Browse Proceedings

Place cells and grid cells are crucial parts of the cognitive map, which shows a presentation of the real-world observation. However, the previous architecture, which uses CAN for simulating the activities of grid cells, is redundant. And it could ...

Bayesian decision-making theory presumes that humans can maximize the expected gains by trading off risk-returns in a predefined gain function. Recent findings from spatial reaching and coincident timing tasks have challenged this theory by ...

The Mother Tree Optimization (MTO) algorithm is a new swarm intelligence technique that we have recently proposed for solving continuous optimization problems. MTO is built on an offspring topology and a set of cooperating agents. In this paper, ...

Cloud computing is a powerful and scalable computing platform that enables the virtualization, share and on-demand use of computing resources. Scientific workflows on clouds are promising for handling computational-intensive and complex scientific ...

Solving jigsaw-puzzles has been of increasing importance in many real-world applications. The existing methods endure the problem of local or premature convergence, which perform inefficiently on some challenging images. For an efficient optimizer ...

Card counting is a family of casino card game advantage gambling strategies, in which a player keeps a mental tally of the cards played in order to calculate whether the next hand is likely to be in the favor of the player or the dealer. A card ...

In machine learning, we presume datasets to be labeled while performing any operation. But, is it true in real-life scenarios? To its contrary, we have an enormous amount of unlabeled datasets available in the form of images, videos, audios, ...

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are ...

Recommender systems have been widely adopted in various large-scale Web applications. Among these applications, online dating application has attracted more and more research efforts. Essentially, online dating data is a bipartite graph with ...

Although a couple of spiking neural network (SNN) architectures have been developed to perform vector quantization, good performances remains hard to attain. Moreover these architectures make use of rate codes that require an unplausible high ...

Interest has been growing lately towards learning representations for non-Euclidean geometric data structures. Such kinds of data are found everywhere ranging from social network graphs, brain images, sensor networks to 3-dimensional objects. To ...

Tax evasion detection has a crucial role in addressing tax revenue loss. In the real world, an accessed tax dataset only contains a small number of labeled taxpayers who evade tax (positive samples) and a large number of unlabeled taxpayers who ...

Scene text recognition with irregular layouts is a challenging yet important problem in computer vision. One widely used method is to employ a rectification network before the recognition stage. However, most previous rectification methods either ...

Community detection algorithms are the basic tools for discovering the internal structure and organizational principles of a community. Ranging from model-based and optimization-based methods, existing efforts typically consider two sources of ...

Ransomware is a widespread class of malware that encrypts files in a victim’s computer and extorts victims into paying a fee to regain access to their data. Previous research has proposed methods for ransomware detection using machine learning ...

Graphs play an important role in many applications. Recently, Graph Neural Networks (GNNs) have achieved promising results in graph analysis tasks. Some state-of-the-art GNN models have been proposed, e.g., Graph Convolutional Networks (GCNs), ...

Curriculum learning has the potential to solve the problem of sparse rewards, a long-standing challenge in reinforcement learning, with greater sample efficiency than traditional reinforcement learning algorithms because curriculum learning ...

Gradient-based reinforcement learning has gained more and more attention. As one of the most important methods, Deep Deterministic Policy Gradient (DDPG) has achieved remarkable success and has been applied to many challenging continuous ...

Causal inference between two observed variables has received a widespread attention in science. Generally, most existing approaches are focusing on inferring the casual direction based on data of the same type. However, in practice, it is very ...

CDMC-International Cybersecurity Data Mining Competition () is a world unique data-analytic competition sitting in the trans-disciplinary area of artificial intelligence and cybersecurity. In this paper, we summarize CDMC’19—...

To address class imbalance issue in scene text detection, we propose two novel loss functions, namely Class-Balanced Self Adaption Loss (CBSAL) and Class-Balanced First Power Loss (CBFPL). Specifically, CBSAL reshapes Cross Entropy (CE) loss to ...

Recently, multi-agent deep reinforcement learning (MADRL) has been studied to learn actions to achieve complicated tasks and generate their coordination structure. The reward assignment in MADRL is a crucial factor to guide and produce both their ...

This paper proposes a deep hierarchical Non-negative Matrix Factorization (NMF) method with Skip-Gram with Negative sampling (SGNS) to learn semantic relationships in short text data. The proposed unsupervised method learns a dense lower-order ...

Advances in deep reinforcement learning have allowed autonomous agents to perform well on video games, often outperforming humans, using only raw pixels to make their decisions. However, timely context awareness is not fully integrated. In this ...

In this paper we consider the problem of how to balance exploration and exploitation in deep reinforcement learning (DRL). We propose a generative method called double replay buffers with restricted gradient (DRBRG). DRBRG divides the replay ...

A series of semi-supervised learning (SSL) algorithms have been proposed to alleviate the need for labeled data by leveraging large amounts of unlabeled data. Those algorithms have achieved good performance on standard benchmark datasets, however, ...