Als u wijzigingen in Pure hebt gemaakt, zullen deze hier binnenkort zichtbaar zijn.

Persoonlijk profiel

Quote

"Increases in data and computational power mean Artificial Intelligence (AI) has considerable societal impact. Although impactful, the AI theory is extremely far from creating true intelligence. Thus, the question is not what AI will do to humans, but how humans will improve AI and what they will do with it?"

Research profile

Decebal Mocanu is an Assistant Professor in Artificial Intelligence and Machine Learning within the Data Mining group, Department of Mathematics and Computer Science, Eindhoven University of Technology (TU/e) since September 2017, and a member of TU/e Young Academy of Engineering. His short-term research interest is to conceive scalable deep artificial neural network models and their corresponding learning algorithms using principles from network science, evolutionary computing, optimization and neuroscience. Such models shall have sparse and evolutionary connectivity, make use of previous knowledge, and have strong generalization capabilities to be able to learn, and to reason, using few examples in a continuous and adaptive manner.

Most science carried out throughout human evolution uses the traditional reductionism paradigm, which even if it is very successful, still has some limitations. Aristotle wrote in Metaphysics “The whole is more than the sum of its parts”. Inspired by this quote, in long term, Decebal would like to follow the alternative complex systems paradigm and study the synergy between artificial intelligence, neuroscience, and network science for the benefits of science and society.

Academic background

In 2017, Decebal received his PhD in Artificial Intelligence and Network Science from TU/e. During his doctoral studies, Decebal undertook three research visits: the University of Pennsylvania (2014), Julius Maximilian University of Wurzburg (2015), and University of Texas, Austin (2016).

Prior to this, in 2013, he obtained his MSc in Artificial Intelligence from Maastricht University . During his master studies, Decebal also worked as a part time software developer at We Focus BV in Maastricht. In the last year of his master studies, he also worked as an intern at Philips Research in Eindhoven, where he prepared his internship and master thesis projects. Decebal obtained his Licensed Engineer degree from University Politehnica of Bucharest. While in Bucharest, between 2001 and 2010, Decebal started MDC Artdesign SRL (a software house specialized in web development), worked as a computer laboratory assistant at the University Nicolae Titulescu, and as a software engineer at Namedrive LLC.

Affiliated with

  • Department of Mathematics and Computer Science
  • Data Science Center Eindhoven (DSC/e)

Partners in (semi-)industry 

  • Philips
  • TNO

Onderwijs en Doceren

PhD students:

PDEng students supervision (graduated)

  • Eleftherios Koulierakis, Detection of outbreak of infectious diseases : a data science perspective, July 2018

MSc students supervision (graduated)

  • Joost Pieterse (cum laude), Evolving sparse neural networks using cosine similarity, July 2018
  • Bram Linders (2nd supervisor), Prediction and reduction of MRP nervousness by parameterization from a cost perspective, February 2019
  • Thomas Hagebols, Block-sparse evolutionary training using weight momentum evolution: training methods for hardware efficient sparse neural networks, March 2019

 

Conference tutorials

  • D.C. Mocanu, E. Mocanu, P.H. Nguyen, M. Gibescu, Z. Vale, D. Ernst, Scalable Deep Learning: from theory to practice (T11), International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), Link, Materials
  • D.C. Mocanu, E. Mocanu, Z. Vale, D. Ernst, Scalable Deep Learning: from theory to practice (T24), International Joint Conference on Artificial Intelligence (IJCAI 2019), Link, Materials
  • E. Mocanu, D.C. Mocanu, Scalable Deep Learning: from theory to practice, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD 2019), Link, Materials

Vingerafdruk Duik in de onderzoeksthema's waar Decebal C. Mocanu actief is. Deze onderwerplabels komen voort uit het werk van deze persoon. Samen vormen ze een unieke vingerafdruk.

  • 1 Vergelijkbare profielen
Learning systems Engineering en materiaalwetenschappen
Reinforcement learning Engineering en materiaalwetenschappen
Video streaming Engineering en materiaalwetenschappen
Packet loss Engineering en materiaalwetenschappen
Smart meters Engineering en materiaalwetenschappen
Learning algorithms Engineering en materiaalwetenschappen
Quality of service Engineering en materiaalwetenschappen
Complex networks Engineering en materiaalwetenschappen

Netwerk Recente externe samenwerking op landenniveau. Duik in de details door op de stippen te klikken.

Projecten 2016 2018

Interoperability of Heterogeneous IoT Platforms

Liotta, A., Exarchakos, G., van Hout, J., Mocanu, D., van der Lee, T., van Mil, J., van Mil, J. & Exarchakos, G.

1/01/1631/12/18

Project: Onderzoek direct

Onderzoeksoutput 2013 2019

14 Citaties (Scopus)

Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science

Mocanu, D. C., Mocanu, E., Stone, P., Nguyen, H. P., Gibescu, M. & Liotta, A., 19 jun 2018, In : Nature Communications. 9, 1, 12 blz., 2383

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Open Access
Bestand
education
Learning
Neural networks
Neural Networks (Computer)
Artificial Intelligence
7 Citaties (Scopus)

Decentralized dynamic understanding of hidden relations in complex networks

Mocanu, D. C., Exarchakos, G. & Liotta, A., 25 jan 2018, In : Scientific Reports. 8, 1, 15 blz., 1571

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Open Access
Bestand
Complex networks
games
Electric network analysis
Artificial intelligence
network analysis

Online contrastive divergence with generative replay: experience replay without storing data

Mocanu, D. C., Torres Vega, M., Eaton, E., Stone, P. & Liotta, A., 18 okt 2016, In : arXiv. 16 blz., 1610.05555

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademic

Bestand
Reinforcement learning
Data storage equipment
Unsupervised learning
Supervised learning
Learning algorithms

On the synergy of network science and artificial intelligence

Mocanu, D. C., 2016, Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2016). Palo Alto: AAAI Press

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Open Access
Bestand
Reductionism
Synergy
Artificial Intelligence
Paradigm
Complex Systems
23 Citaties (Scopus)

Factored four way conditional restricted Boltzmann machines for activity recognition

Mocanu, D. C., Bou Ammar, H., Lowet, D. J. C., Driessens, K., Liotta, A., Weiss, G. & Tuyls, K. P., 2015, In : Pattern Recognition Letters. 66, blz. 100-108

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Open Access
Bestand
Neurons
Markov processes
Learning algorithms
Labels
Robotics

Prijzen

Highly Commended Paper Award - International Journal of Pervasive Computing and Communications

Decebal Mocanu (Ontvanger), 2017

Prijs: AndersWerk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.)Wetenschappelijk

Travel Award at IJCAI 2016

Decebal Mocanu (Ontvanger), 11 jul 2016

Prijs: AndersBeurzenWetenschappelijk

Master AI Thesis Award, 1st prize, Maastricht University, the Netherlands

Decebal Mocanu (Ontvanger), 12 jul 2013

Prijs: AndersWerk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.)Wetenschappelijk

artificial intelligence
Netherlands

Best Paper Award MoMM2015

Decebal Mocanu (Ontvanger), 13 dec 2015

Prijs: AndersWerk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.)Wetenschappelijk

Certificate of appreciation from the Journal of Electronic Imaging for serving as a reviewer.

Decebal Mocanu (Ontvanger), 1 jan 2015

Prijs: AndersWerk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.)Wetenschappelijk

Activiteiten 2014 2016

  • 2 Bezoek externe academische instelling
  • 1 Aangemelde presentatie

University of Texas at Austin

Decebal Mocanu (Bezoekende onderzoeker)
16 jan 201616 apr 2016

Activiteit: Types bezoeken aan een externe instellingBezoek externe academische instellingWetenschappelijk

"Deep Learning and its applicability" at University of Würzburg, Germany.

Decebal Mocanu (Spreker)
24 aug 201528 aug 2015

Activiteit: Types gesprekken of presentatiesAangemelde presentatieWetenschappelijk

University of Pennsylvania

Decebal Mocanu (Bezoekende onderzoeker)
15 sep 201415 dec 2014

Activiteit: Types bezoeken aan een externe instellingBezoek externe academische instellingWetenschappelijk

Cursussen

CSE - Web Science

1/09/15 → …

Cursus

Foundations of data mining

1/09/17 → …

Cursus

Scriptie

Block-sparse evolutionary training using weight momentum evolution: training methods for hardware efficient sparse neural networks

Auteur: Hagebols, T., 29 apr 2019

Begeleider: Mocanu, D. (Afstudeerdocent 1), Zhang, Y. (Afstudeerdocent 2) & Lowet, D. (Externe coach)

Scriptie/masterproef: Master

Evolving sparse neural networks using cosine similarity

Auteur: Pieterse, J., 31 aug 2018

Begeleider: Mocanu, D. (Afstudeerdocent 1)

Scriptie/masterproef: Master

Bestand

Prediction and reduction of MRP nervousness by parameterization from a cost perspective

Auteur: Linders, B., 28 feb 2019

Begeleider: Dijkman, R. (Afstudeerdocent 1) & Mocanu, D. (Afstudeerdocent 2)

Scriptie/masterproef: Master

Bestand