If you made any changes in Pure these will be visible here soon.

Personal profile

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 Assistant Professor in Artificial Intelligence and Machine Learning within the DMB group, Faculty of Electrical Engineering, Mathematics, and Computer Science at University of Twente and Guest Assistant Professor within the Data Mining group, Department of Mathematics and Computer Science at Eindhoven University of Technology. From September 2017 until February 2020, Decebal was Assistant Professor at TU/e, 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

For an updated webpgae, please see https://people.utwente.nl/d.c.mocanu

Fingerprint Dive into the research topics where Decebal C. Mocanu is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Projects

Interoperability of Heterogeneous IoT Platforms

Exarchakos, G., Mocanu, D. C., van der Lee, T. & Exarchakos, G.

1/01/1631/12/18

Project: Research direct

Research Output

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 p., 2383.

Research output: Contribution to journalArticleAcademicpeer-review

Open Access
File
  • 35 Citations (Scopus)
    337 Downloads (Pure)

    Decentralized dynamic understanding of hidden relations in complex networks

    Mocanu, D. C., Exarchakos, G. & Liotta, A., 1 Dec 2018, In : Scientific Reports. 8, 1, 15 p., 1571.

    Research output: Contribution to journalArticleAcademicpeer-review

    Open Access
    File
  • 7 Citations (Scopus)
    75 Downloads (Pure)

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

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

    Research output: Contribution to journalArticleAcademic

    File
  • 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

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Open Access
    File
  • 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, p. 100-108

    Research output: Contribution to journalArticleAcademicpeer-review

    Open Access
    File
  • 25 Citations (Scopus)
    115 Downloads (Pure)

    Prizes

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

    Decebal Mocanu (Recipient), 2017

    Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

    Travel Award at IJCAI 2016

    Decebal Mocanu (Recipient), 11 Jul 2016

    Prize: OtherScholarshipsScientific

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

    Decebal Mocanu (Recipient), 12 Jul 2013

    Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

  • Best Paper Award MoMM2015

    Decebal Mocanu (Recipient), 13 Dec 2015

    Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

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

    Decebal Mocanu (Recipient), 1 Jan 2015

    Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

    Activities

    • 2 Visiting an external academic institution
    • 1 Contributed talk

    University of Texas at Austin

    Decebal Mocanu (Visiting researcher)
    16 Jan 201616 Apr 2016

    Activity: Visiting an external institution typesVisiting an external academic institutionScientific

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

    Decebal Mocanu (Speaker)
    24 Aug 201528 Aug 2015

    Activity: Talk or presentation typesContributed talkScientific

    University of Pennsylvania

    Decebal Mocanu (Visiting researcher)
    15 Sep 201415 Dec 2014

    Activity: Visiting an external institution typesVisiting an external academic institutionScientific

    Courses

    CSE - Web Science

    1/09/15 → …

    Course

    Foundations of data mining

    1/09/1731/08/21

    Course

    Press / Media

    Student theses

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

    Author: Hagebols, T., 29 Apr 2019

    Supervisor: Mocanu, D. (Supervisor 1), Zhang, Y. (Supervisor 2) & Lowet, D. (External coach)

    Student thesis: Master

    File

    Evolving sparse neural networks using cosine similarity

    Author: Pieterse, J., 31 Aug 2018

    Supervisor: Mocanu, D. (Supervisor 1)

    Student thesis: Master

    File

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

    Author: Linders, B., 28 Feb 2019

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

    Student thesis: Master

    File

    Unsupervised learning for early detection of merchant risk in payments

    Author: Bahulikar, S., 25 Nov 2019

    Supervisor: Mocanu, D. C. (Supervisor 1) & Moura, J. (External person) (External coach)

    Student thesis: Master

    File