Edited Book

• Chen K. and Wang L. (2007): Trends in Neural Computation, Berlin: Springer. (ISBN: 3-540-36121-9)
• Wang L., Chen K. and Ong Y. (2005): Advances in Natural Computation (LNCS 3610-3612), Berlin: Springer. (ISBN: 3-540-28325-0)

Book Chapter

• Chen K. (2015): Deep and modular neural networks. In Handbook on Computational Intelligence (Chapter 28, pp. 473-494), Springer. (Invited Article)
• Yang Y. and Chen K. (2007): Combining competitive learning networks of various representations for sequential data clustering. In Trends in Neural Computation (Chapter 13, pp. 315-336), Springer.
• Chen K. (2002): Personalize mobile access by speaker authentication. In Biometrics Resolutions for Authentication in an E-World (Chapter 5, pp. 99-129), Kluwer Academic Publishers.
• Chen K. (1991): An object model organization approach based on probabilistic evident reasoning to support computer vision systems. In: Advances in Postdoctoral Science Researches China, Peking University Press, pp. 731-738.

Journal Article

• Wu L.S. and Chen K. (2024): Goal exploration augmentation via pre-trained skills for sparse-reward long-horizon goal-conditioned reinforcement learning, Machine Learning: (to appear).
• Xia Y., Chen K., and Yang Y. (2021): Multi-label classification with weighted classifier selection and stacked ensemble, Information Science 557: 421-442.
• Phuycharoen M., Zarrineh P., Bridoux, L., Amin S., Losa M., Chen K., Bobola, N., and Rattray M. (2020): Uncovering tissue-specific binding features from differential deep learning, Nucleic Acids Research 48(5): e27.
• Wang Q. and Chen K. (2020): Multi-label zero-shot human action recognition via joint latent ranking embedding, Neural Networks 122: 1-23.
• Zhang S., He Y., Wei J., Mei S., Wan S., and Chen K. (2019): Person re-identification with joint verification and identification of identity-attribute labels, IEEE Access 7(1): 126116-126126.
• Shi P. and Chen K. (2018): Learning constructive primitives for real-time dynamic difficulty adjustment in Super Mario Bros, IEEE Transactions on Games 10(2): 155-169.
• Zennaro F.M. and Chen K. (2018): Towards understanding sparse filtering: A theoretical perspective, Neural Networks, 98: 154-177.
• Madl T., Franklin S., Chen K., and Trappl R. (2018): A computational cognitive framework of spatial memory in brains and robots, Cognitive System Research 47: 147-172.
• Rosyid H., Palmerlee M. and Chen K. (2018): Deploying learning materials to game content for serious education game development: A case study, Entertainment Computing 26: 1-9.
• Wang Q. and Chen K. (2017): Zero-shot visual recognition via bidirectional latent embedding, International Journal of Computer Vision 124(3): 356–383.
• Buckley D., Chen K. and Knowles J. (2017): Rapid skill capture in a first-person shooter, IEEE Transactions on Computational Intelligence and AI in Games 9(1): 63-75.
• Sandouk U. and  Chen K. (2016): Learning contextualized music semantics from tags via a Siamese neural network, ACM Transactions on Intelligent Systems and Technology 8(2): Article 24. (Special Issue on Intelligent Music Systems and Applications)
• Madl T., Franklin S., Chen K., Trappl R., and Montaldi D. (2016): Exploring the structure of spatial representations, PLoS ONE 11(6): e0157343. doi:10.1371/journal.pone.0157343.
• Madl T., Franklin S., Chen K., Montaldi D., and Trappl R. (2016): Towards real-world capable spatial memory in the LIDA cognitive architecture, Biologically Inspired Cognitive Architectures 16: 87-104.
• Sandouk U. and  Chen K. (2016): Learning contextualized semantics from co-occurring terms via a Siamese architecture, Neural Networks 76: 65-96.
• Teh P.S., Zhang N., Teoh A., and Chen K. (2016): A survey on touch dynamics authentication in mobile devices, Computers & Security 59: 210-235.
• Teh P.S., Zhang N., Teoh A., and Chen K. (2016): TDAS: A touch dynamics based multi-factor authentication solution for mobile devices, International Journal of Pervasive Computing and Communications 12(1): 127-153.
• Roberts J. and Chen K. (2015): Learning-based procedural content generation, IEEE Transactions on Computational Intelligence and AI in Games 7(1): 88-101.
• Madl T., Chen K., Montaldi D., and Trappl R. (2015): Computational cognitive models of spatial memory in navigation space: A review, Neural Networks 65: 18-43.
• Madl T., Franklin S., Chen K., Montaldi D., and Trappl R. (2014): Bayesian integration of information in hippocampal place cells, PLoS ONE 9(3): e89762. doi:10.1371/journal.pone.0089762.
• Chen K. and Salman A. (2011): Learning speaker-specific characteristics with a deep neural architecture, IEEE Transactions on Neural Networks 22(11): 1744-1756.
• Chen K. and Wang S. (2011): Semi-supervised learning via regularized boosting working on multiple semi-supervised assumptions, IEEE Transactions on Pattern Analysis and Machine Intelligence 33(1): 129-143.
• Yang Y. and Chen K. (2011): Temporal data clustering via weighted clustering ensemble with different representations, IEEE Transactions on Knowledge and Data Engineering 23(2): 307-320.
• Yang Y. and Chen K. (2011): Time series clustering via RPCL ensemble networks with different representations, IEEE Transactions on Systems, Man and Cybernetics (Part C) 41(2): 190-199.
• Chen K. (2005): Adaptive smoothing via contextual and local discontinuities, IEEE Transactions on Pattern Analysis and Machine Intelligence 27(10): 1552-1567.
• Chen K. (2005): On the use of different representations for speaker modeling, IEEE Transactions on Systems, Man, and Cybernetics (Part C) 35(3): 301-314. (Special issue on Biometric Systems)
• Chen K. (2003): Towards better making a decision in speaker verification, Pattern Recognition 36(2): 329-346. (Special issue on Biometric Authentication)
• Chen K. and Wang D.L. (2002): A dynamically coupled neural oscillator network for image segmentation, Neural Networks 15(3): 423-439.
• Wang L., Chen K., and Chi H.S. (2002): Capture inter-speaker information with a neural network for speaker identification, IEEE Transactions on Neural Networks 13(2): 436-445.
• Chen K., Wu T.Y., and Zhang H.J. (2002): On the use of nearest feature line for speaker identification, Pattern Recognition Letters 23: 1735-1746.
• Chen K. and Wang D.L. (2001): Preserving geometric patterns: from spirals to inside/outside relations, IEEE Transactions on Neural Networks 12(5): 1084-1102.
• Liu X.W., Chen K., and Wang D.L. (2001): Extraction of hydrographic regions from remote sensing images using an oscillator network with weight adaptation, IEEE Transactions on Geoscience and Remote Sensing 39(1), 207-211.
• Chen K. (2001): Book Review on `Supervised and unsupervised pattern recognition -- feature extraction and computational intelligence' (by E. Micheli-Tzanakou), IEEE Transactions on Neural Networks 12(3): 644-647.
• Chen K., Wang D.L., and Liu X.W. (2000): Weight adaptation and oscillatory correlation for image segmentation, IEEE Transactions on Neural Networks 11(5), 1106-1123.
• Chen K., Xu L., and Chi H.S. (1999): Improved learning algorithms for mixture of experts in multiclass classification, Neural Networks 12(9), 1229-1252.
• Chen K. and Chi H.S. (1999): A modular neural network architecture for pattern classification based on different feature sets , International Journal of Neural Systems 9(6), 563-581.
• Chen K. (1998): A connectionist method for pattern classification with diverse features, Pattern Recognition Letters 19(7), 545-558.
• Chen K. and Chi H.S. (1998): A method of combining multiple probabilistic classifiers through soft competition on different feature sets, Neurocomputing -- An International Journal 20(1-3), 227-252.
• Wang L., Chen K., and Chi H.S. (1998): Text-independent speaker identification by combining multiple classifiers with different features. Acta Scientiarum Naturalium, Universitatis Pekinensis 34(2-3): 275-282. Peking University Press. (Invited Paper) (Acta Scientiarum Naturalium, Universitatis Pekinensis: Special Issue in Commemoration of the Centennial of Peking University)
• Chen K., Yu X., and Chi H.S. (1997): Combining linear discriminant functions with neural networks for supervised learning, Neural Computing & Applications 6(1), 19-41.
• Chen K., Wang L., and Chi H.S. (1997): Methods of combining multiple classifiers with different features and their applications to text-independent speaker identification, International Jouranl of Pattern Recognition and Artificial Intelligence 11(3), 417-445.
• Chen K., Yang L.P., Yu X., and Chi H.S. (1997): A self-generating modular neural network architecture for supervised learning, Neurocomputing - An International Journal 16(1), 33-48.
• Bao W.Q., Chen K., and Chi H.S. (1997): A hybrid architecture based on HMM/MLFNN for speaker identification. Acta Scientiarum Naturalium, Universitatis Pekinensis 33(3): 359-367. Peking University Press.
• Chen K., Xie D.H., and Chi H.S. (1996): A modified HME architecture for text-dependent speaker identification, IEEE Transactions on Neural Networks 7(5), 1309-1313.
• Chen K., Xie D.H., and Chi H.S. (1996): Text-dependent speaker identification based on input/output HMMs: An empirical study, Neural Processing Letters 3(2), 81-89.
• Chen K., Xie D.H., and Chi H.S. (1996): Speaker identification using time-delay HMEs, International Journal of Neural Systems, 7(1), 29-43.
• Chen K., Yu X. and Chi H.S. (1996): Text-dependent speaker identification based on the modular tree. Journal of Electronics 5(2): 38-46. Hong Kong Exchange Ltd.
• Chen K., Bao W.Q., and Chi H.S. (1996): Speed up training of recurrent neural networks using constrained optimization techniques. Journal of Computer Science and Technology 11(6): 581-588. Science & Allerton Press.
• Xiang B., Chen K., and Chi H.S. (1996): Explore perceptually-based features for speaker recognition: An empirical study. Journal of Electronics 5(1): 56-63. Hong Kong Exchange Ltd.
• Chen K., Xie D.H., and Chi H.S. (1996): Speaker identification using hierarchical mixtures of experts. Acta Scientiarum Naturalium, Universitatis Pekinensis 32(3): 396-405. Peking University Press.
• Chen K. and Ishikawa M. (1995): A parallel voting scheme for aspect recovery, Journal of Computer Science and Technology, 10(5), 385-402.
• Chen K. (1992): A novel edge detection approach based on fuzzy enhancement techniques. Journal of Pattern Recognition and Artificial Intelligence 5(1): 36-45.
• Chen K., Zhang D.L., and Yan P.F. (1992): Applications of a structural learning algorithm for feed-forward networks to classifications of remote sensing data. Journal of Information and Control 12(5): 32-37.
• Chen K. and Chen H.S. (1989): An effective approach to image enhancement using fuzzy sets theory. Journal of Mini-Micro Computer Systems 10(2): 1-8.
• Cui G.W., Chen K., Su W.H., and Li Z.R. (1989): A rule based expert system for Chinese character text segmentation. Journal of Pattern Recognition and Artificial Intelligence 2(3): 43-49.
• Chen K. and Wang X.Y. (1988): The design and implementation of the interconnection system between DSA and Ethernet. Journal of Nanjing University 24(2): 43-57.
• Chen K. and Zhai C.X. (1987): PT: A syntax-directed editor for high-level programming language. Journal of Computer Applications 10(1): 31-39.

Conference Paper

• Baker T., Climent R. and Chen K. (2023): PolyDDSP: A lightweight and polyphonic differentiable digital signal processing library. In International Symposium on Computer Music Multidisciplinary Research (CMMR 2023), Springer Lecture Note in Artificial Intelligence 13770, Tokyo, Japan.
• Wojtas M. and Chen K. (2020): Feature importance ranking for deep learning. In Advanced Neural Information Processing Systems 33 (NeurIPS 2020), Vancouver, Canada.
• Chen K. (2019): Learning-based video game development in MLP@UoM: An overview. Proceedings of IEEE International Conference on Electrical, Electronics and Information Engineering (ICEEIE 2019), Invited Paper, Bali, Indonesia.
• Zhou H. and Chen K. (2019): Transferable positive/negative speech emotion recognition via class-wise adversarial domain adaptation. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP'19), Brighton, U.K.
• Woof W. and Chen K. (2018): Learning to play general video-games via an object embedding network. In Proceedings of IEEE Computational Intelligence and Games Conference (IEEE CIG'18), Maastricht, The Netherlands.
• Wang Q. and Chen K. (2017): Alternative semantic representations for zero-shot human action recognition. In Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD 2017), Skopje, Macedonia.
• Zennaro F. and Chen K. (2016): Covariate shift adaptation via sparse filtering for high-dimensional periodic data. In NIPS Workshop on Learning in High Dimension with Structure, Barcelona, Spain.
• Shi P. and Chen K. (2016): Online level generation in Super Mario Bros via learning constructive primitives. In Proceedings of IEEE Computational Intelligence and Games Conference (IEEE CIG'16), Santorini, Greece.
• Parkinson J., Sandouk U., and Chen K. (2016): Exploring a mixed representation for encoding temporal coherence. In Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD 2016), Riva del Garda, Italy.
• Teh P.S., Zhang N., Teoh A., and Chen K. (2015): Recognizing your touch: Towards strengthening mobile device authentication via touch dynamics integration. Proceedings of the 13th International Conference on Advances in Mobile Computing & Multimedia (MoMM2015). Brussels, Belgium: ACM. 
• Buckley D., Chen K. and Knowles J. (2013): Predicting skill from player input in a first-person shooter. Proceedings of IEEE Conference on Computational Intelligence and Games (CIG'13), Niagara Falls, ON, Canada
• Madl T., Franklin S., Chen K. and Trappl R. (2013): Spatial working memory in the LIDA cognitive architecture. Proceedings of International Conference on Cognitive Modeling (ICCM'13), Ottawa, Canada
• Chen K. and Salman A. (2011): Extracting speaker-specific information with a regularized Siamese deep network. In Advances in Neural Information Processing Systems 24 (NIPS'11), pp. 298--306, MIT Press.
• Salman A. and Chen K. (2011): Exploring speaker-specific characteristics with deep learning. Proceedings of International Joint Conference on Neural Networks (IJCNN'11), San Jose, U.S.A.
• Shaukat A. and Chen K. (2011): Emotional speech recognition via soft-competition on different acoustic representations. Proceedings of International Joint Conference on Neural Networks (IJCNN'11), San Jose, U.S.A.
• Hau D. and Chen K. (2011): Exploring hierarchical speech representations with a deep convolutional neural network. Proceedings of United Kingdom Annual Workshop on Computational Intelligence (UKCI'11), Manchester, U.K.
• Yang Y. and Chen K. (2010): Unsupervised learning via an iteratively constructed clustering ensemble. Proceedings of International Joint Conference on Neural Networks (IJCNN'10), Barcelona, Spain.
• Shaukat A. and Chen K. (2008): Towards automatic emotional state categorization from speech signals. Proceedings of INTERSPEECH, Brisbane, Australia.
• Chen K. and Wang S.H. (2007): Regularized boost for semi-supervised learning. In Advances in Neural Information Processing Systems 20 (NIPS'07), pp. 281-288, MIT Press.
• Wang S.H. and Chen K. (2007): Ensemble learning with active data selection for semi-supervised pattern classification. Proceedings of IEEE-INNS International Joint Conference on Neural Networks (IJCNN'07), pp. 355-360, Orlando, U.S.A.
• Yang Y. and Chen K. (2006): An ensemble of competitive learning learning networks with different representations for temporal data clustering. Proceedings of International Joint Conference on Neural Networks (IJCNN'06), pp. 5759-5766, Vancouver, Canada.
• Chen K. (2005): Boosting input/output hidden Markov models for sequence classification. Proceedings of International Conference on Natural Computation (ICNC'05), pp. 656-665, Changsha, China. (LNCS 3611, Springer)
• Chen K. (2004): Speaker modeling with various speech representations. Proceedings of International Conference on Biometric Authentication (ICBA'04), pp. 592-599, Hong Kong, China. (LNCS 3072, Springer)
• Chen K. and Yeung S. (2004): Personalized news reading via hybrid learning. Proceedings of International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'04), pp. 607-612, Exeter, U.K. (LNCS 3177, Springer)
• Luo D.S. and Chen K. (2003): Refine decision boundaries of a statistical ensemble by active learning. Proceedings of International Joint Conference on Neural Networks (IJCNN'03), pp. 1523-1528, Portland, U.S.A.
• Luo D.S. and Chen K. (2003): On generalization of statistical ensemble learning on mismatch conditions: An empirical study. Proceedings of International Conference on Neural Information Processing (ICONIP'03), Istanbul, Turkey.
• Wu T.Y., Lu L., Chen K., Zhang H.J. (2003): UBM-based real-time speaker segmentation for broadcasting news. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP'03), pp. II193-II196, Hong Kong, China.
• Wu T.Y., Lu L., Chen K., Zhang H.J. (2003): Universal background models for real-time speaker change detection. Proceedings of International Conference on Multi-Media Modeling (MMM'03), Taiwan.
• Wu T.Y., Lu L., Chen K., Zhang H.J. (2003): Incremental speaker adaptation based on universal background model and its applications on speaker segmentation. Proceedings of International Conference on MultiMedia & Expo (ICME'03), U.S.A.
• Li X.L. and Chen K. (2002): Mandarin verbal information verification. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP'02), pp. I833-I836, Orlando, U.S.A.
• Luo D.S. and Chen K. (2002): A comparative study of statistical ensemble methods on mismatch conditions. Proceedings of World Congress on Computational Intelligence - International Joint Conference on Neural Networks (WCCI'02-IJCNN'02), pp. 59-64, Honolulu, U.S.A.
• Luo D.S. and Chen K. (2002): On the use of statistical ensemble methods for telephone-line speaker identification. Proceedings of IEEE International Conference on Communications, Circuits and Systems (ICCCAS'02), pp. II904-II908, Chengdu, China.
• Chen K., Wang D.L., and Liu X.W. (2001): Image segmentation by weight adaptation and oscillatory correlation. Proceedings of International Conference on Neural Information Processing (ICONIP'2001), pp. 267-272, Shanghai, China. (Invited Paper)
• Wu T.Y. and Chen K. (2001): On the use of nearest feature line for speaker identification. Proceedings of International Conference on Neural Information Processing (ICONIP'2001), pp. 1697-1702, Shanghai, China.
• Wang L., Chen K., and Chi H.S. (2001): Towards better capturing inter-speaker information by active learning for speaker identification. Proceedings of International Joint Conference on Neural Networks (IJCNN'2001), pp. 2985-2990, Washington D.C., U.S.A.
• Meng H., Chan S.F., Wong Y.F., Chan C.C., Wong Y.W., Fung T.Y., Tsui W.C., Chen K., Wang L., Wu T.Y., li X.L., Lee T., Choi W.N., Ching P.C., and Chi H.S. (2001): ISIS: A learning system with combined interaction and delegation dialogs. Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), Vol.3, pp.1551 - 1554, Aalborg, Denmark.
• Cao Y.H., Zhao H.L., and Chen K. (2001): Methodologies of distance invigilation to support distance education. Proceedings of World Congress on Educational Multimedia, Hypermedia, and Telecommunication (ED-MEDIA'2001), Tampere, Finland.
• Liu J.H. and Chen K. (2000): Pruning abnormal data for better making a decision in speaker verification. Proceedings of International Conference on Spoken Language Processing (ICSLP'2000), pp. III1005-III1008, Beijing, China.
• Wang L., Chen K., and Chi H.S. (2000): Optimal fusion of diverse feature sets for speaker identification: An alternative method. Proceedings of International Conference on Spoken Language Processing (ICSLP'2000), pp. II294-II297, Beijing, China.
• Meng H., Chan S.F., Wong Y.F., Fung T.Y., Tsui W.C., Lo T.H., Chan C.C., Chen K., Wang L., Wu T.Y., Li X.L., Lee T., Choi W.N., Wong Y.W., Ching P.C., and Chi H.S. (2000): ISIS: A multilingual spoken dialog system developed with CORBA and KQML agents. Proceedings of International Conference on Spoken Language Processing (ICSLP'2000), pp. II150-II153, Beijing, China.
• Qing X.K. and Chen K. (2000): On use of GMM for multilingual speaker verification: An empirical study. Proceedings of International Symposium on Chinese Spoken Language Processing (ISCSLP'2000), pp. 263-266, Beijing, China.
• Wang L., Chen K., and Chi H.S. (2000): Capture inter-speaker information by a neural network for speaker identification. Proceedings of International Joint Conference on Neural Networks (IJCNN'2000), pp. V247-V252, Como, Italy.
• Chen K. and Chi H.S. (1999): On use of different feature sets for pattern classification: An alternative method. Proceedings of International Joint Conference on Neural Networks (IJCNN'99), pp. 2940-2945, Washington D. C., U.S.A.
• Chen K. and Wang D.L. (1999): Image segmentation based on a dynamically coupled neural oscillator network. International Joint Conference on Neural Networks (IJCNN'99), pp. 2653-2658, Washington D. C., U.S.A.
• Chen K. and Wang D.L. (1999): Perceiving without learning: from spirals to inside/outside relations. In Advances in Neural Information Processing Systems 11 (NIPS'98), pp. 10-16, MIT Press.
• Bao W.Q., Chen K., and Chi H.S. (1998): An HMM/MFNN hybrid architecture based on stacked generalization for speaker identification, Proceedings of IEEE World Congress on Computational Intelligence -- International Joint Conference on Neural Networks (WCCI'98-IJCNN'98), pp. 367-371, Anchorage, Alaska, U.S.A.
• Chen K. and Wang D.L. (1998): Perceiving spirals and inside/outside relations by a neural oscillator network. Proceedings of IEEE World Congress on Computational Intelligence -- International Joint Conference on Neural Networks (WCCI'98-IJCNN'98), pp. 619-624, Anchorage, Alaska, U.S.A.
• Wang L., Chen K., and Chi H.S. (1997): Methods of linear combination with different features. Proceedings of International Conference on Neural Information Processing (ICONIP-97), pp. 1088-1091, Springer-Velag, Dunedin/Queenstown, New Zealand.
• Chen K. and Chi H.S. (1997): A modified mixtures of experts architecture for classification with diverse features. Proceedings of IEEE International Conference on Neural Networks (ICNN-97), pp. 215-220, Houston, U.S.A.
• Chen K. and Chi H.S. (1996): A method of combining multiple classifiers with different features. Proceedings of International Conference on Neural Information Processing (ICONIP-96), pp. 1349-1354. (invited paper)
• Chen K., Yu X., and Chi H.S. (1996): Text-dependent speaker identification based on the modular tree: an empirical study. Proceedings of International Conference on Neural Information Processing (ICONIP-96), pp. 294-299, Springer-Verlag, Hong Kong.
• Chen K., Yu X., and Chi H.S. (1996): Classification by combining Fisher's linear discriminant with neural networks. Proceedings of Proceeding of World Congress on Neural Networks (WCNN-96), pp. 395-398, Elbaum, San Diego, U.S.A.
• Wang L., Chen K., and Chi H.S. (1996): Text-independent speaker identification by combining classifiers with different features. Proceedings of Proceeding of World Congress on Neural Networks (WCNN-96), pp. 59-62, Elbaum, San Diego, U.S.A.
• Chen K., Xie D.H., and Chi H.S. (1996): Speaker identification based on input/output HMMs. Proceeding of World Congress on Neural Networks (WCNN-96), pp. 37-40, San Diego, U.S.A.
• Chen K., Xie D.H., and Chi H.S. (1996): Combine multiple time-delay HMEs for speaker identification. Proceedings of IEEE International Conference on Neural Networks (ICNN-96), pp. 2015-2020, Washington D.C., U.S.A.
• Wu Z.Q., Chen K., Xiang B. and Chi H.S. (1995): A novel feature based on perceptual knowledge for speaker recognition. Proceedings of Proceedings of IEEE International Conference on Neural Networks and Signal Processing (ICNNSP-95), pp. I804-I807.
• Chen K., Bao W.Q., and Chi H.S. (1995): Speed up training of the recurrent neural networks using constrained optimization techniques. Proceedings of IEEE International Conference on Neural Networks and Signal Processing (ICNNSP-95), pp. I132-I135, Nanjing, China.
• Chen K., Xie D.H., and Chi H.S. (1995): Speaker identification based on the time-delay hierarchical mixture of experts. Proceedings of IEEE International Conference on Neural Networks (ICNN-95), pp. 2062-2066, Perth, Australia.
• Chen K., Yang L.P., Yu X., and Chi H.S. (1995): A self-architecture modular neural network. Proceedings of Proceedings of International Conference on Neural Information Processing (ICONIP-95), pp. II821-II824.
• Chen K., Xie D.H., and Chi H.S. (1995): Speaker identification using temporal HME. Proceedings of International Conference on Neural Information Processing (ICONIP-95), pp. II865-II868, Beijing, China.
• Chen K., Xie D.H., and Chi H.S. (1995): Speaker identification based on hierarchical mixture of experts. Proceedings of World Congress on Neural Networks (WCNN-95), pp. I493-I496, Elbaum, Washington D.C, U.S.A.
• Szu H.H., Zhong S., Xu, L., Shi Q.Y., Cheng M.T., Chen K., Chi H.S., Li C. (1995): Multiresolution wavelet techniques for noisy inverse-sensing problems. Proceedings of SPIE - The International Society for Optical Engineering, v 2491/1, pp. 481-489, Seattle, U.S.A.
• Chen K. and Ishikawa M. (1993): 3-D shape recovery by incorporating context--a connectionist approach. Proceedings of International Joint Conference of Neural Networks (IJCNN-93), pp. 1180-1183, Nagoya, Japan.
• Chen K. and Ishikawa M. (1993): A connectionist approach to subgraph isomorphism in attributed graphs. Proceeding of Japanese Symposium on Neural Networks, pp. 115-116, Iizuka, Japan.
• Chen K. (1992): A novel model of linear associative memory. In D.W. Ruck (ed.) Science of Artificial Neural Networks, SPIE Proceedings 1710, pp. 650-657.
• Chen K. (1992): A novel associative-memory based self-learning neurocontrol Model. In: S.K. Rogers (ed.), Applications of Artificial Neural Networks, SPIE Proceedings 1709, pp. 616-623.
• Chen K., Yu T., and Yan P.F. (1991): A novel model of associative memory with biorthogonal properties. Proceedings of International Joint Conference of Neural Networks (IJCNN-91), pp. 42-48. Singapore.
• Chen K. (1991): 3-D inference from 2-D image features in the perceptual-organization based computational visual model. Proceedings of International Symposium for Young Computer Scientists, pp. 552-560, Beijing, China.
• Chen K. and Li Z.R. (1990): Object models development tool to support image understanding s ystem. Proceedings of Graphics Interface, pp. 239-243, Halifax, Canada.
• Chen H.S. and Chen K. (1990): A model-directed image understanding system. Proceedings of The Third International Conference on Industrial and Engineering Applications of AI and Expert Systems, pp. 183-189, Charleston, U.S.A.
• Chen K. (1989): Support expert systems using fuzzy logic programming. Proceedings of International Symposium for Young Computer Professionals, pp. 258-264, Beijing, China.
• Chen K. and Li Z.R. (1989): Image understanding based on RBC theory. In Proceedings of The Third Pan Pacific Computer Conference, pp. 541-547, Beijing, China.

On-line Publication

• Chen K. (2005): On the dynamic pattern analysis, discovery and recognition. Feature Article, IEEE Systems, Man, and Cybernetics Society E-Newsletter, Issue 12, September 2005. ( [PDF])

Technical Report

• Wu L.S. and Chen K. (2023): Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning. Technical Report, Department of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:2311.17565).
• Wu L.S. and Chen K. (2022): Goal exploration augmentation via pre-trained skills for sparse-Reward long-horizon goal-conditioned reinforcement learning. Technical Report, Department of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:2210.16058).
• Murphy W. and Chen K. (2022): Univariate vs multivariate time series forecasting with transformers. Technical Report, Department of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from UoM-CS-TR2022).
• Wojtas M. and Chen K. (2020): Feature importance ranking for deep learning. Technical Report, Department of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:2010.08973).
• Woof W. and Chen K. (2020): A framework for end-to-end learning on semantic tree-structured data. Technical Report, Department of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:2002.05707).
• Zennaro F.M. and Chen K. (2019): Towards further understanding of sparse filtering via information bottleneck, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1910.08964).
• Chen K. (2019): Learning-based video game development in MLP@UoM: An overview. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1908.10127).
• Zhou H. and Chen K. (2018): Transferable positive/negative speech emotion recognition via class-wise adversarial domain adaptation. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1810.12782).
• Woof W. and Chen K. (2018): Learning to play general video-games via an object embedding network. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1803.05262).
• Wang Q. and Chen K. (2017): Multi-label zero-shot human action recognition via joint latent ranking embedding. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1706.09317).
• Wang Q. and Chen K. (2017): Alternative semantic representations for zero-shot human action recognition. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1706.09317).
• Rosyid H., Palmerlee M. and Chen K. (2016): Deploying learning materials to game content for serious education game development: A case study. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1608.01611).
• Zennaro F.M. and Chen K. (2016): On covariate shift adaptation via sparse filtering. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1607.06781).
• Wang Q. and Chen K. (2016): Zero-shot visual recognition via bidirectional latent embedding. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1607.02104).
• Sandouk U. and Chen K. (2016): Multi-label zero-shot learning via concept embedding. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1606.00282).
• Zennaro F.M. and Chen K. (2016): Towards understanding sparse filtering: A theoretical perspective. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1603.08831).
• Shi P. and Chen K. (2015): Learning constructive primitives for online level generation and real-time content adaptation in Super Mario Bros. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv:1510.07889).
• Sandouk U. and Chen K. (2015): Learning contextualized semantics from co-occurring terms via a Siamese architecture. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1506.05514).
• Sandouk U. and Chen K. (2015): Learning contextualized music semantics from tags via a Siamese network. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1504.07968).
• Buckley D., Chen K. and Knowles J. (2014): Rapid skill capture in a first-person shooter. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1411.1316).
• Madl T., Chen K., Montaldi D., and Trappl R. (2014): Computational cognitive models of spatial memory: A review. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Roberts J. and Chen K. (2013): Learning-based procedural content generation. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. (The technical report is available from arXiv 1308.6415, and the prototype is available from LBPCG-Quake.)
• Salman A. and Chen K. (2012): Extracting speaker-specific information with a deep neural architecture. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Chen K. and Salman A. (2010): Learning speaker-specific characteristics with a deep neural architecture. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Shaukat A. and Chen K. (2009): Towards discovering language-independent emotional acoustic features via feature selection. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. Available from arXiv 1009.0117
• Shaukat A. and Chen K. (2009): Emotional state categorization from speech: human vs. machine. Technical Report, School of Computer Science, The University of Manchester, United Kingdom. Available from arXiv 1009.0108
• Chen K. and S.H. Wang (2008): Semi-supervised learning via regularized boosting working on semi-supervised assumptions. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Yang Y. and Chen K. (2008): Temporal data clustering via weighted clustering ensemble networks with different representations. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Yang Y. and Chen K. (2007): Temporal data clustering via RPCL ensemble networks with different representations. Technical Report, School of Computer Science, The University of Manchester, United Kingdom.
• Chen K. (2003): Adaptive smoothing via contextual and local discontinuities. Technical Report, School of Computer Science, The University of Birmingham, United Kingdom.
• Chen K. (2003): On the use of different speech representations for speaker recognition: An alternative approach. Technical Report, School of Computer Science, The University of Birmingham, United Kingdom.
• Chen K. (2002): Personalise mobile access by speaker authentication. Technical Report, School of Computer Science, The University of Birmingham, United Kingdom.
• Chen K. (2001): Towards better making a decision in speaker verification. Technical Report, School of Computer Science, The University of Birmingham, United Kingdom.
• Chen K. (1999): A feature-perserving adaptive smoothing approach for early vision, Technical Report , National Laboratory of Machine Perception and The Center for Information Science, Peking University, Beijing, China.