scholarly journals Dynamically Optimizing Network Structure Based on Synaptic Pruning in the Brain

2021 ◽  
Vol 15 ◽  
Author(s):  
Feifei Zhao ◽  
Yi Zeng
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Network Performance ◽  
Computational Cost ◽  
Deep Convolutional Neural Networks ◽  
Learning Speed ◽  
Proposed Model ◽  
The Cost ◽  
Fully Connected ◽  
Synaptic Pruning

Most neural networks need to predefine the network architecture empirically, which may cause over-fitting or under-fitting. Besides, a large number of parameters in a fully connected network leads to the prohibitively expensive computational cost and storage overhead, which makes the model hard to be deployed on mobile devices. Dynamically optimizing the network architecture by pruning unused synapses is a promising technique for solving this problem. Most existing pruning methods focus on reducing the redundancy of deep convolutional neural networks by pruning unimportant filters or weights, at the cost of accuracy drop. In this paper, we propose an effective brain-inspired synaptic pruning method to dynamically modulate the network architecture and simultaneously improve network performance. The proposed model is biologically inspired as it dynamically eliminates redundant connections based on the synaptic pruning rules used during the brain's development. Connections are pruned if they are not activated or less activated multiple times consecutively. Extensive experiments demonstrate the effectiveness of our method on classification tasks of different complexity with the MNIST, Fashion MNIST, and CIFAR-10 datasets. Experimental results reveal that even for a compact network, the proposed method can also remove up to 59–90% of the connections, with relative improvement in learning speed and accuracy.

A Method of Environmental Sound Classification Based on Residual Networks and Data Augmentation

2021 ◽  
pp. 2150018
Author(s):  
Jinfang Zeng ◽  
Youming Li ◽  
Yu Zhang ◽  
Da Chen
Keyword(s):  
Neural Networks ◽  
Data Augmentation ◽  
Machine Learning Techniques ◽  
Deep Convolutional Neural Networks ◽  
Mel Frequency Cepstral Coefficients ◽  
Environmental Sound ◽  
Sound Classification ◽  
Learning Techniques ◽  
Proposed Model ◽  
Audio Data

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. To date, a variety of signal processing and machine learning techniques have been applied to ESC task, including matrix factorization, dictionary learning, wavelet filterbanks and deep neural networks. It is observed that features extracted from deeper networks tend to achieve higher performance than those extracted from shallow networks. However, in ESC task, only the deep convolutional neural networks (CNNs) which contain several layers are used and the residual networks are ignored, which lead to degradation in the performance. Meanwhile, a possible explanation for the limited exploration of CNNs and the difficulty to improve on simpler models is the relative scarcity of labeled data for ESC. In this paper, a residual network called EnvResNet for the ESC task is proposed. In addition, we propose to use audio data augmentation to overcome the problem of data scarcity. The experiments will be performed on the ESC-50 database. Combined with data augmentation, the proposed model outperforms baseline implementations relying on mel-frequency cepstral coefficients and achieves results comparable to other state-of-the-art approaches in terms of classification accuracy.

scholarly journals Binary and Multiclass Text Classification by Means of Separable Convolutional Neural Network

Inventions ◽  
2021 ◽  
Vol 6 (4) ◽  
pp. 70
Author(s):  
Elena Solovyeva ◽  
Ali Abdullah
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Recurrent Neural Networks ◽  
Low Cost ◽  
Computational Cost ◽  
High Accuracy ◽  
Activation Functions ◽  
Fully Connected ◽  
Fully Connected Networks

In this paper, the structure of a separable convolutional neural network that consists of an embedding layer, separable convolutional layers, convolutional layer and global average pooling is represented for binary and multiclass text classifications. The advantage of the proposed structure is the absence of multiple fully connected layers, which is used to increase the classification accuracy but raises the computational cost. The combination of low-cost separable convolutional layers and a convolutional layer is proposed to gain high accuracy and, simultaneously, to reduce the complexity of neural classifiers. Advantages are demonstrated at binary and multiclass classifications of written texts by means of the proposed networks under the sigmoid and Softmax activation functions in convolutional layer. At binary and multiclass classifications, the accuracy obtained by separable convolutional neural networks is higher in comparison with some investigated types of recurrent neural networks and fully connected networks.

scholarly journals A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks

2020 ◽  
Author(s):  
B Wang ◽  
Y Sun ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Learning Task ◽  
Fixed Number ◽  
Learning Rate ◽  
Current Layer ◽  
Training Process ◽  
Deep Convolutional Neural Networks

© 2019, Springer Nature Switzerland AG. Image classification is a difficult machine learning task, where Convolutional Neural Networks (CNNs) have been applied for over 20 years in order to solve the problem. In recent years, instead of the traditional way of only connecting the current layer with its next layer, shortcut connections have been proposed to connect the current layer with its forward layers apart from its next layer, which has been proved to be able to facilitate the training process of deep CNNs. However, there are various ways to build the shortcut connections, it is hard to manually design the best shortcut connections when solving a particular problem, especially given the design of the network architecture is already very challenging. In this paper, a hybrid evolutionary computation (EC) method is proposed to automatically evolve both the architecture of deep CNNs and the shortcut connections. Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs. The proposed algorithm is evaluated on three widely used benchmark datasets of image classification and compared with 12 peer Non-EC based competitors and one EC based competitor. The experimental results demonstrate that the proposed method outperforms all of the peer competitors in terms of classification accuracy.

Pruning for Hardware-Based Deep Spiking Neural Networks Using Gated Schottky Diode as Synaptic Devices

2020 ◽  
Vol 20 (11) ◽  
pp. 6603-6608 ◽  
Author(s):  
Sung-Tae Lee ◽  
Suhwan Lim ◽  
Jong-Ho Bae ◽  
Dongseok Kwon ◽  
Hyeong-Su Kim ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Schottky Diodes ◽  
Computational Cost ◽  
Spiking Neural Networks ◽  
Training Procedure ◽  
Learning Tasks ◽  
L1 Regularization ◽  
The Cost ◽  
High Computational Cost

Deep learning represents state-of-the-art results in various machine learning tasks, but for applications that require real-time inference, the high computational cost of deep neural networks becomes a bottleneck for the efficiency. To overcome the high computational cost of deep neural networks, spiking neural networks (SNN) have been proposed. Herein, we propose a hardware implementation of the SNN with gated Schottky diodes as synaptic devices. In addition, we apply L1 regularization for connection pruning of the deep spiking neural networks using gated Schottky diodes as synap-tic devices. Applying L1 regularization eliminates the need for a re-training procedure because it prunes the weights based on the cost function. The compressed hardware-based SNN is energy efficient while achieving a classification accuracy of 97.85% which is comparable to 98.13% of the software deep neural networks (DNN).

scholarly journals CircConv: A Structured Convolution with Low Complexity

2019 ◽  
Vol 33 ◽  
pp. 4287-4294
Author(s):  
Siyu Liao ◽  
Bo Yuan
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Low Complexity ◽  
Deep Convolutional Neural Networks ◽  
Significant Saving ◽  
Machine Learning Applications ◽  
Fast Multiplication ◽  
Large Model

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structureimposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.

scholarly journals BE-FNet: 3D Bounding Box Estimation Feature Pyramid Network for Accurate and Efficient Maxillary Sinus Segmentation

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Zhuofu Deng ◽  
Binbin Wang ◽  
Zhiliang Zhu
Keyword(s):  
Neural Networks ◽  
Maxillary Sinus ◽  
Convolutional Neural Networks ◽  
Feature Fusion ◽  
Medical Images ◽  
Medical Image Segmentation ◽  
3D Segmentation ◽  
Deep Convolutional Neural Networks ◽  
Bounding Box ◽  
Proposed Model

Maxillary sinus segmentation plays an important role in the choice of therapeutic strategies for nasal disease and treatment monitoring. Difficulties in traditional approaches deal with extremely heterogeneous intensity caused by lesions, abnormal anatomy structures, and blurring boundaries of cavity. 2D and 3D deep convolutional neural networks have grown popular in medical image segmentation due to utilization of large labeled datasets to learn discriminative features. However, for 3D segmentation in medical images, 2D networks are not competent in extracting more significant spacial features, and 3D ones suffer from unbearable burden of computation, which results in great challenges to maxillary sinus segmentation. In this paper, we propose a deep neural network with an end-to-end manner to generalize a fully automatic 3D segmentation. At first, our proposed model serves a symmetrical encoder-decoder architecture for multitask of bounding box estimation and in-region 3D segmentation, which cannot reduce excessive computation requirements but eliminate false positives remarkably, promoting 3D segmentation applied in 3D convolutional neural networks. In addition, an overestimation strategy is presented to avoid overfitting phenomena in conventional multitask networks. Meanwhile, we introduce residual dense blocks to increase the depth of the proposed network and attention excitation mechanism to improve the performance of bounding box estimation, both of which bring little influence to computation cost. Especially, the structure of multilevel feature fusion in the pyramid network strengthens the ability of identification to global and local discriminative features in foreground and background achieving more advanced segmentation results. At last, to address problems of blurring boundary and class imbalance in medical images, a hybrid loss function is designed for multiple tasks. To illustrate the strength of our proposed model, we evaluated it against the state-of-the-art methods. Our model performed better significantly with an average Dice 0.947±0.031, VOE 10.23±5.29, and ASD 2.86±2.11, respectively, which denotes a promising technique with strong robust in practice.

scholarly journals A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study

Algorithms ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 273
Author(s):  
Ioannis E. Livieris ◽  
Spiros D. Dafnis ◽  
George K. Papadopoulos ◽  
Dionissios P. Kalivas
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Computational Cost ◽  
Economic Benefits ◽  
Mixed Data ◽  
Cotton Production ◽  
Proposed Model ◽  
Multiple Input ◽  
Fully Connected

Cotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network model for the prediction of cotton’s production. The proposed model utilizes as inputs three different kinds of data (soil data, cultivation management data, and yield management data) which are treated and handled independently. The significant advantages of the selected architecture are that it is able to efficiently exploit mixed data, which usually requires being processed separately, reduces overfitting, and provides more flexibility and adaptivity for low computational cost compared to a classical fully-connected neural network. An empirical study was performed utilizing data from three consecutive years from cotton farms in Central Greece (Thessaly) in which the prediction performance of the proposed model was evaluated against that of traditional neural network-based and state-of-the-art models. The numerical experiments revealed the superiority of the proposed approach.

scholarly journals Understanding unconventional preprocessors in deep convolutional neural networks for face identification

2019 ◽  
Vol 1 (11) ◽  
Author(s):  
Chollette C. Olisah ◽  
Lyndon Smith
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Color Space ◽  
Back Propagation ◽  
Face Identification ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Deep Network

Abstract Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

scholarly journals Guided Networks for Few-Shot Image Segmentation and Fully Connected CRFs

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1508
Author(s):  
Kun Zhang ◽  
Yuanjie Zheng ◽  
Xiaobo Deng ◽  
Weikuan Jia ◽  
Jian Lian ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feature Fusion ◽  
Object Segmentation ◽  
Conditional Random Field ◽  
High Dimensional ◽  
Learning Method ◽  
Deep Convolutional Neural Networks ◽  
Structured Output ◽  
Fully Connected ◽  
Task Representations

The goal of the few-shot learning method is to learn quickly from a low-data regime. Structured output tasks like segmentation are challenging for few-shot learning, due to their being high-dimensional and statistically dependent. For this problem, we propose improved guided networks and combine them with a fully connected conditional random field (CRF). The guided network extracts task representations from annotated support images through feature fusion to do fast, accurate inference on new unannotated query images. By bringing together few-shot learning methods and fully connected CRFs, our method can do accurate object segmentation by overcoming poor localization properties of deep convolutional neural networks and can quickly updating tasks, without further optimization, when faced with new data. Our guided network is at the forefront of accuracy for the terms of annotation volume and time.

scholarly journals Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

2021 ◽  
Author(s):  
Mohammed Abdulla Salim Al Husaini ◽  
Mohamed Hadi Habaebi ◽  
Teddy Surya Gunawan ◽  
Md Rafiqul Islam ◽  
Elfatih A. A. Elsheikh ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Early Stage ◽  
Computational Cost ◽  
Optimization Methods ◽  
Optimization Method ◽  
Deep Convolutional Neural Networks ◽  
Breast Thermography

AbstractBreast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3–30 were used in conjunction with learning rates 1 × 10–3, 1 × 10–4 and 1 × 10–5, Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 × 10–4, and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20–30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.

Sign in / Sign up

Export Citation Format

Share Document