The Romanian Institute of Science and Technology has a strong focus on basic and applied research in machine learning and artificial intelligence (AI).
Research topics included:
- developing technologies for program synthesis or induction, using deep learning and other machine learning methods, with a focus on the automated development of web pages;
- deep learning for processing medical images;
- object reconstruction with deep learning, with a focus on museum artifacts;
- new learning rules for spiking neural networks; components of such a learning rule have been implemented in Intel’s Loihi neuromorphic chip.
We welcome collaborations with companies where we can apply our know-how in deep learning and other machine learning methods. Contact us to discuss about this.
Our know-how in deep learning can be broadly applied in a large variety of fields. Some examples of topics we approached are:
- automated generation of web pages;
- detecting tumors in brain scans;
- detecting anomalies in heart sounds;
- segmenting ultrasound images for periodontal investigations;
- detecting spinocerebellar ataxia type 2 in electrooculogram signals;
- defending against adversarial attacks in image classification, e.g. of traffic signs;
- text analysis, e.g. sentiment detection.
Scientific publications in artificial intelligence & machine learning
- N. Bacanin, C. Stoean, D. Markovic, M. Zivkovic, T. A. Rashid, A. Chhabra, & M. Sarac. (2024)Multimedia Tools and Applications, 83(31), 76035-76075.
- R. Stoean, N. Bacanin, C. Stoean, & L. Ionescu. (2024)Journal of Cultural Heritage, 69, 18-26.
- A. Ungureanu, A. – S. Marcu, C. L. Patru, D. Ruican, R. Nagy, R. Stoean, …. (2023)BMC Pregnancy and Childbirth, 23(1), 20.
- C. Stoean, N. Bacanin, R. Stoean, L. Ionescu, A. – M. Gărău, & C. – C. Ghiţescu. (2023)In 2023 25th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) (p. 266-273).
- Study on Semantic Inpainting Deep Learning Models for Artefacts with Traditional MotifsC. Stoean, N. Bacanin, Z. Volkovich, L. Ionescu, & R. Stoean. (2023)In I. Rojas, G. Joya, & A. Catala (Eds.), Advances in Computational Intelligence (p. 479-490)Cham: Springer Nature Switzerland.
- Automatic Control of Class Weights in the Semantic Segmentation of Corrosion Compounds on Archaeological ArtefactsR. Stoean, P. G. Báez, C. P. S. Araujo, N. Bacanin, M. Atencia, & C. Stoean. (2023)In I. Rojas, G. Joya, & A. Catala (Eds.), Advances in Computational Intelligence (p. 467-478)Cham: Springer Nature Switzerland.
- OF-AE: Oblique Forest AutoEncodersC. D. Alecsa. (2023)In I. Maglogiannis, L. Iliadis, J. MacIntyre, & M. Dominguez (Eds.), Artificial Intelligence Applications and Innovations (p. 207-219)Cham: Springer Nature Switzerland.
- R. Stoean, N. Bacanin, C. Stoean, L. Ionescu, M. Atencia, & G. Joya. (2023)Journal of Cultural Heritage, 64, 198-206.
- C. Cano-Domingo, R. Stoean, G. Joya, N. Novas, M. Fernandez-Ros, & J. A. Gazquez. (2023)Measurement, 208, 112426.
- C. Stoean, N. Bacanin, W. Paja, R. Stoean, D. Iliescu, C. Patru, & R. Nagy. (2022)Procedia Computer Science, 207, 3085-3092.
- C. Stoean, N. Bacanin, R. Stoean, L. Ionescu, C. Alecsa, M. Hotoleanu, …. (2022)In 2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) (p. 276-283).
- N. Bacanin, C. Stoean, M. Zivkovic, D. Jovanovic, M. Antonijevic, & D. Mladenovic. (2022)Sensors, 22(11).
- R. Stoean, N. Bacanin, L. Ionescu, C. Stoean, M. Boicea, A. – M. Garau, & C. – C. Ghitescu. (2022)Procedia Computer Science, 207, 1303-1311.
- A. Davody, M. Safari, & R. V. Florian. (2022)Neurocomputing, 489, 323-332.
- D. G. Iliescu, R. D. Nagy, C. Patru, C. Stoean, R. Stoean, & A. Marcu. (2021)Ultrasound in Obstetrics & Gynecology, 58.
- C. Stoean, R. Stoean, M. Hotoleanu, D. Iliescu, C. Patru, & R. Nagy. (2021)In 2021 25th International Conference on System Theory, Control and Computing (ICSTCC) (p. 242-248).
- R. Stoean, D. Iliescu, C. Stoean, V. Ilie, C. Patru, M. Hotoleanu, …. (2021)In I. Rojas, G. Joya, & A. Català (Eds.), Advances in Computational Intelligence (p. 3-14)Cham: Springer International Publishing.
- R. Stoean, N. Bacanin, L. Ionescu, M. Boicea, A. – M. Gărău, & C. – C. Ghiţescu. (2021)In 2021 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) (p. 246-251).
- Artificial intelligence can “see” the chemical composition of archaeological objects before restorationR. Stoean, L. Ionescu, C. Stoean, M. Boicea, A. – M. Gărău, & C. – C. Ghițescu. (2021)In 8th International Conference on Matter and Materials in/for Heritage Conservation (MATCONS) (p. 279-287).
- A Convolutional Neural Network as a Proxy for the XRF Approximation of the Chemical Composition of Archaeological Artefacts in the Presence of Inter-microscope VariabilityC. Stoean, L. Ionescu, R. Stoean, M. Boicea, M. Atencia, & G. Joya. (2021)In I. Rojas, G. Joya, & A. Català (Eds.), Advances in Computational Intelligence (p. 260-271)Cham: Springer International Publishing.
- R. Stoean, L. Ionescu, C. Stoean, M. Boicea, M. Atencia, & G. Joya. (2021)Procedia Computer Science, 192, 2002-2011.
- R. Volpi, U. Thakur, & L. Malagò. (2021)Entropy, 23(3), 287.
- R. Stoean, C. Stoean, M. Atencia, R. Rodríguez-Labrada, & G. Joya. (2020)Mathematics, 8(7).
- C. Várady, R. Volpi, L. Malagò, & N. Ay. (2020)arXiv:2008.06687.
- H. J. Hortúa, L. Malagò, & R. Volpi. (2020)In ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning.
- R. Volpi, & L. Malagò. (2020)In 5th Workshop on Representation Learning for NLP .
- A. Albu, A. Enescu, & L. Malagò. (2020)In 2020 KDD Workshop on Applied Data Science for Healthcare.
- H. J. Hortúa, R. Volpi, & L. Malagò. (2020)In ICLR 2020 Fundamental Science in the era of AI .
- N. Uțiu. (2020)In Bridge between perception and reasoning: Graph neural networks and beyond – ICML 2020 workshop.
- C. Ivan, & R. V. Florian. (2020)arXiv:2006.16627.
- C. Stoean, R. Stoean, M. Atencia, M. Abdar, L. Velázquez-Pérez, A. Khosravi, …. (2020)Sensors, 20(11), 3032.
- A. I. Albu, A. Enescu, & L. Malagò. (2020)In Proceedings of the Northern Lights Deep Learning WorkshopTromsø, Norway: Septentrio Academic Publishing.
- P. Hlihor, R. Volpi, & L. Malagò. (2020)In Proceedings of the Northern Lights Deep Learning WorkshopTromsø, Norway: Proceedings of the Northern Lights Deep Learning Workshop.
- C. D. Alecsa, T. Pința, & I. Boros. (2020)Neural Networks, 126, 178-190.
- C. Stoean, W. Paja, R. Stoean, & A. Săndiță. (2019)PLOS One, 14(10), e0223593.
- A. Davody. (2019)In Reinforcement Learning for Real Life ICML 2019 Workshop.
- Analyzing the theoretical grounds of curiosity-driven, intrinsically-motivated learningR. V. Florian. (2019)In The Fourth International Workshop on Intrinsically Motivated Open-ended Learning (IMOL 2019).
- C. Ivan. (2019)In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (p. 1-8).
- C. Ivan, & B. Indurkhya. (2019)In Beyond Curve Fitting: Causation, Counterfactuals, and Imagination-based AI. AAAI Spring Symposium.
- S. Sârbu, R. Volpi, A. Pește, & L. Malagò. (2018)In ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models.
- A. Davody, & M. S. Baba. (2018)In Working Papers and Documents of the IJCAI-ECAI-2018 Workshop on Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge: L & R – 2018 (p. 30-38).
- A. Davody, H. Davoudi, M. S. Baba, & R. V. Florian. (2018)In Neural Abstract Machines & Program Induction v2: A Federated Artificial Intelligence Meeting (FAIM) workshop (ICML, IJCAI/ECAI, AAMAS).
- C. F. Perțicaș, M. S. Baba, H. Davoudi, & R. V. Florian. (2018)In Neural Abstract Machines & Program Induction v2: A Federated Artificial Intelligence Meeting (FAIM) workshop (ICML, IJCAI/ECAI, AAMAS).
- A. Pește, L. Malagò, & S. Sârbu. (2017)In NIPS 2017 Workshop on Bayesian Deep Learning.
- C. F. Perțicaș, B. Indurkhya, R. V. Florian, & L. Csató. (2017)In 28th Annual Workshop of the Psychology of Programming Interest Group – PPIG 2017: Proceedings (p. 76-85).
- Z. Bodó, & B. Indurkhya. (2017)In New Trends in Intelligent Software Methodologies, Tools and Techniques: Proceedings of the 16th International Conference (SoMeT_17) (Vol. 297, p. 88-98)Presented at the 16th International Conference on Intelligent Software Methodologies, Tools, and Techniques (SOMET_17), IOS Press.
- L. Malagò, & D. Marinelli. (2017)In ICML 2017 Workshop on Principled Approaches to Deep Learning.
- A. Pește, & L. Malagò. (2017)In ICML 2017 Workshop on Implicit Models.
- Hierarchical representations of perceptual and sensorimotor information in deep neural networksR. V. Florian. (2017)In The Third International Workshop on Intrinsically Motivated Open-ended Learning (IMOL 2017).
- R. V. Florian. (2012)In N. M. Seel (Eds.), Encyclopedia of the Sciences of Learning (p. 3245–3247)Boston, MA: Springer US.
- R. V. Florian. (2012)PLoS ONE, 7(8), e40233.
- R. V. Florian. (2012)In N. M. Seel (Eds.), Encyclopedia of the Sciences of Learning (p. 2802–2803)Boston, MA: Springer US.
- R. V. Florian. (2008)In Artificial Neural Networks – ICANN 2008 (Vol. Part II, p. 368-375)Presented at the 18th International Conference on Artificial Neural Networks, Berlin / Heidelberg: Springer.
- R. V. Florian. (2007)Neural Computation, 19(6), 1468–1502.
- R. V. Florian. (2006)In From Animals to Animats 9 (p. 570-581)Presented at the 9th International Conference on Simulation of Adaptive Behavior, SAB 2006, Berlin / Heidelberg: Springer.
- Modulation of STDP by a global reward signal leads to reinforcement learningR. V. Florian. (2006)In Conference on Mathematical Neuroscience (Neuromath06) (p. 45-46).
- Reinforcement learning for spiking neural networks with modulated spike-timing-dependent plasticityR. V. Florian. (2006)In Proceedings of the Tenth International Conference on Cognitive and Neural Systems (p. 126)Boston, MA, USA: Boston University.
- R. V. Florian. (2005)In D. Zaharie, D. Petcu, V. Negru, T. Jebelean, G. Ciobanu, A. Cicortas, et al. (Eds.), Seventh International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC 2005), 25-29 September 2005, Timisoara, Romania (p. 299–306)IEEE Computer Society.
- An evolved spiking neural controller for alternate object pushing by a simulated embodied agentR. V. Florian. (2005)In Proceedings of the Ninth International Conference on Cognitive and Neural Systems (p. 27)Presented at the Ninth International Conference on Cognitive and Neural Systems, Boston, MA: Boston University.