His research interest is in adaptive systems and structures, parallel processing, information theory, inference, natural and learning algorithms. He is occupied with research, application oriented and bilateral projects on a regular basis. The research results are published in the scientific publications with SCI and INSPEC impact factors and presented on the international scientific conferences. He is member of Advisory Committee of the ICANNGA conference (International Conference on the Adaptive and Natural computiNG Algorithms).

**Office Hours:**

Tuesday: 12:00 - 13:00

**Courses:**

**Teacher ID:**000046

## Activities and Events

Organization of ICANNGA 2011 conference to be held in Ljubljana, Slovenia.

## Projects

### Current Projects

- Synergy of the technological systems and processes, Research Programme, P2-0241, 2009−2019

### Closed Projects

- Modeling of complex dynamic systems with soft computing methods, Bilateral Collaboration Project, BI-PL/10-11-014, 2010−2011
- Development and realization of on-line regulation of compound mixer with soft computing methods, Industry-Funded Project, IPMT-001/2006/FRI-LASPP-001, 2006−2008
- Global GRID for data mining with soft computing on large data bases , Bilateral Collaboration Project, BI-PT/06-07-008, 2006−2007
- Data mining of combined bases of mixing recipies and compound testing with soft computing methods, Basic Research and Application Project, L2-6460, 2004−2007
- Relating the physical properties of polymeric materials by parallel implementation of soft computing methods, Basic Research and Application Project, L2-6143, 2004−2007

## Selected publications

- A. Dobnikar, B. Šter. Structural properties of Recurrent Neural Networks, Neural Processing Letters, 2009, sprejeto v objavo
- B. Šter, A. Dobnikar. Modelling the environment of a mobile robot with the embedded flow state machine, J. intell. robot. syst., 46(2), 182-199, 2006.
- I. Jeras, A. Dobnikar. Cellular automata preimages : count and list algorithm. V: V. N. Alexandrov (ur.). Computational science - ICCS 2006 : 6th International Conference, Reading, UK, May 28-31, 2006 : proceedings. Part 1-4, (Lecture notes in computer science. Berlin: Springer, cop., pp.345-352, 2006.
- B. Šter, A. Dobnikar. Adaptive Radial Basis Decomposition by Learning Vector Quantization, Neural Processing Letters, 18(1), pp. 17–27, 2003.
- U. Lotric, A. Dobnikar. Predicting time series using neural networks with wavelet-based denoising layers.
*Neural Ccomput.Aappl. (Print)*, 2005, vol. 14, no. 1, str. [11]-17, - I. Gabrijel, A. Dobnikar. On-line identification and reconstruction of finite automata with generalized recurrent neural networks, Neural Networks, 16(1): 101–121, 2003.
- A. Dobnikar. Genetic synthesis of task oriented neural networks.
*Neural parallel sci. comput.*, 1994, let. 2, št. 4, str. 533-542. - B. Viher, A. Dobnikar, D. Zazula. Cellular automata and follicle recognition problem and possibilities of using cellular automata for image recognition purposes.
*International journal of medical informatics*. [Print ed.], April 1998, 49, št. 2, str. 231-241. - A. Dobnikar. Learning feedforward neural networks with synaptic correlations.
*Elektroteh. vestn.*, 1995, let. 62, št. 5, str. 295-298. - A. Likar, A. Dobnikar. On-line correction of the gain in Kalman filtering.
*Automatica (Oxf.)*. [Print ed.], 1994, let. 30, št. 4, str. 729-730.

## Graduate Students

- Jernej Zupanc
- Nejc Ilc