Targeting High Productivity Workforces via Data-Centric Transfer Optimization in the Internet Era

Project Description

This project aims at developing a novel computational framework that can adaptively re-use the knowledge across multiple machines potentially communicating via internet, to enhance the productivity in problem-solving. The developed framework comprises a class of optimization algorithms which are capable of automatically transferring knowledge across problem-solving tasks and by which the complicated real-world problems can be efficiently tackled. Different from the optimizers in the existing multitudinous Bayesian frameworks which are computationally demanding and prevailingly applicable in continuous search space, the optimization algorithms considered by the proposed framework are constraint-free in search space, and rely on nature-inspired, derivative-free, population-based search strategies which require little domain expertise on the user’s side. Besides, the proposed framework is significantly flexible in model selection and combination, and is highly parallelizable due to its emphasis on population-based search. The considered class of algorithms is regarded as a potential shortcut through which artificial general intelligence is achieved.

This project aims at developing a novel computational framework that can adaptively re-use the knowledge across multiple machines potentially communicating via internet, to enhance the productivity in problem-solving. The developed framework comprises a class of optimization algorithms which are capable of automatically transferring knowledge across problem-solving tasks and by which the complicated real-world problems can be efficiently tackled. Different from the optimizers in the existing multitudinous Bayesian frameworks which are computationally demanding and prevailingly applicable in continuous search space, the optimization algorithms considered by the proposed framework are constraint-free in search space, and rely on nature-inspired, derivative-free, population-based search strategies which require little domain expertise on the user’s side. Besides, the proposed framework is significantly flexible in model selection and combination, and is highly parallelizable due to its emphasis on population-based search. The considered class of algorithms is regarded as a potential shortcut through which artificial general intelligence is achieved.

Research Technical Area

  • Heuristic search and optimization
  • Machine learning
  • Search and constraint satisfaction

Benefits to the society

The proposed project may significantly improve the productivity of real-world problem-solving and autonomous decision-making through human-like knowledge transfer across problems.

The class of optimization algorithms considered by the project may impact a wide range of real applications, such as smart logistic systems, supply chain management, path planning of autonomous vehicles, automatic traffic signal control, design of smart charging strategies for electrical vehicles, optimization of smart grids, and advanced materials manufacturing, which align with the Smart Nation Initiative of Singapore.

Project’s Publications

  1. Abhishek Gupta, Yew-Soon Ong:
    Back to the Roots: Multi-X Evolutionary Computation. Cognitive Computation 11(1): 1-17 (2019)

  2. Tiantian He, Yang Liu, Tobey H. Ko, Keith C.C. Chan, Yew-Soon Ong: 
    Contextual Correlation Preserving Multi-View Featured Graph Clustering. IEEE Transactions on Cybernetics. 2019. PP. 10.1109/TCYB.2019.2926431. 

  3. Hao Li, Yew-Soon Ong, Maoguo Gong, Zhenkun Wang: 
    Evolutionary Multitasking Sparse Reconstruction: Framework and Case Study. IEEE Transactions on Evolutionary Computation. 2018. PP. 1-1. 10.1109/TEVC.2018.2881955.

  4. Tiantian He, Lu Bai, Yew-Soon Ong:
    Manifold Regularized Stochastic Block Model. 2019. 10.1109/ICTAI.2019.00115.

Team’s Principal Investigator

Professor Ong Yew-Soon
School of Computer Science and Engineering
College of Engineering Nanyang Technological University

 

Dr. Ong Yew-Soon received BEng (Hons) and MEng degrees from Nanyang Technological University in 1998 and 1999, and PhD degree from the University of Southampton in 2003. Dr. Ong is currently a Professor at the School of Computer Science and Engineering, Nanyang Technological University, where he is also the Director of the Data Science and Artificial Intelligence Research Center, and co-Director of the Singtel-NTU Cognitive & Artificial Intelligence Joint Lab and the A*Star SIMTECH-NTU Joint Lab on Complex Systems. His current research interests include artificial and computational intelligence, memetic computing, evolutionary and Bayesian optimization, and machine learning.

 

Recent Notable Awards

  1. Outstanding Paper Award, IEEE Transactions on Evolutionary Computation, 2019
  2. Fellow of IEEE, 2018
  3. Thomson Reuters Highly Cited Researcher, 2016

The Team

Co-Principal Investigator

Prof. Dipti Srinivasan, National University of Singapore

Research Focus: Heuristic search and optimisation, Multiagent systems, Smart grid