Research

Projects

Past Students

Academic Service

Publications

Code

Vacancies

 

 

Dr. Tingting Mu (穆婷婷) Senior Lecturer (Associate Professor)   Department of Computer Science Kilburn Building University of Manchester Manchester, M13 9PL United Kingdom   Email: tingting.mu@manchester.ac.uk Phone: +44 (0)161 275 6169

 

 

I received a B.Eng. degree from the School of the Gifted Young, University of Science and Technology, China in 2004, and a Ph.D. from The University of Liverpool in 2008. I am a Senior Lecturer (Associate Professor) in Machine Learning at the University of Manchester (UoM), a Turing Fellow and an Honorary Research Fellow on Representation Learning at UoM Harwell. Before I joined UoM in 2016, I was a Lecturer in the Department of Electrical Engineering and Electronics at the University of Liverpool.

 

I am a machine learning researcher and my work focuses on mathematical modelling and optimisation techniques for: i) the development of AI solutions, and ii) the analysis of real-world complex data. For the former, I aim at constructing effective machine learning models to automate tasks such as matching, recognition, prediction, ranking, inference, and characterisation. For the latter, I develop algorithms that discover latent structure and extract information from large-scale, noisy and unstructured data. My general application interests include image, text, and speech data analysis and their associated practical AI solutions.

A particular focus of my work is representation learning, e.g., how to extract refined information from raw data and knowledge, and encode it in representation spaces for use in pattern recognition and prediction tasks. My team and I work on algorithm design and the theoretical understanding of a diverse range of representation learning methodologies, such as manifold learning, matrix factorisation, neural representation learning, etc.

 

Some currently active research directions I have engaged with over the years with my team and collaborators.

 

Data Visualisation (since 2015):

The goal is to enable the user to look at the data to facilitate understanding and data navigation. The most common way of “looking” at high-dimensional data is to embed it into a 1D, 2D or 3D space, but this inevitably compromises information content. The central research question is: what patterns and structures to preserve in such low-dimensional spaces and how to do it in an accurate and fast way.

See some of our work: X. Evangelopoulos, A. J. Brockmeier, T. Mu, J. Y. Goulermas, Circular object arrangement using spherical embeddings, Pattern Recognition, 103:107192, 2020. X. Evangelopoulos, A. J. Brockmeier, T. Mu, J. Y. Goulermas, Continuation methods for approximate large scale object sequencing, Machine Learning, 108(4):595-626, 2019. T. Mu, J. Y. Goulermas, S. Ananiadou, Data visualization with structural control of global cohort and local data neighborhoods, IEEE TPAMI, 40(6):1323-1337, 2018. J. Y. Goulermas, A. Kostopoulos, T. Mu, A new measure for analyzing and fusing sequences of objects, IEEE TPAMI, 38(5):833-848, 2015.

 

Relation Encoding (since 2012):

We are interested in a special type of data representing (directly or indirectly) relation information and measurements, e.g., distances, (dis)similarities, correlations, relations, links, interactions, graph and correspondence data. Such data occupies a vast portion of the information generated and recorded in our world today, through networks, rating preferences, knowledge bases, geometric locations, biological pathways, etc. We aim at developing algorithms which construct effective representations that encode the observed relations so that missing and new relations can be inferred. We are also interested in establishing a theoretical understanding of this type of data and algorithms.

See some of our work: T. Mu, J. Y. Goulermas, Provable Relation Factorisation, under preparation. A. J. Brockmeier, T. Mu, S. Ananiadou, J. Y. Goulermas, Quantifying the informativeness of similarity measurements, JMLR, 18(76):1-61, 2017. Y. Wu, T. Mu, J. Y. Goulermas, Translating on pairwise entity space for knowledge graph embedding, Neurocomputing, 260:411-419, 2017. Y. Wu, T. Mu, P. Liatsis, J. Y. Goulermas, Computation of heterogeneous object co-embeddings from relational measurements, Pattern Recognition, 65:146-163, 2017. T. Mu, J. Y. Goulermas, I. Korkontzelos, S. Ananiadou, Descriptive document clustering via discriminant learning in a co-embedded space of multi-level similarities, JASIST, 67(1):106-133, 2016. T. Mu, J. Y. Goulermas, Automatic generation of co-embeddings from relational data with adaptive shaping, IEEE TPAMI, 35(10):2340-2356, 2013.

 

High-dimensional Data Embedding (since 2009):

The goal here is to understand and learn embeddings and hidden representation spaces to encode high-dimensional data. We are investigating the invariant principles and unification of the overarching algorithmic formulations of the different approaches and establish theoretical understanding. We also develop neural networks as effective feature extractors to facilitate computer vision and natural language processing applications, addressing issues like insufficient data labelling, fusing data modalities, and model explainability.

See some of our work: Embedding and Dimensionality Reduction H. W. J. Reeve, T. Mu and G. Brown, Modular Dimensionality Reduction, ECML/PKDD, 2018. E. Rodriguez-Martinez, T. Mu, J. Jiang, and J. Y. Goulermas, Automated induction of heterogeneous proximity measures for supervised spectral embedding, IEEE TNNLS, 24(10):1575-1587, 2013. T. Mu, J. Jiang, Y. Wang and J. Y. Goulermas, Adaptive data embedding framework for multi-class classification, IEEE TNNLS, 23(8):1291-1303, 2012. T. Mu, J. Y. Goulermas, T. Tsujii and S. Ananiadou, Proximity-based frameworks for generating embeddings from multi-output data, IEEE TPAMI, 34(11):2216-2232, 2012. Computer Vision Applications X. Gao, T. Mu, J. Y. Goulermas, M. Wang, Improving image similarity learning by adding external memory, IEEE TKDE, early access, 2020. X. Gao, T. Mu, J. Y. Goulermas, J. Thiyagalingam, M. Wang, An interpretable deep architecture for similarity learning built upon hierarchical concepts, IEEE TIP, 29:3911-3926, 2020. X. Gao, T. Mu, J. Y. Goulermas, M. Wang, Attention driven multimodal similarity learning, Information Sciences, 432:530-542, 2018. Y. Hao, T. Mu, R. Hong, M. Wang, N. An, J. Y. Goulermas, Stochastic multi-view hashing for large-scale near-duplicate video retrieval, IEEE TM, 19(1):1-14, 2017. Natural Language Processing Applications Y. Hao, T. Mu, R. Hong. M. Wang, X. Liu, J. Y. Goulermas, Cross-domain sentiment encoding through stochastic word embedding, IEEE TKDE, 32(10): 1909 - 1922, 2019. D. Bollegala, T. Mu, J. Y. Goulermas, Cross-domain sentiment classification using sentiment sensitive embeddings, IEEE TKDE, 28(2):398-410, 2016. T. Mu, M. Miwa, T. Tsujii and S. Ananiadou, Discovering robust embeddings in (dis)similarity space for high-dimensional linguistic features, Computational Intelligence, 30(2): 285-315, 2014.

 

Knowledge-driven Machine Learning (since 2019):

The goal is to develop effective approaches to merge human knowledge with data-driven machine learning. In practice, annotated data is often limited, expensive to obtain and noisy. Data-driven machine learning models with complex architectures work in a black-box manner “unfriendly” to users. We have been working on reducing reliance on labels and improving model explainability, by fusing images and common sense and domain knowledge in representation spaces.

See some of our work: A. Sarullo, T. Mu. Zero-Shot Human-Object Interaction Recognition via Affordance Graphs, AAAI Workshop, 2021. M. Jayathilaka, T. Mu and U. Sattler, Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification, NeSy 2021.

 

 

Here are some new directions I have started to explore more recently:

 

Adversarial Robustness, Attack and Defence:

No matter how successful deep neural networks are, they are vulnerable to imperceptible perturbations calculated by adversarial attacks. We are interested in establishing provable relationships between the existence of adversarial attacks and the conditions imposed over data and models, and to develop effective defending algorithms.

 

Bias, Variance and Diversity:

This is a very classical topic exploring the generalisation of machine learning models by studying the principles of how models differ and average out under stochastic settings. I have recently joined this interesting direction, hoping to contribute to the underlying theory.

 

Hybrid Signal Processing and Machine Learning:

I have just started to explore the interesting direction of developing hybrid modelling strategies to merge the strength of machine learning and signal processing techniques, where image denoising is primarily used as our test platform.

 

·        2021-now: X-ray image denoising by machine learning and signal processing (with UoM Harwell and STFC, PDRA: Dr. S. Pinilla)

·        2021-now: Developing text retrieval and analysis tools to support tender scan (with Thornton and Lowe Ltd, PDRA: I. Tsantilas)

·        2020-now: Developing vulnerability detection tools in speech communication (with VoiceIQ Ltd, PDRA: Dr. X. Cui)

·        2021-now: Cross-modality generative models for large-scale scientific data (funded by STFC, PhD student: S. Jackson)

·        2020-now: Lipschitz constant estimation and regularisation for adversarial robustness (funded by EPSRC DTP, PhD student: Y. Sulehman)

·        2019-now: Differential geometry in machine learning (funded by CSC, PhD student: Y. Deng)

·        2018-now: Surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis (funded by EPSRC iCASE and EDF Energy, PhD student: H. Jones)

·        2018-now: Image understanding informed by ontological background knowledge (funded by CS Departmental studentship, PhD student: M. Jayathilaka)

·        2017-now: Cohort data visualisation informed by ordinal information (funded by CS Departmental studentship, PhD student: R. Qin)

 

·       2021, Dr. A. Sarullo on zero-shot learning of human-object interactions through common-sense knowledge (primary supervisor).

·       2021, Dr. M. Li on graphical and deep learning models for natural language labelling tasks with multiple annotators (co-supervisor).

·       2018, Dr. J. Wu on sentence matching for question answering with neural networks (primary supervisor).

·       2017, Dr. Y. Wu on embedding approach for relational data (primary supervisor).

·       2017, Dr. Y. Hao on near-duplicate video retrieval and cross-domain sentiment classification based on embedding learning (primary UK supervisor, visiting PhD).

·       2017, Dr. X. Gao on Multi-modal similarity learning (primary UK supervisor, visiting PhD).

·       2014, Dr. L. Gong on nonnegative matrix analysis for data clustering and compression (primary supervisor).

·       2014, Dr. C. Wei on advanced modelling and feature extraction for fault diagnosis of power apparatus (co-supervisor).

 

·       Associate Editor, IEEE Transactions on Neural Networks and Learning Systems, 2020-present.

·       Associate Editor, Neurocomputing, 2014-present.

·       Program Committee Member: AAAI, IJCAI, ECML, NAACL-HLT, ACL, EMNLP, and more.

·       Journal Reviewer for IEEE TPAMI, TNNLS, TIP, TKDE, Pattern Recognition, and more.

 

Also, in Google Scholar & DBLP

 

Journal publications:

1.     X. Gao, Z. Zhang, T. Mu, X. Zhang, C. Cui and M. Wang, Self-attention driven adversarial similarity learning network, Pattern Recognition, 105:107331, 2020. [Link]

2.     X. Evangelopoulos, A. J. Brockmeier, T. Mu and J. Y. Goulermas, Circular object arrangement using spherical embeddings, Pattern Recognition, 103:107192, 2020. [Link]

3.     J. Wu, T. Mu, J. Thiyagalingam, and J. Y. Goulermas, Building interactive sentence-aware representation based on generative language model for community question answering, Neurocomputing, 389:93-107, 2020. [Link]

4.     X. Gao, T. Mu, J. Y. Goulermas, J. Thiyagalingam and M. Wang, An interpretable deep architecture for similarity learning built upon hierarchical concepts, IEEE Trans. on Image Processing, 29:3911-3926, 2020. [Link]

5.     H. Ma, Z. Qian, T. Mu and S. Shi, Fast and accurate 3D measurement based on light-field camera and deep learning, Sensors, 19(20):4399, 2019. [Link]

6.     Y. Hao, T. Mu, R. Hong. M. Wang, X. Liu, J. Y. Goulermas, Cross-domain sentiment encoding through stochastic word embedding, IEEE Trans. on Knowledge and Data Engineering, 32(10): 1909-1922, 2020. [Link]

7.     X. Evangelopoulos, A. J. Brockmeier, T. Mu, J. Y. Goulermas, Continuation methods for approximate large scale object sequencing, Machine Learning, 108(4)-595-626, 2019. [Link]

8.     A. J. Brokmeier, T. Mu, S. Ananiadou and J. Y. Goulermas, Self-tuned descriptive document clustering using a predictive network, IEEE Trans. on Knowledge and Data Engineering, 30(10):1929-1942 2018. [Link]

9.     W. Fu, M. Wang, S. Hao and T. Mu, FLAG: Faster learning on anchor graph with label predictor optimization, IEEE Trans. on Big Data, early access, 2017. [Link]

10.  X. Gao, T. Mu, J. Y. Goulermas and M. Wang, Attention driven multimodal similarity learning, Information Sciences, 432:530-542, 2018. [Link]

11.  T. Mu, J. Y. Goulermas and S. Ananiadou, Data visualization with structural control of global cohort and local data neighbourhoods, IEEE Trans on Pattern Analysis and Machine Intelligence, 40(6): 1323-1337, 2018. [Link]

12.  X. Gao, T. Mu, J. Y. Goulermas and M. Wang, Topic driven multimodal similarity learning with multi-view voted convolutional features, Pattern Recognition, 75:223-234, 2018. [Link]

13.  L. Gong, T. Mu, M. Wang, H. Liu and J. Y. Goulermas, Evolutionary nonnegative matrix factorization with adaptive control of cluster quality, Neurocomputing, 272:237-249, 2018. [Link]

14.  A. J. Brokmeier, T. Mu, S. Ananiadou and J. Y. Goulermas, Quantifying the informativeness of similarity measurements, Journal of Machine Learning Research, 18(76):1−61, 2017. [Link]

15.  Y. Hao, T. Mu, J. Y. Goulermas, R. Hong, N. An and M. Wang, Unsupervised t-distributed video hashing and its deep extension, IEEE Trans. on Image Processing, 26(11):5531-5544, 2017. [Link]

16.  G. Kontonatsios, A. J. Brockmeier, P. Przybyła, J. McNaught, T. Mu, J. Y. Goulermas and S. Ananiadou, A semi-supervised approach using label propagation to support citation screening, Journal of Biomedical Informatics, 72:67-76, 2017. [Link]

17.  Y. Wu, T. Mu and J. Y. Goulermas, Translating on pairwise entity space for knowledge graph embedding, Neurocomputing, 260:411-419, 2017. [Link]

18.  Y. Wu, T. Mu, P Liatsis and J. Y. Goulermas, Computation of heterogeneous object co-embeddings from relational measurements, Pattern Recognition, 65:146-163, 2017. [Link]

19.  Y. Hao, T. Mu, R. Hong, M. Wang, N. An and J. Y. Goulermas, Stochastic multi-view hashing for large-scale near-duplicate video retrieval, IEEE Trans. on Multimedia, 19(1):1-14, 2017. [Link]

20.  D. Bollegala, T. Mu, J. Y. Goulermas, Cross-domain sentiment classification using sentiment sensitive embeddings, IEEE Trans. on Knowledge and Data Engineering, 28(2):398-410, 2016. [Link]

21.  X. Gao, T. Mu and M. Wang, Local voting based multi-view embedding, Neurocomputing, 171:901-909, 2016. [Link]

22.  T. Mu, J. Y. Goulermas, I. Korkontzelos and S. Ananiadou, Descriptive document clustering via discriminant learning in a co-embedded space of multi-level similarities, Journal of the Association for Information Science and Technology, 67(1):106-133, 2016. [Link]

23.  J. Y. Goulermas, A. Kostopoulos and T. Mu, A new measure for analyzing and fusing sequences of objects, IEEE Trans. on Pattern Analysis and Machine Intelligence, 38(5): 833-848, 2016. [Link]

24.  E. Rodriguez-Martinez, T. Mu and J. Y. Goulermas, Sequential projection pursuit with kernel matrix update and symbolic model selection, IEEE Trans. on Cybernetics, 44(12):2458 - 2469, 2014. [Link]

25.  K. Nikolaidis, T. Mu and J. Y. Goulermas, Prototype reduction based on direct weighted pruning, Pattern Recognition Letters, 36:22-28, 2014. [Link]

26.  T. Mu, M. Miwa, T. Tsujii and S. Ananiadou, Discovering robust embeddings in (dis)similarity space for high-dimensional linguistic features, Computational Intelligence, 30(2): 285-315, 2014. [Link]

27.  Y. Wang, J. Jiang and T. Mu, Context-aware and energy-driven route optimization for fully electric vehicles, IEEE Trans. on Intelligent Transportation Systems, 14(3):1331-1345, 2013. [Link]

28.  E. Rodriguez-Martinez, T. Mu, J. Jiang, and J. Y. Goulermas, Automated induction of heterogeneous proximity measures for supervised spectral embedding, IEEE Trans. on Neural Networks and Learning Systems, 24(10):1575-1587, 2013. [Link]

29.  T. Mu and J. Y. Goulermas, Automatic generation of co-embeddings from relational data with adaptive shaping, IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(10):2340-2356, 2013. [Link]

30.  T. Mu, J. Jiang and Y. Wang, Heterogeneous delay embeddings for travel time and energy cost prediction via regression analysis, IEEE Trans. on Intelligent Transportation Systems, 14(1):214-224, 2013. [Link]

31.  T. Mu, J. Jiang, Y. Wang and J. Y. Goulermas, Adaptive data embedding framework for multi-class classification, IEEE Trans. on Neural Networks and Learning Systems, 23(8):1291-1303, 2012. [Link]

32.  T. Mu, J. Y. Goulermas, T. Tsujii and S. Ananiadou, Proximity-based frameworks for generating embeddings from multi-output data, IEEE Trans. on Pattern Analysis and Machine Intelligence, 34(11):2216-2232, 2012. [Link]

33.  Y. Korkontzelos, T. Mu and S. Ananiadou, ASCOT: A text mining-based web-service for efficient search and assisted creation of clinical trials, BMC Medical Informatics and Decision Making, 12 (Suppl 1):S3, 2012. [Link]

34.  E. Romero, T. Mu and P. J. G. Lisboa, Cohort-based kernel visualisation with scatter matrices, Pattern Recognition, 45:1436-1454, 2012. [Link]

35.  T. C. Pataky, T. Mu, K. Bosch, D. Rosenbaum and J. Y. Goulermas, Gait recognition: highly unique dynamic plantar pressure patterns amongst 104 individuals, Journal of the Royal Society Interface, 9(69):790-800, 2012. [Link]

36.  E. Rodriguez-Martinez, K. Nikolaidis, T. Mu, J. Y. Goulermas and J. F. Ralph, Towards collaborative feature extraction for face recognition, Natural Computing, 11(3):395-404, 2012. [Link]

37.  T. C. Pataky, K. Bosch, T. Mu, N. L. W. Keijsers, B. Segers, D. Rosenbaum and J. Y. Goulermas, An anatomically unbiased foot template for inter-subject plantar pressure evaluation, Gait & Posture, 33:418-422, 2011. [Link]

38.  E. Rodriguez-Martinez, J. Y. Goulermas, T. Mu and J. F. Ralph, Automatic induction of projection pursuit indices, IEEE Trans. on Neural Networks, 21(8):1281-1295, 2010. [Link]

39.  S. Ananiadou, P. Thompson, J. Thomas, T. Mu, S. Oliver, M. Rickinson, Y. Sasaki, D. Weissenbacher and J. McNaught, Supporting the education evidence portal via text mining, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Science, 368(1925):3829-3844, 2010. [Link]

40.  T. Mu, T. C. Pataky, A. H. Findlow, M. S. H. Aung and J. Y. Goulermas, Automated nonlinear feature generation and classification of foot pressure lesions, IEEE Trans. on Information Technology in Biomedicine, 14(2):418-424, 2010. [Link]

41.  T. Mu and A. K. Nandi, Multi-class classification based on extended support vector data description, IEEE Trans. on Systems, Man and Cybernetics - Part B, 39(5):1206-1216, 2009. [Link]

42.  T. Mu and A. K. Nandi, Automatic tuning of L2-SVM parameters employing the extended Kalman filter, Expert Systems, 26(2):160-175, 2009. [Link]

43.  T. Mu, A. K. Nandi and R. M. Rangayyan, Screening of knee-joint vibroarthrographic signals using the strict 2-surface proximal classifier and genetic algorithm, Computers in Biology and Medicine, 38(10):1103-1111, 2008. [Link]

44.  T. Mu, A. K. Nandi and R. M. Rangayyan, Classification of breast masses using selected shape, edge-sharpness and texture features with linear and kernel-based classifiers, Journal of Digital Imaging, 21(2):153-169, 2008. [Link]

45.  T. Mu, A. K. Nandi and R. M. Rangayyan, Analysis of breast tumours in mammograms using the pairwise Rayleigh quotient classifier, Journal of Electronic Imaging, 16(4):043004:1-11, 2007. [Link]

46.  T. Mu, A. K. Nandi and R. M. Rangayyan, Classification of breast masses via nonlinear transformation of features based on a kernel matrix, Medical and Biological Engineering and Computing, 45(8):769-780, 2007. [Link]

47.  T. Mu and A. K. Nandi, Breast cancer detection from FNA using SVM with different parameter tuning systems and SOM-RBF classifier, Journal of the Franklin Institute - Engineering and Applied Mathematics, 344(3-4):285-311, 2006. [Link]

 

Conference publications:

1.     X. Cui, A. Gamage, T. Hanley and T. Mu, Identifying indicators of vulnerability from short speech segments using acoustic and textual features. Proc. Interspeech, 2021. [Link]

2.     M. Jayathilaka, T. Mu and U. Sattler, Ontology-based 𝑛-ball concept embeddings informing few-shot image classification, NeSy’2021. [Link]

3.     A. Sarullo and T. Mu. Zero-shot human-object interaction recognition via affordance graphs, AAAI Workshop on Common Sense Knowledge Graphs, 2021. [Link]

4.     A. Sarullo and T. Mu, On class imbalance and background filtering in visual relationship detection, International Joint Conference on Neural Networks, Budapest, Hungary, IJCNN, 2019. [Link]

5.     M. Li, A. F. Myrman, T. Mu and S. Ananiadou, Modelling instance-level annotator reliability for natural language labelling tasks, Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, Minneapolis, USA, 2019. [Link]

6.     H. Reeve, T. Mu and G. Brown, Modular Dimensionality Reduction, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD, Dublin, Ireland, 2018. [Link]

7.     X. Evangelopoulos, A. J. Brockmeier, T. Mu and J. Y. Goulermas, A graduated non-convexity relaxation for large scale seriation, SIAM International Conference on Data Mining, Houston, Texas, USA, 2017. [Link]

8.     M. Sato, A. J. Brockmeier, G. Kontonatsios, T. Mu, J. Y. Goulermas, J. Tsujii, S. Ananiadou, Distributed document and phrase co-embeddings for descriptive clustering, European Chapter of the Association for Computational Linguistics, EACL, Valencia, Spain, 2017. [Link]

9.     L. Gong, T. Mu, and J. Y. Goulermas, Evolutionary nonnegative matrix factorization for data compression, International Conference on Intelligent Computing, ICIC, 2015. [Link]

10.  M. Tufail, F. Coenen and T. Mu, Mining movement patterns from video data to inform multi agent based simulation, 10th International Workshop on Agents and Data Mining Interaction, ADMI, 2014. [Link]

11.  Y. Korkontzelos, T. Mu, A. Restificar and S. Ananiadou, Text mining for efficient search and assisted creation of clinical trials, ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO’11, Glasgow, Scotland, UK, 2011. [Link]

12.  T. Mu, J. Tsujii and S. Ananiadou, Proximity-based graph embeddings for multi-label-classification, Int’l Conference on Knowledge Discovery and Information Retrieval, KDIR, Valencia, Spain, 2010. [Link]

13.  T. Mu, X. Wang, J. Tsujii and S. Ananiadou, Imbalanced classification using dictionary-based prototypes and hierarchical decision rules for entity sense disambiguation, the 23rd Int’l Conference on Computational Linguistics, Coling, Beijing, China, 2010. [Link]

14.  E. Romero, A. S. Fernandes, T. Mu and P. J.G. Lisboa, Cohort-based kernel visualisation with scatter matrices, Int’l Joint Conference on Neural Networks, IJCNN, Barcelona, Spain, 2010. [Link]

15.  T. Mu and A. K. Nandi, Breast cancer diagnosis and prognosis using different kernel-based classifiers, Int'l Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS, pp. 342-348, Funchal, Madeira, Portugal, 2008. [Link]

16.  T. Mu and A. K. Nandi and R. M. Rangayyan, Breast cancer diagnosis from fine-needle aspiration using supervised compact hyperspheres and establishment of confidence of malignancy, the 16th European Signal Processing Conference, EUSIPCO, Lausanne, Switzerland, 2008. [Link]

17.  T. Mu, A. K. Nandi and R. M. Rangayyan, Strict 2-surface proximal classification of knee-joint vibroarthrographic signals, the 29th Annual Int’l Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pp. 4911-4914, Lyon, France, 2007. [Link]

18.  T. Mu and A. K. Nandi, A proximal classification method based on two smallest and supervised hyperspheres, the IEEE Int'l Workshop on Machine Learning for Signal Processing, MLSP, pp. 63-68, Thessaloniki, Greece, 2007. [Link]

19.  T. Mu, A. K. Nandi and R. M. Rangayyan, Strict 2-surface proximal classifier with application to breast cancer detection in mammograms, the 32nd Int'l Conference on Acoustics, Speech and Signal Processing, ICASSP, 2:477-480, Hawaii, USA, 2007. [Link]

20.  T. Mu, A. K. Nandi and R. M. Rangayyan, Pairwise Rayleigh quotient classifier with application to the analysis of breast tumors, the 4th IASTED Int'l Conference on Signal Processing, Pattern Recognition and Applications, SPPRA, pp. 356-361, Innsbruck, Austria, 2007. [Link]

21.  T. Mu, A. K. Nandi and R. M. Rangayyan, Classification of breast masses via transformation of features using kernel principal component analysis, the 5th IASTED Int'l Conference on Biomedical Engineering, BioMED, pp. 396-401, Innsbruck, Austria, 2007. [Link]

22.  T. Mu and A. K. Nandi, EKF based multiple parameter tuning system for a L2-SVM classifier, the IEEE Int'l Workshop on Machine Learning for Signal Processing, MLSP, 229-233, Maynooth, Ireland, 2006. [Link]

23.   T. Mu and A. K. Nandi, Detection of breast cancer using v-SVM and RBF networks with self organized selection of centers, In Proc. of the 3rd IEE Int'l Seminar on Medical Applications of Signal Processing, MASP, pp.47-52, London, UK, 2005. [Link]

 

 

 

 

·         Informativeness code from “AJ Brockmeier, T Mu, S Ananiadou, JY Goulermas, Quantifying the informativeness of similarity measurements, Journal of Machine Learning Research, vol.18(76), pp.1-61, 2017” ·         Video Hashing code from “Y Hao, T Mu, R Hong, M Wang, N An and JY Goulermas, Stochastic multi-view hashing for large-scale near-duplicate video retrieval, IEEE Trans. on Multimedia, 19(1):1-14, 2017.” ·        Seriation toolbox used in “JY Goulermas, A Kostopoulos, T Mu, A new measure for analyzing and fusing sequences of objects, IEEE Trans. Pattern Analysis and Machine Intelligence, vol.38(5), pp.833-848, 2016” ·        ACAS code from “T Mu, JY Goulermas, Automatic generation of co-embeddings from relational data with adaptive shaping, IEEE Trans. Pattern Analysis and Machine Intelligence, vol.35(10), p.2340-2356, 2013” ·        SEHP code from “E Rodriguez-Martinez, T Mu, J Jiang, JY Goulermas, Automated induction of heterogeneous proximity measures for supervised spectral embedding, IEEE Trans. Neural Networks, vol.24(10), pp.1575-1587, 2013” ·        MESD/MOPE code from “T Mu, JY Goulermas, J Tsujii, S Ananiadou, Proximity-based frameworks for generating embeddings from multi-output data, IEEE Trans. Pattern Analysis and Machine Intelligence, vol.34(11), pp.2216-2232, 2012” ·         DEFC code from “T Mu, J Jiang, Y Wang, JY Goulermas, An adaptive data embedding framework for multi-class classification, IEEE Trans. Neural Networks, vol.23(8), pp.1291-1303, 2012”

 

 

 

I welcome PhD applications all around the year from people with strong technical (i.e., mathematical & programming) skills and even stronger commitment. PhD applicants can apply to work in these two areas (but other interesting-only areas are welcome!):

·         Representation Learning and its Applications (here)

·         Machine Learning for Vision and Language Understanding (here)

Competition-based PhD funding opportunities are also available (here).

Post-doctoral research posts as well as externally funded PhD positions will be advertised when a vacancy becomes available.