With the rapid development of artificial intelligence, people have put forward higher requirements for robot path planning. As a more commonly used algorithm, reinforcement learning learns from experience by imitating...
详细信息
The prediction of urban traffic congestion has always been one of the important contents in the research of intelligent transportation systems. The difficulty in predicting urban traffic congestion is that urban traff...
详细信息
Topic modeling algorithms such as the latent Dirichlet allocation (LDA) play an important role in machine learning research. Fitting LDA using Gibbs sampler-related algorithms involves a sampling process over K topics...
详细信息
Among qualitative direction relation models, Oriented point relation algebra(OPRAm) is a remarkable model for robot navigation with uncertain direction information. It has great advantages in providing powerful expr...
详细信息
Among qualitative direction relation models, Oriented point relation algebra(OPRAm) is a remarkable model for robot navigation with uncertain direction information. It has great advantages in providing powerful expressions with very limited information compared with other point-based spatial relation *** original OPRAm is defined in 2D space, and its model and reasoning algorithm are found not applicable in 3D space. We proposed a novel direction relation model named OPRA3Dmto extend the original OPRAm to 3D space,and presented a new reasoning algorithm on Oriented point relation algebra in three dimension(OPRA3Dm). A further study was carried out for composition reasoning on OPRA3Dm. The proposed reasoning algorithm will deduce new information which cannot be directly detected by hardware. The experiment showed the algorithm had some practical significance, it can be applied to the Unmanned aerial vehicle(UAV) navigation and similar scenarios.
Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing meth...
详细信息
Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense *** observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, learning accurate network dynamics with sparse, irregularly-sampled,partial, and noisy observations remains a fundamental challenge. We introduce a new concept of the stochastic skeleton and its neural implementation, i.e., neural ODE processes for network dynamics(NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6% and improving the learning speed for new dynamics by three orders of magnitude.
To facilitate the search of rapidly growing biomedical knowledge in literature, we developed a Biomedical entity-relationship search tool(BERST). It is also a biomedical knowledge integration framework, which presentl...
详细信息
To facilitate the search of rapidly growing biomedical knowledge in literature, we developed a Biomedical entity-relationship search tool(BERST). It is also a biomedical knowledge integration framework, which presently contains six popular databases represented in terms of a network of concepts and relations extracted from these knowledge sources. Users search the integrated knowledge network by entering keywords, and BERST returns a sub-network matching and representing the keywords and their relationships. The resulting graph can be navigated interactively allowing users to explore specific paths between any two nodes representing potentially interesting relationships between them. A graphical UI was developed to provide a more intuitive and overall view of the information being searched and studied. BERST framework can be naturally expanded to integrate other biomedical knowledge sources. BERST is implemented as a Java web application.
Traditional fuzzy C-means clustering algorithm has poor noise immunity and clustering results in image segmentation. To overcome this problem, a novel image clustering algorithm based on SLIC superpixel and transfer l...
详细信息
Compared with traditional algorithms of rough set feature selection, the stochastic algorithms for feature selection based on rough set and swarm intelligence are popular. This paper gives the overview of rough set al...
详细信息
The main challenge in the area of reinforcement learning is scaling up to larger and more complex problems. Aiming at the scaling problem of reinforcement learning, a scalable reinforcement learning method, DCS-SRL, i...
详细信息
The main challenge in the area of reinforcement learning is scaling up to larger and more complex problems. Aiming at the scaling problem of reinforcement learning, a scalable reinforcement learning method, DCS-SRL, is proposed on the basis of divide-and-conquer strategy, and its convergence is proved. In this method, the learning problem in large state space or continuous state space is decomposed into multiple smaller subproblems. Given a specific learning algorithm, each subproblem can be solved independently with limited available resources. In the end, component solutions can be recombined to obtain the desired result. To ad- dress the question of prioritizing subproblems in the scheduler, a weighted priority scheduling algorithm is proposed. This scheduling algorithm ensures that computation is focused on regions of the problem space which are expected to be maximally productive. To expedite the learning process, a new parallel method, called DCS-SPRL, is derived from combining DCS-SRL with a parallel scheduling architecture. In the DCS-SPRL method, the subproblems will be distributed among processors that have the capacity to work in parallel. The experimental results show that learning based on DCS-SPRL has fast convergence speed and good scalability.
Local binary patterns was used to distinguish the Photorealistic Computer Graphics and Photographic Images, however the dimension of the extracted features is too high. Accordingly, the Local Ternary Count based on th...
详细信息
暂无评论