datasets namely Corel-1K, Corel-5K and Corel-10K and Oxford flower.

scholarly journals High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

2021 ◽  
Vol 13 (12) ◽  
pp. 2326
Author(s):  
Xiaoyong Li ◽  
Xueru Bai ◽  
Feng Zhou
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Phase Error ◽  
Random Phase ◽  
Back Propagation ◽  
Estimation Method ◽  
Data Driven ◽  
Reconstruction Performance ◽  
Imaging Results ◽  
Isar Imaging

A deep-learning architecture, dubbed as the 2D-ADMM-Net (2D-ADN), is proposed in this article. It provides effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging under scenarios of low SNRs and incomplete data, by combining model-based sparse reconstruction and data-driven deep learning. Firstly, mapping from ISAR images to their corresponding echoes in the wavenumber domain is derived. Then, a 2D alternating direction method of multipliers (ADMM) is unrolled and generalized to a deep network, where all adjustable parameters in the reconstruction layers, nonlinear transform layers, and multiplier update layers are learned by an end-to-end training through back-propagation. Since the optimal parameters of each layer are learned separately, 2D-ADN exhibits more representation flexibility and preferable reconstruction performance than model-driven methods. Simultaneously, it is able to better facilitate ISAR imaging with limited training samples than data-driven methods owing to its simple structure and small number of adjustable parameters. Additionally, benefiting from the good performance of 2D-ADN, a random phase error estimation method is proposed, through which well-focused imaging can be acquired. It is demonstrated by experiments that although trained by only a few simulated images, the 2D-ADN shows good adaptability to measured data and favorable imaging results with a clear background can be obtained in a short time.

An Improved Residual Network for Electricity Power Meter Error Estimation

2019 ◽  
Vol 33 (08) ◽  
pp. 1959024
Author(s):  
Zichao Kou ◽  
Yanjun Fang
Keyword(s):  
Deep Learning ◽  
Error Estimation ◽  
Back Propagation ◽  
Electrical Energy ◽  
Residual Network ◽  
Propagation Process ◽  
Power Meter ◽  
Energy Metering ◽  
Electricity Power ◽  
Comparable Model

The lack of research on the metering characteristics of electricity power meters under complex conditions is a major obstacle to the on-site verification of electrical energy metering equipment. Establishing a predictive model for electricity power meter errors offers an effective way of dealing with this issue. Deep learning has been proven to have the capacity to reduce end-to-end dimensionality and improve recognition. Through the analysis of the back propagation process in residual networks, an improved residual network is set out in this paper. While preserving the advantages of residual network gradient propagation, it adds an adjustable shortcut and designs a convex [Formula: see text]-parameter strategy that can be improved according to different processing objects. Experimental results show that the predicted errors produced by the proposed technique are significantly lower than in a comparable model. At the same time, the improved residual network does not increase the network’s complexity.

scholarly journals Face Recognition Model Using Back Propagation

2018 ◽  
Vol 7 (3.34) ◽  
pp. 237
Author(s):  
R Aswini Priyanka ◽  
C Ashwitha ◽  
R Arun Chakravarthi ◽  
R Prakash
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Face Recognition ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Face Identification ◽  
Identification System ◽  
Scientific World ◽  
The Face ◽  
Deep Learning Neural Network

In scientific world, Face recognition becomes an important research topic. The face identification system is an application capable of verifying a human face from a live videos or digital images. One of the best methods is to compare the particular facial attributes of a person with the images and its database. It is widely used in biometrics and security systems. Back in old days, face identification was a challenging concept. Because of the variations in viewpoint and facial expression, the deep learning neural network came into the technology stack it’s been very easy to detect and recognize the faces. The efficiency has increased dramatically. In this paper, ORL database is about the ten images of forty people helps to evaluate our methodology. We use the concept of Back Propagation Neural Network (BPNN) in deep learning model is to recognize the faces and increase the efficiency of the model compared to previously existing face recognition models.   

Predictive deep learning models for environmental properties: the direct calculation of octanol–water partition coefficients from molecular graphs

2019 ◽  
Vol 21 (16) ◽  
pp. 4555-4565 ◽  
Author(s):  
Zihao Wang ◽  
Yang Su ◽  
Weifeng Shen ◽  
Saimeng Jin ◽  
James H. Clark ◽  
...  
Keyword(s):  
Deep Learning ◽  
Partition Coefficients ◽  
Back Propagation ◽  
Direct Calculation ◽  
Back Propagation Neural Network ◽  
Learning Approach ◽  
Learning Models ◽  
Water Partition Coefficient ◽  
Environmental Properties ◽  
Lstm Network

A deep learning approach coupling the Tree-LSTM network and back-propagation neural network for predicting the octanol–water partition coefficient.

scholarly journals Assessment of Accuracy Enhancement of Back Propagation Algorithm by Training the Model using Deep Learning

2017 ◽  
Vol 10 (2) ◽  
pp. 298-304 ◽  
Author(s):  
Baby Kahkeshan ◽  
Syed Hassan
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Back Propagation ◽  
Back Propagation Algorithm ◽  
Accuracy Enhancement ◽  
Propagation Algorithm

Deep learning is a branch of machine learning which is recently gaining a lot of attention due to its efficiency in solving a number of AI problems. The aim of this research is to assess the accuracy enhancement by using deep learning in back propagation algorithm. For this purpose, two techniques has been used. In the first technique, simple back propagation algorithm is used and the designed model is tested for accuracy. In the second technique, the model is first trained using deep learning via deep belief nets to make it learn and improve its parameters values and then back propagation is used over it. The advantage of softmax function is used in both the methods. Both the methods have been tested over images of handwritten digits and accuracy is then calculated. It has been observed that there is a significant increase in the accuracy of the model if we apply deep learning for training purpose.

Sign in / Sign up

Export Citation Format

Share Document