Results 1 to 10 of about 609,020 (244)

Bio-Inspired Neural Network Dynamics-Aware Reinforcement Learning for Spiking Neural Network [PDF]

Biomimetics
Artificial Intelligence (AI) has seen rapid advancements in recent times, finding applications across various sectors and achieving notable successes. However, current AI models based on Deep Convolutional Neural Networks (DNNs) face numerous challenges,
Yu Zheng, Jingfeng Xue, Junhan Yang, Yanjun Zhang   +3 more
doaj   +2 more sources

Explanations for Neural Networks by Neural Networks [PDF]

Applied Sciences, 2022
Understanding the function learned by a neural network is crucial in many domains, e.g., to detect a model’s adaption to concept drift in online learning. Existing global surrogate model approaches generate explanations by maximizing the fidelity between the neural network and a surrogate model on a sample-basis, which can be very time-consuming ...
Sascha Marton, Stefan Lüdtke, Christian Bartelt   +2 more
openaire   +2 more sources

Unet-Astar: A Deep Learning-Based Fast Routing Algorithm for Unified PCB Routing

IEEE Access, 2023
In recent years, there has been extensive research on the routing problem of printed circuit boards (PCBs). Due to the increasing number of pins, high pin density, and unique physical constraints, manual PCB routing has become a time-consuming task to ...
Shiyuan Yin, Min Jin, Gang Chen, Guoliang Gong, Wenyu Mao, Huaxiang Lu   +5 more
doaj   +1 more source

Reinforcement-learning-based parameter adaptation method for particle swarm optimization

Complex & Intelligent Systems, 2023
Particle swarm optimization (PSO) is a well-known optimization algorithm that shows good performances in solving different optimization problems. However, the PSO usually suffers from slow convergence.
Shiyuan Yin, Min Jin, Huaxiang Lu, Guoliang Gong, Wenyu Mao, Gang Chen, Wenchang Li   +6 more
doaj   +1 more source

JD-SLAM: Joint camera pose estimation and moving object segmentation for simultaneous localization and mapping in dynamic scenes

International Journal of Advanced Robotic Systems, 2021
As a fundamental assumption in simultaneous localization and mapping, the static scenes hypothesis can be hardly fulfilled in applications of indoor/outdoor navigation or localization.
Yujia Zhai, Baoli Lu, Weijun Li, Jian Xu, Shuangyi Ma   +4 more
doaj   +1 more source

Prediction model of coal seam gas content based on ACSOA optimized BP neural network

Meikuang Anquan, 2022
For the problem of coal seam gas content prediction, the influencing factors of coal seam gas content were analyzed by taking No.2 coal seam of Chensilou Coal Mine as the research object.
Prediction model of coal seam gas content based on ACSOA optimized BP neural network
doaj   +1 more source

Prediction of metal ion ligand binding residues by adding disorder value and propensity factors based on deep learning algorithm

Frontiers in Genetics, 2022
Proteins need to interact with different ligands to perform their functions. Among the ligands, the metal ion is a major ligand. At present, the prediction of protein metal ion ligand binding residues is a challenge. In this study, we selected Zn2+, Cu2+,
Sixi Hao, Sixi Hao, Xiuzhen Hu, Xiuzhen Hu, Zhenxing Feng, Zhenxing Feng, Kai Sun, Kai Sun, Xiaoxiao You, Xiaoxiao You, Ziyang Wang, Ziyang Wang, Caiyun Yang, Caiyun Yang   +13 more
doaj   +1 more source

Bootstrapping Neural Networks [PDF]

Neural Computation, 2000
Knowledge about the distribution of a statistical estimator is important for various purposes, such as the construction of confidence intervals for model parameters or the determination of critical values of tests. A widely used method to estimate this distribution is the so-called bootstrap, which is based on an imitation of the probabilistic ...
Franke, Jürgen, Neumann, Michael
openaire   +3 more sources

Recognition of Metal Ion Ligand-Binding Residues by Adding Correlation Features and Propensity Factors

Frontiers in Genetics, 2022
The realization of many protein functions is inseparable from the interaction with ligands; in particular, the combination of protein and metal ion ligands performs an important biological function.
Shuang Xu, Shuang Xu, Xiuzhen Hu, Xiuzhen Hu, Zhenxing Feng, Zhenxing Feng, Jing Pang, Jing Pang, Kai Sun, Kai Sun, Xiaoxiao You, Xiaoxiao You, Ziyang Wang, Ziyang Wang   +13 more
doaj   +1 more source

Correlational Neural Networks [PDF]

Neural Computation, 2016
Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)–based approaches and autoencoder (AE)–based approaches.
Chandar, Sarath, Khapra, Mitesh M., Larochelle, Hugo, Ravindran, Balaraman   +3 more
openaire   +4 more sources