Common Kernels and Convolutions in Binary- and Ternary-Weight Neural Networks

2020 ◽  
pp. 2150158
Author(s):  
Byungmin Ahn ◽  
Taewhan Kim
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Optimization Algorithm ◽  
State Of The Art ◽  
The State ◽  
Memory Access ◽  
Experimental Results ◽  
Hardware Platform ◽  
Access Latency ◽  
The Common

A new algorithm for extracting common kernels and convolutions to maximally eliminate the redundant operations among the convolutions in binary- and ternary-weight convolutional neural networks is presented. Precisely, we propose (1) a new algorithm of common kernel extraction to overcome the local and limited exploration of common kernel candidates by the existing method, and subsequently apply (2) a new concept of common convolution extraction to maximally eliminate the redundancy in the convolution operations. In addition, our algorithm is able to (3) tune in minimizing the number of resulting kernels for convolutions, thereby saving the total memory access latency for kernels. Experimental results on ternary-weight VGG-16 demonstrate that our convolution optimization algorithm is very effective, reducing the total number of operations for all convolutions by [Formula: see text], thereby reducing the total number of execution cycles on hardware platform by 22.4% while using [Formula: see text] fewer kernels over that of the convolution utilizing the common kernels extracted by the state-of-the-art algorithm.

scholarly journals Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Md Zahangir Alom ◽  
Paheding Sidike ◽  
Mahmudul Hasan ◽  
Tarek M. Taha ◽  
Vijayan K. Asari
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
State Of The Art ◽  
The State ◽  
Superior Performance ◽  
Deep Convolutional Neural Networks ◽  
Practical Applications ◽  
High Degree

In spite of advances in object recognition technology, handwritten Bangla character recognition (HBCR) remains largely unsolved due to the presence of many ambiguous handwritten characters and excessively cursive Bangla handwritings. Even many advanced existing methods do not lead to satisfactory performance in practice that related to HBCR. In this paper, a set of the state-of-the-art deep convolutional neural networks (DCNNs) is discussed and their performance on the application of HBCR is systematically evaluated. The main advantage of DCNN approaches is that they can extract discriminative features from raw data and represent them with a high degree of invariance to object distortions. The experimental results show the superior performance of DCNN models compared with the other popular object recognition approaches, which implies DCNN can be a good candidate for building an automatic HBCR system for practical applications.

Sanitizing hidden activations for improving adversarial robustness of convolutional neural networks

2021 ◽  
pp. 1-11
Author(s):  
Tianshi Mu ◽  
Kequan Lin ◽  
Huabing Zhang ◽  
Jian Wang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Black Box ◽  
Experimental Results ◽  
Amplification Effect ◽  
Wide Range ◽  
Adversarial Examples

Deep learning is gaining significant traction in a wide range of areas. Whereas, recent studies have demonstrated that deep learning exhibits the fatal weakness on adversarial examples. Due to the black-box nature and un-transparency problem of deep learning, it is difficult to explain the reason for the existence of adversarial examples and also hard to defend against them. This study focuses on improving the adversarial robustness of convolutional neural networks. We first explore how adversarial examples behave inside the network through visualization. We find that adversarial examples produce perturbations in hidden activations, which forms an amplification effect to fool the network. Motivated by this observation, we propose an approach, termed as sanitizing hidden activations, to help the network correctly recognize adversarial examples by eliminating or reducing the perturbations in hidden activations. To demonstrate the effectiveness of our approach, we conduct experiments on three widely used datasets: MNIST, CIFAR-10 and ImageNet, and also compare with state-of-the-art defense techniques. The experimental results show that our sanitizing approach is more generalized to defend against different kinds of attacks and can effectively improve the adversarial robustness of convolutional neural networks.

scholarly journals LdsConv: Learned Depthwise Separable Convolutions by Group Pruning

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4349
Author(s):  
Wenxiang Lin ◽  
Yan Ding ◽  
Hua-Liang Wei ◽  
Xinglin Pan ◽  
Yutong Zhang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Computational Cost ◽  
The State ◽  
Direct Replacement ◽  
Improved Accuracy ◽  
Pruning Technique ◽  
Strong Capacity

Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning. It integrates the pruning technique into the design of convolutional filters, formulated as a generic convolutional unit that can be used as a direct replacement of convolutions without any adjustments of the architecture. To show the effectiveness of the proposed method, experiments are carried out using the state-of-the-art convolutional neural networks (CNNs), including ResNet, DenseNet, SE-ResNet and MobileNet, respectively. The results show that by simply replacing the original convolution with LdsConv in these CNNs, it can achieve a significantly improved accuracy while reducing computational cost. For the case of ResNet50, the FLOPs can be reduced by 40.9%, meanwhile the accuracy on the associated ImageNet increases.

scholarly journals AAR-CNNs: Auto Adaptive Regularized Convolutional Neural Networks

2018 ◽  
Author(s):  
Yao Lu ◽  
Guangming Lu ◽  
Yuanrong Xu ◽  
Bob Zhang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Experimental Results ◽  
Training Phase ◽  
Low Resolution ◽  
Adaptive Regularization ◽  
End To End ◽  
Overfitting Problem

In order to address the overfitting problem caused by the small or simple training datasets and the large model’s size in Convolutional Neural Networks (CNNs), a novel Auto Adaptive Regularization (AAR) method is proposed in this paper. The relevant networks can be called AAR-CNNs. AAR is the first method using the “abstraction extent” (predicted by AE net) and a tiny learnable module (SE net) to auto adaptively predict more accurate and individualized regularization information. The AAR module can be directly inserted into every stage of any popular networks and trained end to end to improve the networks’ flexibility. This method can not only regularize the network at both the forward and the backward processes in the training phase, but also regularize the network on a more refined level (channel or pixel level) depending on the abstraction extent’s form. Comparative experiments are performed on low resolution ImageNet, CIFAR and SVHN datasets. Experimental results show that the AAR-CNNs can achieve state-of-the-art performances on these datasets.

scholarly journals Graph Convolutional Networks for Text Classification

2019 ◽  
Vol 33 ◽  
pp. 7370-7377 ◽  
Author(s):  
Liang Yao ◽  
Chengsheng Mao ◽  
Yuan Luo
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Text Classification ◽  
State Of The Art ◽  
Classical Problem ◽  
Experimental Results ◽  
Training Data ◽  
Convolutional Networks ◽  
Single Text

Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.

scholarly journals Informing Piano Multi-Pitch Estimation with Inferred Local Polyphony Based on Convolutional Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 851
Author(s):  
Michael Taenzer ◽  
Stylianos I. Mimilakis ◽  
Jakob Abeßer
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Piano Music ◽  
Experimental Results ◽  
Pitch Estimation ◽  
Feature Representations ◽  
Series Of Experiments ◽  
Music Recordings ◽  
Recent Extension

In this work, we propose considering the information from a polyphony for multi-pitch estimation (MPE) in piano music recordings. To that aim, we propose a method for local polyphony estimation (LPE), which is based on convolutional neural networks (CNNs) trained in a supervised fashion to explicitly predict the degree of polyphony. We investigate two feature representations as inputs to our method, in particular, the Constant-Q Transform (CQT) and its recent extension Folded-CQT (F-CQT). To evaluate the performance of our method, we conduct a series of experiments on real and synthetic piano recordings based on the MIDI Aligned Piano Sounds (MAPS) and the Saarland Music Data (SMD) datasets. We compare our approaches with a state-of-the art piano transcription method by informing said method with the LPE knowledge in a postprocessing stage. The experimental results suggest that using explicit LPE information can refine MPE predictions. Furthermore, it is shown that, on average, the CQT representation is preferred over F-CQT for LPE.

scholarly journals Optimizing 3D Convolution Kernels on Stereo Matching for Resource Efficient Computations

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6808
Author(s):  
Jianqiang Xiao ◽  
Dianbo Ma ◽  
Satoshi Yamane
Keyword(s):  
Neural Networks ◽  
Computational Complexity ◽  
Convolutional Neural Networks ◽  
Stereo Matching ◽  
State Of The Art ◽  
Computational Cost ◽  
The State ◽  
Matching Network ◽  
Convolution Kernels ◽  
Low Computational Cost

Despite recent stereo matching algorithms achieving significant results on public benchmarks, the problem of requiring heavy computation remains unsolved. Most works focus on designing an architecture to reduce the computational complexity, while we take aim at optimizing 3D convolution kernels on the Pyramid Stereo Matching Network (PSMNet) for solving the problem. In this paper, we design a series of comparative experiments exploring the performance of well-known convolution kernels on PSMNet. Our model saves the computational complexity from 256.66G MAdd (Multiply-Add operations) to 69.03G MAdd (198.47G MAdd to 10.84G MAdd for only considering 3D convolutional neural networks) without losing accuracy. On Scene Flow and KITTI 2015 datasets, our model achieves results comparable to the state-of-the-art with a low computational cost.

scholarly journals Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting Method

2021 ◽  
Author(s):  
Emna Krichene ◽  
Wael Ouarda ◽  
Habib Chabchoub ◽  
Ajith Abraham ◽  
Abdulrahman M. Qahtani ◽  
...  
Keyword(s):  
Neural Networks ◽  
State Of The Art ◽  
High Accuracy ◽  
The State ◽  
Experimental Results ◽  
Forecasting Method ◽  
Testing Data ◽  
Predicted Values ◽  
Estimated Error ◽  
Forecasting Techniques

A newly introduced method called Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting method is applied and extended in this study to forecast numerical values. Unlike traditional forecasting techniques which forecast only future values, our proposed method provides a new extension to correct the predicted values which is done by forecasting the estimated error. Experimental results demonstrated that the proposed method has a high accuracy both in training and testing data and outperform the state-of-the-art RNN models on Mackey-Glass, NARMA, Lorenz and Henon map datasets.

Recurrent convolutional neural networks for poet identification

2020 ◽  
Author(s):  
Dariush Salami ◽  
Saeedeh Momtazi
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Short Term Memory ◽  
State Of The Art ◽  
The State ◽  
Support Vector ◽  
Neural Network Models ◽  
Spatial Features ◽  
Input Text

Abstract Deep neural networks have been widely used in various language processing tasks. Recurrent neural networks (RNNs) and convolutional neural networks (CNN) are two common types of neural networks that have a successful history in capturing temporal and spatial features of texts. By using RNN, we can encode input text to a lower space of semantic features while considering the sequential behavior of words. By using CNN, we can transfer the representation of input text to a flat structure to be used for classifying text. In this article, we proposed a novel recurrent CNN model to capture not only the temporal but also the spatial features of the input poem/verse to be used for poet identification. Considering the shortcomings of the normal RNNs, we try both long short-term memory and gated recurrent unit units in the proposed architecture and apply them to the poet identification task. There are a large number of poems in the history of literature whose poets are unknown. Considering the importance of the task in the information processing field, a great variety of methods from traditional learning models, such as support vector machine and logistic regression, to deep neural network models, such as CNN, have been proposed to address this problem. Our experiments show that the proposed model significantly outperforms the state-of-the-art models for poet identification by receiving either a poem or a single verse as input. In comparison to the state-of-the-art CNN model, we achieved 9% and 4% improvements in f-measure for poem- and verse-based tasks, respectively.

Sign in / Sign up

Export Citation Format

Share Document