S
Siguang Li
Researcher at Tongji University
Publications - 8
Citations - 141
Siguang Li is an academic researcher from Tongji University. The author has contributed to research in topics: Cloud computing & Convolutional neural network. The author has an hindex of 4, co-authored 7 publications receiving 71 citations. Previous affiliations of Siguang Li include Binzhou University.
Papers
More filters
Journal ArticleDOI
Explaining the black-box model: A survey of local interpretation methods for deep neural networks
TL;DR: This survey focuses on local interpretation methods of deep neural networks with an in-depth analysis of the representative works including the newly proposed approaches, and makes a fine-grained distinction between the two types of these methods.
Journal ArticleDOI
MapReduce based parallel neural networks in enabling large scale machine learning
TL;DR: This paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications and evaluates the performance of these networks from the aspects of accuracy in classification and efficiency in computation.
Journal ArticleDOI
A MapReduce-based parallel K-means clustering for large-scale CIM data verification
TL;DR: Both the experimental and simulation results show that the parallel K‐means reduces the CIM data‐verification time significantly compared with the sequential K-means clustering, while generating a high level of precision in data verification.
Journal ArticleDOI
Transfer learning‐based online multiperson tracking with Gaussian process regression
TL;DR: A novel multi‐person tracking framework is presented by introducing a new Gaussian Process Regression based observation model, which learns in a semi‐supervised manner, which outperforms a number of state‐of‐the‐art methods on some benchmark datasets.
Journal ArticleDOI
A genetic algorithm enhanced automatic data flow management solution for facilitating data intensive applications in the cloud
TL;DR: A genetic algorithm enhanced Automatic Data Flow Management Solution (ADFMS) that facilitates automatic routing function and a self‐adjustable intermediate data management mechanism to achieve an efficient data processing structure of cloud computing.