A5101569328- Complex Network Analysis Techniques
- Genomics and Phylogenetic Studies
- Tensor decomposition and applications
- Model Reduction and Neural Networks
- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Endometrial and Cervical Cancer Treatments
- Quantum many-body systems
- Cancer Genomics and Diagnostics
- Advanced Graph Neural Networks
- Anomaly Detection Techniques and Applications
- Opinion Dynamics and Social Influence
- Genetics, Bioinformatics, and Biomedical Research
- Data-Driven Disease Surveillance
- Knowledge Management and Sharing
- Bayesian Modeling and Causal Inference
- Topological and Geometric Data Analysis
- Influenza Virus Research Studies
- Genomics and Rare Diseases
- Protein Tyrosine Phosphatases
- Biochemical Analysis and Sensing Techniques
- Tannin, Tannase and Anticancer Activities
- Neural Networks and Applications
- MicroRNA in disease regulation
- melanin and skin pigmentation
Women's Hospital, School of Medicine, Zhejiang University
2022-2023
Group Sense (China)
2022
University of Chinese Academy of Sciences
2020-2021
Chinese Academy of Sciences
2020-2021
Institute of Theoretical Physics
2020-2021
Wenzhou Medical University
2012
We present a general method for approximately contracting tensor networks with an arbitrary connectivity. This enables us to release the computational power of wide use in inference and learning problems defined on graphs. show applications our algorithm graphical models, specifically estimating free energy spin glasses various graphs, where largely outperforms existing algorithms, including mean-field methods recently proposed neural-network-based methods. further apply simulation random...
Objective. The purpose of this study was to evaluate the accuracy brachytherapy (BT) planning structures derived from Deep learning (DL) based auto-segmentation compared with standard manual delineation for postoperative cervical cancer.Approach. We introduced a convolutional neural networks (CNN) which developed and presented in cancer radiotherapy. dataset 60 patients received BT used train test model high-risk clinical target volume (HRCTV) organs at risk (OARs). Dice similarity...
Restricted Boltzmann machines (RBMs) and deep (DBMs) are important models in machine learning, recently found numerous applications quantum many-body physics. We show that there fundamental connections between them tensor networks. In particular, we demonstrate any RBM DBM can be exactly represented as a two-dimensional network. This representation gives characterizations of the expressive power RBMs DBMs using entanglement structures networks, also provides an efficient network contraction...
We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts small Feedback Vertex Set (FVS) from the graph, converting system to much smaller with many-body and dense interactions an effective energy every configuration of FVS, then learns variational distribution parameterized using neural networks approximate original Boltzmann distribution. The is able estimate free energy, compute observables, generate unbiased samples via direct sampling without...
We perform theoretical and algorithmic studies for the problem of clustering semisupervised classification on graphs with both pairwise relational information single-point attribute information, upon a joint stochastic block model synthetic item-item edges item-attribute edges. Asymptotically exact analysis based Bayesian inference are conducted, using cavity method in statistical physics. Analytically, we identify phase transition generative model, which poses fundamental limits...
Abstract Objective: The purpose of this study was to evaluate the accuracy brachytherapy (BT) planning structures derived from Deep learning (DL) based auto-segmentation compared with standard manual delineation for postoperative cervical cancer. Methods : We introduced a convolutional neural networks (CNN) which developed and presented in cancer radiotherapy. dataset 60 patients received BT used train test model high-risk clinical target volume (HRCTV) organs at risk (OARs). Dice similarity...
Objective To investigate influence of phosphatase regenerating liver-3 (PRL-3)gene silencing with small interference RNA (siRNA) on biological behaviors human prostate cancer LNCaP cells,including proliferation and invasion.Methods The method PRL-3 was established by lentivirus-mediated RNAi.The cells were divided into 3 groups.In experimental group,the expression in stably blocked RNAi.In negative control transfected RNAi (without any to PRL-3).The normal served as blank group.Methyl...
Abstract Next-generation sequencing technologies have increased throughput by 100-1000 folds and subsequently reduced the cost of a human genome to approximately US$1,000. However, existence artifacts can cause erroneous identification variants adversely impact downstream analyses. Currently, manual inspection for additional refinement is still necessary high-quality variant calls. The usually done on large binary alignment map (BAM) files which consume huge amount labor time. It also...
Next-generation sequencing technologies have increased throughput by 100-1000 folds and subsequently reduced the cost of a human genome to approximately US$1,000. However, existence artifacts can cause erroneous identification variants adversely impact downstream analyses. Currently, manual inspection for additional refinement is still necessary high-quality variant calls. The usually done on large binary alignment map (BAM) files which consume huge amount labor time. It also suffers from...