scholarly journals Inferring low-dimensional microstructure representations using convolutional neural networks

2017 ◽  
Vol 96 (5) ◽  
Author(s):  
Nicholas Lubbers ◽  
Turab Lookman ◽  
Kipton Barros
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Low Dimensional

scholarly journals Inferring the Disease-Associated miRNAs Based on Network Representation Learning and Convolutional Neural Networks

2019 ◽  
Vol 20 (15) ◽  
pp. 3648 ◽  
Author(s):  
Xuan ◽  
Sun ◽  
Wang ◽  
Zhang ◽  
Pan
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Prediction Models ◽  
Prediction Method ◽  
Feature Space ◽  
Representation Learning ◽  
Superior Performance ◽  
Network Representation ◽  
Disease Associations ◽  
Low Dimensional

Identification of disease-associated miRNAs (disease miRNAs) are critical for understanding etiology and pathogenesis. Most previous methods focus on integrating similarities and associating information contained in heterogeneous miRNA-disease networks. However, these methods establish only shallow prediction models that fail to capture complex relationships among miRNA similarities, disease similarities, and miRNA-disease associations. We propose a prediction method on the basis of network representation learning and convolutional neural networks to predict disease miRNAs, called CNNMDA. CNNMDA deeply integrates the similarity information of miRNAs and diseases, miRNA-disease associations, and representations of miRNAs and diseases in low-dimensional feature space. The new framework based on deep learning was built to learn the original and global representation of a miRNA-disease pair. First, diverse biological premises about miRNAs and diseases were combined to construct the embedding layer in the left part of the framework, from a biological perspective. Second, the various connection edges in the miRNA-disease network, such as similarity and association connections, were dependent on each other. Therefore, it was necessary to learn the low-dimensional representations of the miRNA and disease nodes based on the entire network. The right part of the framework learnt the low-dimensional representation of each miRNA and disease node based on non-negative matrix factorization, and these representations were used to establish the corresponding embedding layer. Finally, the left and right embedding layers went through convolutional modules to deeply learn the complex and non-linear relationships among the similarities and associations between miRNAs and diseases. Experimental results based on cross validation indicated that CNNMDA yields superior performance compared to several state-of-the-art methods. Furthermore, case studies on lung, breast, and pancreatic neoplasms demonstrated the powerful ability of CNNMDA to discover potential disease miRNAs.

scholarly journals Combining Learnable Low-dimensional Binary Filter Bases for Compressing Convolutional Neural Networks

2021 ◽  
Author(s):  
Weichao Lan ◽  
Yiu-ming Cheung ◽  
Liang Lan
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Real Life ◽  
Embedded Devices ◽  
Compression Performance ◽  
Benchmark Datasets ◽  
Significant Performance ◽  
Low Dimensional ◽  
Convolution Filters ◽  
Binary Filter

Existing convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks, but a large number of parameters in convolutional layers requires huge storage and computation resources which makes it difficult to deploy CNNs on memory-constraint embedded devices. In this paper, we propose a novel compression method that generates the convolution filters in each layer by combining a set of learnable low-dimensional binary filter bases. The proposed method designs more compact convolution filters by stacking the linear combinations of these filter bases. Because of binary filters, the compact filters can be represented using less number of bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficient through L1-ball projection when conducting linear combination to avoid overfitting. In addition, we analyze the compression performance of the proposed method in detail. Evaluations on four benchmark datasets under VGG-16 and ResNet-18 structures show that the proposed method can achieve a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.

scholarly journals Combining Learnable Low-dimensional Binary Filter Bases for Compressing Convolutional Neural Networks

2021 ◽  
Author(s):  
Weichao Lan ◽  
Yiu-ming Cheung ◽  
Liang Lan
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Real Life ◽  
Embedded Devices ◽  
Compression Performance ◽  
Benchmark Datasets ◽  
Significant Performance ◽  
Low Dimensional ◽  
Convolution Filters ◽  
Binary Filter

Existing convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks, but a large number of parameters in convolutional layers requires huge storage and computation resources which makes it difficult to deploy CNNs on memory-constraint embedded devices. In this paper, we propose a novel compression method that generates the convolution filters in each layer by combining a set of learnable low-dimensional binary filter bases. The proposed method designs more compact convolution filters by stacking the linear combinations of these filter bases. Because of binary filters, the compact filters can be represented using less number of bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficient through L1-ball projection when conducting linear combination to avoid overfitting. In addition, we analyze the compression performance of the proposed method in detail. Evaluations on four benchmark datasets under VGG-16 and ResNet-18 structures show that the proposed method can achieve a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.

The application of mixed-level model in convolutional neural networks for cashmere and wool identification

2018 ◽  
Vol 30 (5) ◽  
pp. 710-725 ◽  
Author(s):  
Fei Wang ◽  
Xiangyu Jin
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Design Methodology ◽  
Identification Task ◽  
Classification Result ◽  
Content Type ◽  
Level Model ◽  
Low Dimensional ◽  
Object Level

Purpose The purpose of this paper is to use convolutional neural networks in order to solve the problem of the difficulty in the classification of cashmere and wool. To do the research, it proposes a low-dimensional strategy of using part-level features to enhance object-level features. The study aims to use computer version method to find out the most effective and robust method to manage the difficult task of cashmere and wool identification. Design/methodology/approach The authors try to get a coarse classification result and the initial weights of the model in the first step. The authors use the results of the first step and a Fast-RCNN method to extract part-level features in step 2. Finally, the authors mix the part-level features to enhance object-level features and classify the cashmere and wool images. Findings The paper finds that not only the texture is the key element of the cashmere and wool identification but also the image colors. Originality/value Most importantly, the paper finds that the part-level features can enhance object-level features in the fiber identification task. However, it does not work in contrast, and the strategy can be used in the similar fibers identifications.

scholarly journals Deep Convolutional Recurrent Autoencoders for Flow Field Prediction

2020 ◽  
Author(s):  
Sandeep R. Bukka ◽  
Allan Ross Magee ◽  
Rajeev K. Jaiman
Keyword(s):  
Neural Networks ◽  
Model Reduction ◽  
Convolutional Neural Networks ◽  
Nonlinear Dynamical System ◽  
Data Driven ◽  
Model Framework ◽  
Flow Past ◽  
End To End ◽  
Low Dimensional ◽  
Low Dimensional Features

Abstract In this paper, an end-to-end nonlinear model reduction methodology is presented based on the convolutional recurrent autoencoder networks. The methodology is developed in the context of overall data-driven reduced order model framework proposed in the paper. The basic idea behind the methodology is to obtain the low dimensional representations via convolutional neural networks and evolve these low dimensional features via recurrent neural networks in time domain. The high dimensional representations are constructed from the evolved low dimensional features via transpose convolutional neural networks. With an unsupervised training strategy, the model serves as an end to end tool which can evolve the flow state of the nonlinear dynamical system. The convolutional recurrent autoencoder network model is applied on the problem of flow past bluff bodies for the first time. To demonstrate the effectiveness of the methodology, two canonical problems namely the flow past plain cylinder and the flow past side-by-side cylinders are explored in this paper. Pressure and velocity fields of the unsteady flow are predicted in future via the convolutional recurrent autoencoder model. The performance of the model is satisfactory for both the problems. Specifically, the multiscale nature and the gap flow dynamics of the side-by-side cylinders are captured by the proposed data-driven model reduction methodology. The error metrics, the normalized squared error and the normalized reconstruction error are considered for the assessment of the data-driven framework.

Sign in / Sign up

Export Citation Format

Share Document