CLeAR

★ CLeAR Group Members


Work-in-progress

The Evolutionary Dynamics of Independent Learning Agents in Population Games

Shuyue Hu ★, Chin-Wing Leung, Ho-fung Leung, and Harold Soh ★

    [Pre-Print PDF] [BibTeX]
    @article{hu2020evolutionary,
    title={The Evolutionary Dynamics of Independent Learning Agents in Population Games},
    author={Hu, Shuyue and Leung, Chin-Wing and Leung, Ho-fung and Soh, Harold},
    journal={arXiv preprint arXiv:2006.16068},
    year={2020}}

2021

C21-4Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects

Tasbolat Taunyazov★, Luar Shui Song★, Eugene Lim★, Hian Hian See, David Lee, Benjamin C.K. Tee, Harold Soh★

IEEE International Conference on Intelligent Robots and Systems (IROS), 2021

    [PDF] [Github] [BibTeX]
    @inproceedings{taunyazov2021extended,
    title={Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects},
    author={Tasbolat Taunyazov and Luar Shui Song and Eugene Lim and Hian Hian See and David Lee and Benjamin C. K. Tee and Harold Soh},
    year={2021},
    booktitle={IEEE International Conference on Intelligent Robots and Systems (IROS)}}

C21-3Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning

Kaiqi Chen★, Yong Lee★, and Harold Soh★

IEEE International Conference on Robotics and Automation (ICRA), 2021

    [PDF] [BibTeX]
    @inproceedings{Chen2021MuMMI,
    title={Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning},
    author={Kaiqi Chen and Yong Lee and Harold Soh},
    year={2021},
    booktitle={IEEE International Conference on Robotics and Automation (ICRA)}}

C21-2Embedding Symbolic Temporal Knowledge into Deep Sequential Models

Yaqi Xie ★, Fan Zhou ★, and Harold Soh ★

IEEE International Conference on Robotics and Automation (ICRA), 2021

    [PDF] [Video] [Blog Post] [BibTeX]
    @inproceedings{xie20templogic,
    title={Embedding Symbolic Temporal Knowledge into Deep Sequential Models},
    author={Yaqi Xie and Fan Zhou and Harold Soh},
    year={2021},
    booktitle={IEEE International Conference on Robotics and Automation (ICRA)}}

C21-1Refining Deep Generative Models via Discriminator Gradient Flow

Abdul Fatir Ansari ★, Ming Liang Ang ★, and Harold Soh ★

International Conference on Learning Representations (ICLR), 2021

(28.6% Acceptance Rate)

    [PDF] [Github] [Blog Post] [BibTeX]
    @inproceedings{fatir2021refining,
    title={Refining Deep Generative Models via Discriminator Gradient Flow},
    author={Ansari, Abdul Fatir and Ang, Ming Liang and Soh, Harold},
    booktitle={International Conference on Learning Representations (ICLR)},
    year={2021}}

LBR21-1A Theoretical Framework for Large-Scale Human-Robot Interaction with Groups of Learning Agents

Nicholas Teh ★, Shuyue Hu ★, and Harold Soh ★

Late Breaking Report, ACM/IEEE Conference on Human Robot Interaction (HRI), 2021

    [PDF] [BibTeX]
    @inproceedings{Teh21,
    author = {Teh, Nicholas and Hu, Shuyue and Soh, Harold},
    title = {A Theoretical Framework for Large-Scale Human-Robot Interaction with Groups of Learning Agents},
    year = {2021},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    booktitle = {Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction},
    series = {HRI ’21}}

2020

C20-7Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization

Sreejith Balakrishnan ★, Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Harold Soh ★

Neural Information Processing Systems (NeurIPS), 2020

(20.1% Acceptance Rate)

    [PDF] [Blog Post] [BibTeX]
    @misc{balakrishnan20,
    title={Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization},
    author={Sreejith Balakrishnan and Quoc Phong Nguyen and Bryan Kian Hsiang Low and Harold Soh},
    year={2020},
    booktitle={Advances in Neural Information Processing Systems}}

J20-4Trust in Robots: Challenges and Opportunities

Bing Cai Kok★, and Harold Soh ★

Current Robotics Reports, 2020

    [Publisher Link] [PDF] [BibTeX]
    @article{kok20trust,
    title={Trust in Robots: Challenges and Opportunities},
    author={Bing Cai Kok and and Harold Soh},
    journal={Current Robotics Reports},
    year={2020},
    doi={10.1007/s43154-020-00029-y}}

J20-3Robots at work: People prefer—and forgive—service robots with perceived feelings

Kai Chi Yam, Yochanan Bigman, Pok Man Tang, Remus Ilies, David De Cremer, Harold Soh ★, and Kurt Gray

Journal of Applied Psychology, 2020

C20-6Getting to Know One Another: Calibrating Intent, Capabilities and Trust for Human-Robot Collaboration

Joshua Lee★, Jeffrey Fong★, Bing Cai Kok★, and Harold Soh ★

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020

    [PDF] [Github] [BibTeX]
    @inproceedings{lee2020trust,
    title={Getting to Know One Another: Calibrating Intent, Capabilities and Trust for Human-Robot Collaboration},
    author={Joshua Lee and Jeffrey Fong and Bing Cai Kok and and Harold Soh},
    booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
    year = {2020},
    month = {October}}

C20-5TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition

Fuqiang Gu★, Weicong Sng★, Tasbolat Taunyazov★, and Harold Soh ★

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020

    [PDF] [Github] [BibTeX]
    @inproceedings{gu2020tactile,
    title={TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition},
    author={Fuqiang Gu and Weicong Sng and Tasbolat Taunyazov and Harold Soh},
    booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
    year = {2020},
    month = {October}}

C20-4Fast Texture Classification Using Tactile Neural Coding and Spiking Neural Network

Tasbolat Taunyazov★, Yansong Chua, Ruihan Gao, Harold Soh ★, and Yan Wu

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020

    [PDF] [BibTeX]
    @inproceedings{taunyazov2020texture,
    title={Fast Texture Classification Using Tactile Neural Coding and Spiking Neural Network},
    author={Tasbolat Taunyazov and Yansong Chua and Ruihan Gao and Harold Soh and Yan Wu},
    booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
    year = {2020},
    month = {October}}

C20-3Event-Driven Visual-Tactile Sensing and Learning for Robots

Tasbolat Taunyazov★, Weicong Sng★, Hian Hian See, Brian Lim, Jethro Kuan★, Abdul Fatir Ansari★, Benjamin Tee, and Harold Soh ★

Robotics: Science and Systems Conference (RSS), 2020

    [PDF] [Github] [Paper Site] [Blog Post] [BibTeX]
    @inproceedings{taunyazov20event,
    title={Event-Driven Visual-Tactile Sensing and Learning for Robots},
    author={Tasbolat Taunyazoz and Weicong Sng and Hian Hian See and Brian Lim and Jethro Kuan and
    Abdul Fatir Ansari and Benjamin Tee and Harold Soh},
    year={2020},
    booktitle = {Proceedings of Robotics: Science and Systems},
    year = {2020},
    month = {July}}

C20-2OralA Characteristic Function Approach to Deep Implicit Generative Modeling

Abdul Fatir Ansari★, Jonathan Scarlett, and Harold Soh★

The Conference on Computer Vision and Pattern Recognition (CVPR), 2020

(22.1% Acceptance Rate, Oral Presentation ~5%)

    [PDF] [Github] [Video] [BibTeX]
    @misc{ansari2019characteristic,
    title={A Characteristic Function Approach to Deep Implicit Generative Modeling},
    author={Abdul Fatir Ansari and Jonathan Scarlett and Harold Soh},
    year={2019},
    eprint={1909.07425},
    archivePrefix={arXiv}}

C20-1OralFactorized Inference in Deep Markov Models for Incomplete Multimodal Time Series

Zhi-Xuan Tan, Harold Soh ★, Desmond Ong

Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020

(20.6% Acceptance rate, Oral Presentation)

    [PDF] [Github] [BibTeX]
    @inproceedings{tan2020mdmm,
    title={Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series},
    author={Tan, Zhi-Xuan and Soh, Harold and Ong, Desmond},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={34}}

J20-2Multi-Task Trust Transfer for Human Robot Interaction

Harold Soh ★, Yaqi Xie★, Min Chen, and David Hsu

International Journal of Robotics Research (IJRR), 2020

(Impact Factor: 6.134)

    [Publisher Link] [PDF] [Github] [Blog Post] [BibTeX]
    @article{soh2019multi,
    title={Multi-task trust transfer for human--robot interaction},
    author={Soh, Harold and Xie, Yaqi and Chen, Min and Hsu, David},
    journal={The International Journal of Robotics Research},
    volume = {39},
    number = {2-3},
    pages = {233-249},
    year = {2020},
    doi = {10.1177/0278364919866905},
    publisher={SAGE Publications Sage UK: London, England}}

J20-1Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning

Min Chen, Stefanos Nikolaidis, Harold Soh ★, David Hsu, and Siddhartha Srinivasa

ACM Transactions on Human Robot Interaction (THRI), 2020

    [Publisher Link] [PDF] [BibTeX]
    @article{10.1145/3359616, author = {Chen, Min and Nikolaidis, Stefanos and Soh, Harold and Hsu, David and Srinivasa,
    Siddhartha},
    title = {Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning},
    year = {2020},
    issue_date = {February 2020},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    volume = {9},
    number = {2},
    url = {https://doi.org/10.1145/3359616},
    doi = {10.1145/3359616},
    journal = {J. Hum.-Robot Interact.},
    month = jan,
    articleno = {Article 9},
    numpages = {23}}

LBR20-2Modeling the Interplay of Trust and Attention in HRI: an Autonomous Vehicle Study

Indu Prasad Bodala★, Bing Cai Kok★, Weicong Sng★, and Harold Soh ★

Late Breaking Report, ACM/IEEE Conference on Human Robot Interaction (HRI), 2020

    [PDF] [BibTeX]
    @inproceedings{bodala2020modeling,
    title={Modeling the Interplay of Trust and Attention in HRI: An Autonomous Vehicle Study},
    author={Bodala, Indu P and Kok, Bing Cai and Sng, Weicong and Soh, Harold},
    booktitle={Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction},
    pages={145--147},
    year={2020}}

LBR20-1Juiced and Ready to Predict Private Information in Deep Cooperative Reinforcement Learning

Eugene Lim★, Bing Cai Kok★, Joshua Lee★, Songli Wang★, and Harold Soh ★

Late Breaking Report, ACM/IEEE Conference on Human Robot Interaction (HRI), 2020

    [PDF] [BibTeX]
    @inproceedings{10.1145/3371382.3378308,
    author = {Lim, Eugene and Kok, Bing Cai and Wang, Songli and Lee, Joshua and Soh, Harold},
    title = {Juiced and Ready to Predict Private Information in Deep Cooperative Reinforcement Learning},
    year = {2020},
    isbn = {9781450370578},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3371382.3378308},
    doi = {10.1145/3371382.3378308},
    booktitle = {Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction},
    pages = {343–345},
    numpages = {3},
    keywords = {deep reinforcement learning, cooperative multi-agent system, human-robot collaboration},
    location = {Cambridge, United Kingdom},
    series = {HRI ’20}}

2019

C19-6Embedding Symbolic Knowledge into Deep Networks

Yaqi Xie★, Ziwei Xu, Mohan Kankanhalli, Kuldeep S. Meel, and Harold Soh ★

Neural Information Processing Systems (NeurIPS), 2019

(21% Acceptance rate)

    [PDF] [BibTeX]
    @inproceedings{yaqi2019embedding,
    title={Embedding Symbolic Knowledge into Deep Networks},
    author={Yaqi, Xie and Xu, Ziwei and Meel, Kuldeep S and Kankanhalli, Mohan and Soh, Harold},
    booktitle={Advances in Neural Information Processing Systems},
    pages={4235--4245},
    year={2019}}

C19-5Hyperprior Induced Unsupervised Disentanglement of Latent Representations

Abdul Fatir Ansari★ and Harold Soh ★

Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019

(16.2% Acceptance Rate)

    [PDF] [Github] [BibTeX]
    @inproceedings{ansari2019hyperprior,
    title={Hyperprior induced unsupervised disentanglement of latent representations},
    author={Ansari, Abdul Fatir and Soh, Harold},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={33},
    pages={3175--3182},
    year={2019}}

C19-4Robot Capability and Intention in Trust-based Decisions across Tasks

Xie Yaqi★, Indu Prasad★, Desmond Ong, David Hsu and Harold Soh ★

ACM/IEEE Conference on Human Robot Interaction (HRI), 2019

(24% Acceptance Rate)

    [PDF] [BibTeX]
    @inproceedings{xie2019robot,
    title={Robot Capability and Intention in Trust-Based Decisions Across Tasks},
    author={Xie, Yaqi and Bodala, Indu P and Ong, Desmond C and Hsu, David and Soh, Harold},
    booktitle={2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)},
    pages={39--47},
    year={2019},
    organization={IEEE}}

C19-3Towards Effective Tactile Identification of Textures using a Hybrid Touch Approach

Tasbolat Taunyazov★, Hui Fang Koh, Yan Wu, Caixia Cai and Harold Soh ★

IEEE International Conference on Robotics and Automation (ICRA), 2019

    [PDF] [Github] [BibTeX]
    @inproceedings{taunyazov2019towards,
    title={Towards effective tactile identification of textures using a hybrid touch approach},
    author={Taunyazov, Tasbolat and Koh, Hui Fang and Wu, Yan and Cai, Caixia and Soh, Harold},
    booktitle={2019 International Conference on Robotics and Automation (ICRA)},
    pages={4269--4275},
    year={2019},
    organization={IEEE}}

J19-1Applying Probabilistic Programming to Affective Computing

Desmond Ong, Harold Soh ★, Jamil Zaki and Noah Goodman

IEEE Transactions on Affective Computing, 2019

(Impact Factor: 6.288)

    [PDF] [BibTeX]
    @article{ong2019applying,
    title={Applying Probabilistic Programming to Affective Computing},
    author={Ong, Desmond and Soh, Harold and Zaki, Jamil and Goodman, Noah},
    journal={IEEE Transactions on Affective Computing},
    year={2019},
    publisher={IEEE}}

C19-2Deep Language-based Critiquing for Recommender Systems

Ga Wu, Kai Luo, Scott Sanner and Harold Soh ★

ACM Recommender Systems Conference (RecSys), 2019

(19% Acceptance Rate)

    [PDF] [BibTeX]
    @inproceedings{wu2019deep,
    title={Deep language-based critiquing for recommender systems},
    author={Wu, Ga and Luo, Kai and Sanner, Scott and Soh, Harold},
    booktitle={Proceedings of the 13th ACM Conference on Recommender Systems},
    pages={137--145},
    year={2019},
    organization={ACM}}

C19-1Best Paper Sister TrackTrust Dynamics and Transfer across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models

Harold Soh ★, Shu Pan★, Min Chen and David Hsu

IJCAI Best Paper Sister Track, 2019

    [PDF] [Github] [BibTeX]
    @inproceedings{ijcai2019-868,
    title = {Trust Dynamics and Transfer across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models},
    author = {Soh, Harold and Pan, Shu and Chen, Min and Hsu, David},
    booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI-19}},
    publisher = {International Joint Conferences on Artificial Intelligence Organization},
    pages = {6226--6230},
    year = {2019},
    month = {7},
    doi = {10.24963/ijcai.2019/868},
    url = {https://doi.org/10.24963/ijcai.2019/868},}

2018

C18-5BEST PAPER FINALISTThe Transfer of Human Trust in Robot Capabilities across Tasks

Harold Soh ★, Shu Pan★, Min Chen, and David Hsu

Robotics Science and Systems (RSS), 2018

(Best Paper Award Finalist)

    [PDF] [Github] [BibTeX]
    @INPROCEEDINGS{Soh-RSS-18,
    AUTHOR = {Harold Soh AND Shu Pan AND Chen Min AND David Hsu},
    TITLE  = {The Transfer of Human Trust in Robot Capabilities across Tasks},
    BOOKTITLE = {Proceedings of Robotics: Science and Systems},
    YEAR = {2018},
    ADDRESS = {Pittsburgh, Pennsylvania},
    MONTH = {June},
    DOI = {10.15607/RSS.2018.XIV.033}} 

C18-4BEST PAPER FINALISTGeneration Meets Recommendation: Proposing Novel Items for Groups of Users

Vo Vinh Thanh★ and Harold Soh ★

ACM Recommender Systems Conference (RecSys), 2018

(17.7% Acceptance Rate, Best Long Paper Award Runner-up)

    [Publisher Link] [PDF] [Poster] [Slides] [BibTeX]
    @inproceedings{vo2018generation,
    title={Generation meets recommendation: proposing novel items for groups of users},
    author={Vo, Thanh Vinh and Soh, Harold},
    booktitle={Proceedings of the 12th ACM Conference on Recommender Systems},
    pages={145--153},
    year={2018},
    organization={ACM}}

C18-3BEST PAPER FINALISTPlanning with Trust for Human Robot Collaboration

Min Chen, Stefanos Nikolaidis, Harold Soh ★, David Hsu, and Siddhartha Srinivasa

ACM/IEEE Conference on Human Robot Interaction (HRI), 2018

(23% Acceptance Rate, Best Paper Award Finalist)

    [PDF] [BibTeX]
    @inproceedings{chen2018planning,
    title={Planning with trust for human-robot collaboration},
    author={Chen, Min and Nikolaidis, Stefanos and Soh, Harold and Hsu, David and Srinivasa, Siddhartha},
    booktitle={Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction},
    pages={307--315},
    year={2018},
    organization={ACM}}

LBR18-1Human Trust in Robot Capabilities across Tasks

Pan Shu★, Min Chen, Stefanos Nikolaidis, David Hsu, and Harold Soh ★

Late Breaking Report, ACM/IEEE Conference on Human Robot Interaction (HRI), 2018

    [PDF] [BibTeX]
    @inproceedings{Shu2018trust,
    author = {Shu, Pan and Min, Chen and Bodala, Indu and Nikolaidis, Stefanos and Hsu, David and Soh, Harold},
    title = {Human Trust in Robot Capabilities Across Tasks},
    booktitle = {Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction},
    series = {HRI '18},
    year = {2018},
    isbn = {978-1-4503-5615-2},
    location = {Chicago, IL, USA},
    pages = {241--242},
    numpages = {2},
    url = {http://doi.acm.org/10.1145/3173386.3177034},
    doi = {10.1145/3173386.3177034},
    acmid = {3177034},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {human robot interaction, trust},}

C18-2Z-Transforms and its Inference on Partially Observable Point Processes

Young Lee★, Vo Vinh Thanh★, Kar Wai Lim, and Harold Soh ★

Intl. Joint Conference on Artificial Intelligence (IJCAI), 2018

(20.5% Acceptance Rate)

    [PDF] [BibTeX]
    @inproceedings{lee2018z,
    title={Z-Transforms and its Inference on Partially Observable Point Processes.},
    author={Lee, Young and Vo, Thanh Vinh and Lim, Kar Wai and Soh, Harold},
    booktitle={IJCAI},
    pages={2369--2375},
    year={2018}}

C18-1Collaborative Filtering with Behavioral Models

Dusan Sovilj, Scott Sanner, Harold Soh ★, and Hanze Li

ACM User Modeling and Personalization Conference (UMAP), 2018

(28% Acceptance Rate)

    [PDF] [BibTeX]
    @inproceedings{sovilj2018collaborative,
    title={Collaborative filtering with behavioral models},
    author={Sovilj, Dusan and Sanner, Scott and Soh, Harold and Li, Hanze},
    booktitle={Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization},
    pages={91--99},
    year={2018},
    organization={ACM}}

J18-1Measuring and Mitigating the Costs of Attentional Switches in Active Network Monitoring for Cybersecurity

Sean W. Kortschot, Dusan Sovilj, Greg A. Jamieson, Scott Sanner, Chelsea Carrasco, and Harold Soh★

Human Factors: The Journal of the Human Factors and Ergonomics Society

    [PDF] [BibTeX]
    @article{kortschot2018measuring,
    title={Measuring and mitigating the costs of attentional switches in active network monitoring for cybersecurity},
    author={Kortschot, Sean W and Sovilj, Dusan and Jamieson, Greg A and Sanner, Scott and Carrasco, Chelsea and Soh, Harold},
    journal={Human factors},
    volume={60},
    
    number={7},
    pages={962--977},
    year={2018},
    publisher={SAGE Publications Sage CA: Los Angeles, CA}}

Selected publications before 2017

C17-2Deep Sequential Recommendation for Adaptive User Interfaces

Harold Soh, Scott Sanner, Madeleine White, and Greg Jamieson

ACM Intelligent User Interfaces (IUI), 2017

(27% Acceptance Rate)

    [PDF] [BibTeX]
    @inproceedings{soh2017deep,
    title={Deep sequential recommendation for personalized adaptive user interfaces},
    author={Soh, Harold and Sanner, Scott and White, Madeleine and Jamieson, Greg},
    booktitle={Proceedings of the 22nd international conference on intelligent user interfaces},
    pages={589--593},
    year={2017},
    organization={ACM}}

P17-1J15-1Learning Assistance by Demonstration: Smart Mobility with Shared Control and Paired Haptic Controllers

Harold Soh and Yiannis Demiris

Journal of Human-Robot Interaction, vol 4, No 3, 2015.

Selected for Presentation at ACM/IEEE HRI 2017

    [Publisher Link] [PDF] [BibTeX]
    @article{soh2015learning,
    title={Learning assistance by demonstration: Smart mobility with shared control and paired haptic controllers},
    author={Soh, Harold and Demiris, Yiannis},
    journal={Journal of Human-Robot Interaction},
    volume={4},
    number={3},
    pages={76--100},
    year={2015},
    publisher={Journal of Human-Robot Interaction Steering Committee}}

J14-2Spatio-Temporal Learning with the Online Finite and Infinite Echo-state Gaussian Processes

Harold Soh and Yiannis Demiris

IEEE Transactions on Neural Networks and Learning Systems, 2014.

    [Publisher Link] [PDF] [BibTeX]
    @article{DBLP:journals/tnn/SohD15,
    author    = {Harold Soh and Yiannis Demiris},
    title     = {Spatio-Temporal Learning With the Online Finite and Infinite Echo-State Gaussian Processes},
    journal   = {{IEEE} Trans. Neural Networks Learn. Syst.},
    volume    = {26},
    number    = {3},
    pages     = {522--536},
    year      = {2015},
    url       = {https://doi.org/10.1109/TNNLS.2014.2316291},
    doi       = {10.1109/TNNLS.2014.2316291},
    timestamp = {Mon, 09 Mar 2020 15:52:04 +0100},
    biburl    = {https://dblp.org/rec/journals/tnn/SohD15.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}}

J14-1Iteratively Learning Objects by Touch: Online Discriminative and Generative Models for Tactile-­based Recognition

Harold Soh and Yiannis Demiris

IEEE Transactions on Haptics, 2014.

    [Publisher Link] [PDF] [Github] [BibTeX]
    @article{article,
    author = {Soh, Harold and Demiris, Yiannis},
    year = {2014},
    month = {05},
    pages = {512-525},
    title = {Incrementally Learning Objects by Touch: Online Discriminative and Generative Models for Tactile-Based Recognition},
    volume = {7},
    journal = {IEEE Transactions on Haptics},
    doi = {10.1109/TOH.2014.2326159}}

R13-3When and How To Assist: An Iterative Probabilistic Model for Learning Assistance by Demonstration

Harold Soh and Yiannis Demiris

IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan, 2013.

    [PDF] [BibTeX]
    @INPROCEEDINGS{6696815,
    author={Soh, Harold and Demiris, Yiannis},
    booktitle={2013 IEEE/RSJ International Conference on Intelligent Robots and Systems},
    title={When and how to help: An iterative probabilistic model for learning assistance by demonstration},
    year={2013},
    volume={},
    number={},
    pages={3230-3236},
    doi={10.1109/IROS.2013.6696815}}

C13-2BEST PAPER FINALISTOnline Spatio-Temporal Gaussian Process Experts with Application to Tactile Classification

Harold Soh, Yanyu Su and Yiannis Demiris

IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, Portugal, 2012.

    [Publisher Link] [PDF] [Github] [BibTeX]
    @INPROCEEDINGS{soh2012tactile,
    author={Soh, Harold and Su, Yanyu and Demiris, Yiannis},
    booktitle={2012 IEEE/RSJ International Conference on Intelligent Robots and Systems},
    title={Online spatio-temporal Gaussian process experts with application to tactile classification},
    year={2012},
    volume={},
    number={},
    pages={4489-4496},
    doi={10.1109/IROS.2012.6385992}}

C13-1Iterative Temporal Learning and Prediction with the Sparse Online Echo State Gaussian Process

Harold Soh and Yiannis Demiris

IEEE International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia, 2012.

    [Publisher Link] [PDF] [Github] [Dataset] [BibTeX]
    @INPROCEEDINGS{6252504,
    author={Soh, Harold and Demiris, Yiannis},
    booktitle={The 2012 International Joint Conference on Neural Networks (IJCNN)},
    title={Iterative temporal learning and prediction with the sparse online echo state gaussian process},
    year={2012},
    volume={},
    number={},
    pages={1-8},
    doi={10.1109/IJCNN.2012.6252504}}

C11-1Evolving policies for multi-reward partially observable markov decision processes (MR-POMDPs)

Harold Soh and Yiannis Demiris

GECCO’11: Proceedings of the 2011 conference on Genetic and Evolutionary Computation, 713-720, 2011

    [Publisher Link] [Github] [BibTeX]
    @inproceedings{10.1145/2001576.2001674,
    author = {Soh, Harold and Demiris, Yiannis},
    title = {Evolving Policies for Multi-Reward Partially Observable Markov Decision Processes (MR-POMDPs)},
    year = {2011},
    isbn = {9781450305570},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/2001576.2001674},
    doi = {10.1145/2001576.2001674},
    abstract = {Plans and decisions in many real-world scenarios are made under uncertainty and to satisfy multiple, possibly
    conflicting, objectives. In this work, we contribute the multi-reward partially-observable Markov decision process
    (MR-POMDP) as a general modelling framework. To solve MR-POMDPs, we present two hybrid (memetic) multi-objective
    evolutionary algorithms that generate non-dominated sets of policies (in the form of stochastic finite state controllers).
    Performance comparisons between the methods on multi-objective problems in robotics (with 2, 3 and 5 objectives),
    web-advertising (with 3, 4 and 5 objectives) and infectious disease control (with 3 objectives), revealed that memetic
    variants outperformed their original counterparts. We anticipate that the MR-POMDP along with multi-objective evolutionary
    solvers will prove useful in a variety of theoretical and real-world applications.},
    booktitle = {Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation},
    pages = {713–720},
    numpages = {8},
    keywords = {multi-objective optimization, evolutionary algorithm, multi-reward pomdp},
    location = {Dublin, Ireland},
    series = {GECCO '11}}

W11-2Multi-reward policies for medical applications: anthrax attacks and smart wheelchairs

Harold Soh and Yiannis Demiris

MedGEC 2011, 7th GECCO Workshop on Medical Applications of Genetic and Evolutionary Computation, 471-478, 2011

    [Publisher Link] [BibTeX]
    @inproceedings{10.1145/2001858.2002036,
    author = {Soh, Harold and Demiris, Yiannis},
    title = {Multi-Reward Policies for Medical Applications: Anthrax Attacks and Smart Wheelchairs},
    year = {2011},
    isbn = {9781450306904},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/2001858.2002036},
    doi = {10.1145/2001858.2002036},
    abstract = {Medical decisions are often difficult; they involve uncertain information, multiple-objectives
    and debatable outcomes. In this work, we discuss the application of the multi-reward partially-observable
    Markov decision process (MR-POMDP) and NSGA2-LS, a hybridised multi-objective evolutionary solver, to two
    problems in the medical domain: anthrax response and smart-wheelchair control. For the first problem, we
    use a discrete model and analyse the trade-offs between the best solutions (in the form of finite-state
    controllers) found by our evolutionary algorithm. For the second, we contribute an extension of our method
    to the continuous space and optimising recurrent neural networks (RNNs) for use on medical robots such as
    smart wheelchairs.},
    booktitle = {Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation},
    pages = {471–478},
    numpages = {8},
    keywords = {multi-objective optimization, medical applications, evolutionary algorithms},
    location = {Dublin, Ireland},
    series = {GECCO '11}}

J10-2Weighted complex network analysis of travel routes on the Singapore public transportation system

Harold Soh, Sonja Lim, Tianyou Zhang, Xiuju Fu, Gary Kee Khoon Lee, Terence Gih Guang Hung, Pan Di, Silvester Prakasam, Limsoon Wong

Physica A: Statistical Mechanics and its Applications 389 (24), 5852-5863, 2010

    [Publisher Link] [PDF] [BibTeX]
    @article{SOH20105852, title = {Weighted complex network analysis of travel routes on the Singapore public transportation system},
    journal = {Physica A: Statistical Mechanics and its Applications},
    volume = {389},
    number = {24},
    pages = {5852-5863},
    year = {2010},
    issn = {0378-4371},
    doi = {https://doi.org/10.1016/j.physa.2010.08.015},
    url = {https://www.sciencedirect.com/science/article/pii/S0378437110006977},
    author = {Harold Soh and Sonja Lim and Tianyou Zhang and Xiuju Fu and Gary Kee Khoon Lee and Terence Gih Guang Hung
    and Pan Di and Silvester Prakasam and Limsoon Wong},
    keywords = {Weighted complex network analysis, Topological analysis, Transportation system},
    abstract = {The structure and properties of public transportation networks have great implications for
    urban planning, public policies and infectious disease control. We contribute a complex weighted network
    analysis of travel routes on the Singapore rail and bus transportation systems. We study the two networks
    using both topological and dynamical analyses. Our results provide additional evidence that a dynamical
    study adds to the information gained by traditional topological analysis, providing a richer view of complex
    weighted networks. For example, while initial topological measures showed that the rail network is almost
    fully connected, dynamical measures highlighted hub nodes that experience disproportionately large traffic.
    The dynamical assortativity of the bus networks also differed from its topological counterpart. In addition,
    inspection of the weighted eigenvector centralities highlighted a significant difference in traffic flows for
    both networks during weekdays and weekends, suggesting the importance of adding a temporal perspective missing
    from many previous studies.}}

For other publications, please see Harold’s Publications