Neural networks : the official journal of the International Neural Network Society
Mar 4, 2021
We introduce SPLASH units, a class of learnable activation functions shown to simultaneously improve the accuracy of deep neural networks while also improving their robustness to adversarial attacks. SPLASH units have both a simple parameterization a...
Sensors (Basel, Switzerland)
Feb 28, 2021
At present, in the field of video-based human action recognition, deep neural networks are mainly divided into two branches: the 2D convolutional neural network (CNN) and 3D CNN. However, 2D CNN's temporal and spatial feature extraction processes are...
Neural networks : the official journal of the International Neural Network Society
Feb 27, 2021
Knowledge graph embedding (KGE) aims to project both entities and relations into a continuous low-dimensional space. However, for a given knowledge graph (KG), only a small number of entities and relations occur many times, while the vast majority of...
Neural networks : the official journal of the International Neural Network Society
Feb 26, 2021
Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training robust models...
Neural networks : the official journal of the International Neural Network Society
Feb 25, 2021
Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Network (DenseNet), have achieved great success for image representation learning by capturing deep hierarchical features. However, most existing network architectures of simply s...
Neural networks : the official journal of the International Neural Network Society
Feb 24, 2021
Visual question answering requires a deep understanding of both images and natural language. However, most methods mainly focus on visual concept; such as the relationships between various objects. The limited use of object categories combined with t...
Neural networks : the official journal of the International Neural Network Society
Feb 24, 2021
In this paper, the synchronization problem of inertial neural networks with time-varying delays and generally Markovian jumping is investigated. The second order differential equations are transformed into the first-order differential equations by ut...
International journal of computer assisted radiology and surgery
Feb 24, 2021
PURPOSE: Dental radiography represents 13% of all radiological diagnostic imaging. Eliminating the need for manual classification of digital intraoral radiographs could be especially impactful in terms of time savings and metadata quality. However, a...
Sensors (Basel, Switzerland)
Feb 24, 2021
Speech emotion recognition (SER) is a natural method of recognizing individual emotions in everyday life. To distribute SER models to real-world applications, some key challenges must be overcome, such as the lack of datasets tagged with emotion labe...
Neural networks : the official journal of the International Neural Network Society
Feb 23, 2021
Semi-supervised learning has largely alleviated the strong demand for large amount of annotations in deep learning. However, most of the methods have adopted a common assumption that there is always labeled data from the same class of unlabeled data,...