Browse Proceedings

Event-Related Potentials (ERPs) based binary BCI systems help enable users to control external devices through brain signals responding to stimulus. However, the external properties of the auditory or visual stimuli in the typical oddball-paradigm ...

As the bridge between brain science and brain-inspired computation, computational neuroscience has been attracting more and more attention from researchers in different disciplines. However, the current neural simulators based on low-level ...

Gesture recognition using surface electromyography (sEMG) is the technical core of muscle-computer interface (MCI) in human-computer interaction (HCI), which aims to classify gestures according to signals obtained from human hands. Since sEMG ...

Gradient descent is one of the significant research contents in supervised learning of spiking neural networks (SNNs). In order to improve the performance of gradient descent learning algorithms for multilayer SNNs, this paper proposes a spike ...

The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement learning, a ...

Teaching deep learning models commonsense knowledge is a crucial yet challenging step towards building human-level artificial intelligence. Abductive Commonsense Reasoning ($\mathcal{ART}$) is a benchmark that investigates model’s ability on inferencing the ...$\mathcal{}$$$$$$$$$

Recently, micro-expression recognition (MER) has attracted much attention due to its wide application in various fields such as crime trials and psychotherapy. However, the short duration and subtle movement of facial muscles make it difficult to ...

Facial action unit (AU) plays an essential role in human facial behavior analysis. Despite the progress made in frame-level AU analysis, the discrete classification results provided by previous work are not explicit enough for the analysis ...

Convolutional Neural Networks (CNNs) are based on linear kernel at different levels of the network. Linear kernels are not efficient, particularly, when the original data is not linearly separable. In this paper, we focus on this issue by ...

Swarm systems with simple, homogeneous and autonomous individuals can efficiently accomplish specified complex tasks. Recent works have shown the power of deep reinforcement learning (DRL) methods to learn cooperative policies for swarm systems. ...

The open-set recognition task is proposed to handle unknown classes that do not belong to any of the classes in training set. The methods should reject unknown samples while maintaining high classification accuracy on the known classes. Previous ...

This paper explores synthetic image generators in dataset preparation to train models that allow human handwritten character recognition. We examined the most popular deep neural network architectures and presented a method based on autoencoder ...

The partial classification can assign a sample to a class subset when this sample has similar probabilities for multiple classes. However, the extra information for making such predictions usually comes at the cost of retraining the model, ...$\mathrm{}$$\mathrm{}$

Building effective CNN architectures with light weight has become an increasing application demand for person re-identification (Re-ID) tasks. However, most of the existing methods adopt large CNN models as baseline, which is complicated and ...$$$$$$$$

For the grasp task in physical environment, it is important for the manipulator to know the objects’ spatial positions with as few sensors as possible in real time. This work proposed an effective framework to organize the objects’ spatial ...

Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency and usually imposing natural,...

Learning from imbalanced datasets is a challenge in machine learning, oversampling is an effective method to solve the problem of class imbalance, owing to its easy-to-go capability of achieving the balance by synthesizing new samples. However ...

In recent years, learning effective algorithms for combination optimization problems based on reinforcement learning has become a popular topic in artificial intelligence. In this paper, we propose a model Dy-Drl2Op that combines the multi-head ...

For hyperspectral classification, the existence of mixed pixels reduces the classification accuracy. To solve the problem, we apply the multi-label classification technique to hyperspectral classification. The focus of multi-label classification ...

Object detection, one of the core missions in computer vision, plays a significant role in various real-life scenarios. To address the limitations of pre-defined anchor boxes in object detection, a novel multi-scale key-point detector is proposed ...$\mathrm{}\mathrm{}$$\mathrm{}$

In recent years, connectionist networks have become a staple in real world systems due to their ability to generalize and find intricate relationships and patterns in data. One inherent limitation to connectionist networks, however, is ...

Due to various uncertain factors, sometimes it is difficult to obtain accurate data. In comparison, interval-valued data can better represent uncertain information. However, most of the existing theoretical researches on Extended Belief Rule-Based ...

Although the present-day machine learning algorithm sometimes beats humans in visual recognition, we still find significant differences between the brain’s and the machine’s visual processing. Thus, it is not guaranteed that the information ...

Domain-Specific Senses (DSS) acquisition has been one of the major topics in Natural Language Processing (NLP). However, most results from unsupervised learning methods are not effective. This paper addresses the problem and proposes an approach ...

This paper reports and discusses the processing response dependence on a spin-wave reservoir chip, a natural computing device, to present one of the important steps to design a spin-wave reservoir computing hardware. As an example, we deal with a ...