The Centralized Training and Decentralized Execution (CTDE) paradigm, where a centralized critic is allowed to access global information during the training phase while maintaining the learned policies executed with only local information in a ...

In recent years, the transfer learning method of replacing acoustic features with phonetic features has become a new paradigm for end-to-end spoken language recognition. However, these larger transfer learning models always encode too much ...

Display Omitted

• Design a phonetic dictionary to extract phone posterior distributions.
• Propose a PLDE pooling layer to better utilize phonetic features.
• Replace utterance-level projection with chunk-level projection.
• Achieve competitive ...

Spoken language recognition has made significant progress in recent years, for which automatic speech recognition has been used as a parallel branch to extract phonetic features. However, there is still a lack of a better training strategy for ...

Thanks to Network Function Virtualization (NFV), Internet Service Providers (ISPs) can improve network resource utilization with significantly reduced capital and operational expenditures. To dig deeper into the potential of NFV, an important challenge is ...

Attention-based convolutional neural network models are increasingly adopted for language recognition tasks. In this paper, based on the self-attention mechanism, we solve the study of language recognition by acquiring rich context dependence. To ...

• A novel hippocampus-heuristic character recognition network (HCRN) is proposed for zero/few-shot learning.

The recognition of Chinese characters has always been a challenging task due to their huge variety and complex structures. The current radical-based methods fail to recognize Chinese characters without learning all of their radicals in ...

Language recognition based on embedding aims to maximize inter-class variance and minimize intra-class variance. Previous researches are limited to the training constraint of a single centroid, which cannot accurately describe the overall ...

Conjunctive normal forms (CNF) of structured satisfiability problems contain logic gate patterns. So Boolean circuits (BC) by and large can be obtained from them and thus structural information that is lost in the CNF can be recovered. However, it ...

Similarity representation plays a central role in increasingly popular anomaly detection techniques, which have been successfully applied in various realistic scenes. Until now, many low-rank representation techniques have been introduced to measure the ...

A recently proposed canonical representation called Bi-Kronecker Functional Decision Diagrams (BKFDDs) utilizes the classical decompositions (the Shannon and Davio decompositions) and their biconditional variants, and hence can be seen as a ...

• Studying mixed blocking flowshop scheduling problems with sequence-dependent setup times (PFSP-BS).

Permutation flowshop scheduling problem (PFSP) is a classical NP-Hard combinatorial optimisation problem. Existing PFSP variants capture different realistic scenarios, but significant modelling gaps still remain with respect to many ...

The Minimum Dominating Set (MinDS) problem is an NP-hard problem of great importance in both theories and applications. In this paper, we propose a new local search algorithm ScBppw (Score Checking and Best-picking with Probabilistic Walk) to ...

In this paper, we consider the task of discovering the common objects in images. Initially, object candidates are generated in each image and an undirected weighted graph is constructed over all the candidates. Each candidate serves as a node in ...

• An effective heuristic and search algorithm for aircraft sequencing problem.
• ...

Aircraft sequencing problem (ASP) is an NP-Hard problem. It involves allocation of aircraft to runways for landing and takeoff, minimising total tardiness. ASP has made significant progress in recent years. However, within practical ...

Functional transfer matrices consist of real functions with trainable parameters. In this work, functional transfer matrices are used to model functional connections in neural networks. Different from linear connections in conventional weight matrices, ...

An unrealistic assumption in classical extensive game theory is that the complete game tree is fully perceivable by all players. To weaken this assumption, a class of games (called games with short sight) was proposed in literature, modelling the game ...

Weighted partial maximum satisfiability (WPMS) is a significant generalization of maximum satisfiability (MAX-SAT), with many important applications. Recently, breakthroughs have been made on stochastic local search (SLS) for weighted MAX-SAT and (...

The Maximum Vertex Weight Clique (MVWC) problem is NP-hard and also important in real-world applications. In this paper we propose to use the restart and the random walk strategies to improve local search for MVWC. If a solution is revisited in some ...

The graph coloring problem (GCP) is one of the most studied NP hard problems and has numerous applications. Despite the practical importance of GCP, there are limited works in solving GCP for very large graphs. This paper explores techniques for solving ...

Multi-agent systems (MAS) have received extensive studies in the last decade. However, little attention is paid to investigation on reasoning about logics in MAS with hierarchical structures. This paper proposes a complete quantified temporal KBC (...