Tomas Horvath
tomas horvath

Dr Tomas Horvath

  

Biography

Dr. Tomáš Horváth received his MSc and PhD degrees at the Pavol Jozef Šafárik University in Košice, Slovakia, in 2002 and 2008, respectively, in the area of relational learning. Since 2004, he is a the member of the faculty of the Institute of Computer Science of the Faculty of Science at this university. He was on a post-doc internship at the Information Systems and Machine Learning lab of the University in Hildesheim, Germany, from 2009 to 2012 where he was working in the area of recommender systems with applications in education. From 2015 to 2016 he received a post-doc grant at the Department of Computer Science, University of São Paulo in São Carlos, Brazil, where he started to work on automated machine learning with focus on hyper-parameter learning. From 2016 until 2024, he was working as an associate professor at the Faculty of Informatics at the Eötvös Loránd University in Budapest, Hungary where he built the Department of Data Science and Engineering of which he was the head of for more than 6 years. He was continuing to work on automated working on automated machine learning and started to work on applied machine learning for the agriculture domain. From 2024 he is a professor of artificial intelligence at the Edinburgh Napier University, Scotland, UK.

His research interests include relational and rule-based learning, pattern mining, recommender systems, automated machine learning and precision farming.

School

Research Groups

Themes

Esteem

Advisory panels and expert committees or witness

  • Steering Committee Member of the European Conference on Advances in Databases and Information Systems
  • Steering committee member of the Conference Information technologies -- Applications and Theory

 

Editorial Activity

  • Associate Editor of the International Journal of Intelligent Data Analysis

 

Fellowships and Awards

  • Best Paper Award at the 22nd International Conference on Intelligent Data Engineering and Automated Learning, Manchester, UK
  • Best Student Paper Award of the 11thInternational Conference on Computer Supported Education, Noordwijkerhout, The Netherlands
  • Best Student Paper Award of the 3rd International Conference on Computer Supported Education, Noordwijkerhout, The Netherlands

 

Invited Speaker

  • Invited lecture on the 3rd Seminar on Digital Agriculture, Osijek, Croatia
  • Invited lecture on the 4th Seminar on Digital Agriculture, Osijek, Croatia
  • Invited talk at the conference Dáta a Znalosti & WIKT, Košice, Slovak Republik
  • Invited talk at the Machine Learning Meetup in, Košice, Slovakia
  • Invited lecture at the Summer School on Autonomous Driving at University of Maribor, Slovenia
  • Invited talk at Charles University in Prague, Czech Republic
  • Tutorial at the conference Znalosti, Mikulov, Czech Republic
  • Invited lecture at University of Malaga, Spain

 

Filter by

Date


36 results

Denoising Architecture for Unsupervised Anomaly Detection in Time-Series

Conference Proceeding
Skaf, W., & Horváth, T. (2022)
Denoising Architecture for Unsupervised Anomaly Detection in Time-Series. In S. Chiusano, T. Cerquitelli, R. Wrembel, K. Nørvåg, B. Catania, G. Vargas-Solar, & E. Zumpano (Eds.), New Trends in Database and Information Systems: ADBIS 2022 Short Papers, Doctoral Consortium and Workshops: DOING, K-GALS, MADEISD, MegaData, SWODCH, Turin, Italy, September 5–8, 2022, Proceedings (178-187). https://doi.org/10.1007/978-3-031-15743-1_17
Anomalies in time-series provide insights of critical scenarios across a range of industries, from banking and aerospace to information technology, security, and medicine. How...

Directed Undersampling Using Active Learning for Particle Identification

Conference Proceeding
Farou, Z., Ouaari, S., Domian, B., & Horváth, T. (2022)
Directed Undersampling Using Active Learning for Particle Identification. In P. Kumar Singh, Y. Singh, J. Kumar Chhabra, Z. Illés, & C. Verma (Eds.), Recent Innovations in Computing: Proceedings of ICRIC 2021, Volume 2 (149-162). https://doi.org/10.1007/978-981-16-8892-8_12

Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed

Book Chapter
Alexy, M., & Horváth, T. Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed. In Tracing the Domestic Pig. IntechOpen. https://doi.org/10.5772/intechopen.101615

)
Alexy, M., & Horváth, T. Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed. In Tracing the Domestic Pig. IntechOpen. https://doi.org/10.5772/intechopen.101615
Pig farming is largely characterized by closed, large-scale housing technology. These systems are driven by resource efficiency. In intensive technologies, humans control almo...

Migrating Models: A Decentralized View on Federated Learning

Conference Proceeding
Kiss, P., & Horváth, T. (2021)
Migrating Models: A Decentralized View on Federated Learning. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part I (177-191). https://doi.org/10.1007/978-3-030-93736-2_15
Federated learning (FL) researches attempt to alleviate the increasing difficulty of training machine learning models, when the training data is generated in a massively distr...

Time-Series in Hyper-parameter Initialization of Machine Learning Techniques

Conference Proceeding
Horváth, T., Mantovani, R. G., & de Carvalho, A. C. P. L. F. (2021)
Time-Series in Hyper-parameter Initialization of Machine Learning Techniques. In Intelligent Data Engineering and Automated Learning – IDEAL 2021: 22nd International Conference, IDEAL 2021, Manchester, UK, November 25–27, 2021, Proceedings (246-258). https://doi.org/10.1007/978-3-030-91608-4_25
Initializing the hyper-parameters (HPs) of machine learning (ML) techniques became an important step in the area of automated ML (AutoML). The main premise in HP initializatio...

Linear Concept Approximation for Multilingual Document Recommendation

Book Chapter
Salamon, V. T., Tashu, T. M., & Horváth, T. (2021)
Linear Concept Approximation for Multilingual Document Recommendation. . Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-91608-4_15
In this paper, we proposed Linear Concept Approximation, a novel multilingual document representation approach for the task of multilingual document representation and recomme...

Multimodal Emotion Recognition from Art Using Sequential Co-Attention

Journal Article
Tashu, T. M., Hajiyeva, S., & Horvath, T. (2021)
Multimodal Emotion Recognition from Art Using Sequential Co-Attention. Journal of Imaging, 7(8), Article 157. https://doi.org/10.3390/jimaging7080157
In this study, we present a multimodal emotion recognition architecture that uses both feature-level attention (sequential co-attention) and modality attention (weighted modal...

Attention-Based Multi-modal Emotion Recognition from Art

Conference Proceeding
Tashu, T. M., & Horváth, T. (2021)
Attention-Based Multi-modal Emotion Recognition from Art. In Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021, Proceedings, Part III (604-612). https://doi.org/10.1007/978-3-030-68796-0_43
Emotions are very important in dealing with human decisions, interactions, and cognitive processes. Art is an imaginative human creation that should be appreciated, thought-pr...

A Novel Evaluation Metric for Synthetic Data Generation

Conference Proceeding
Galloni, A., Lendák, I., & Horváth, T. (2020)
A Novel Evaluation Metric for Synthetic Data Generation. In Intelligent Data Engineering and Automated Learning – IDEAL 2020: 21st International Conference, Guimaraes, Portugal, November 4–6, 2020, Proceedings, Part II (25-34). https://doi.org/10.1007/978-3-030-62365-4_3
Differentially private algorithmic synthetic data generation (SDG) solutions take input datasets Dp consisting of sensitive, private data and generate synthetic data Ds with s...

Data Generation Using Gene Expression Generator

Conference Proceeding
Generative adversarial networks (GANs) could be used efficiently for image and video generation when labeled training data is available in bulk. In general, building a good ma...