Natural and High Performance Computing Laboratory (NHPC Lab)

http://atm.neuro.pub.ro/radu_d/

 

Team:

Radu Dogaru, Ph.D., Full professor, PhD advisor (computational intelligence, natural computing, nonlinear dynamics)
Ioana Dogaru, Ph.D., Associate professor, (advanced programming techniques and tools, reconfigurable computing systems, natural computing)

2 teaching staff (PhD, listed above) + 7 (variable by the year) PhD students/researchers

1 office and research lab + 1 educational and research lab with up to 10 work-places.

 

Research directions:

 

- Natural computing algorithms (cellular nonlinear networks, artificial neural networks and machine learning, fuzzy logic, swarm intelligence and naturally inspired optimization and learning algorithms, etc.) and their applications

 

- Nonlinear dynamics in complex networks and their applications: ciphering, prediction, models for various physical, biological and social processes.

 

- Embedded solutions with HP3 (high performance, portability and productivity) for implementing the above mentioned algorithms into actual computing platforms (PC, FPGA-based systems, GPU based systems with CUDA support, development of specialized circuits in cooperation with other groups)

 

Representative results:

 

 

 

1.      The RBF-M (recently renamed FSVC = Fast Support Vector Classifier) - more details follow

2.      The Simplicial Neural Network  (based on it a smart visual processor was recently (2014) developed: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6716069);

3.      The SORT neural network (or a brief version here) it is a simplified version of the Simplicial NN targeting digital platforms.

4.      The modified Naive-Bayes classifier (it is actually a Naive Bayes classifier with tuning parameters, thus allowing better performance). It also includes easy-to implement triangular shape functions replacing the traditional Gaussian.

5.      (most cited of our papers) The Multi-nested neuron (universal CNN cell); Initially developed to provide a very compact implementation of CNN cells, may be also used in any other machine learning task. It is a very compact, hardware oriented, alternative to polynomial neurons. 

 

 

 

 

Some relevant projects and downloads

 

- FSVC - Efficient classifier for embedded systems (Fast Support Vector Classifier) - freely available on MatlabCentral. Simillar performance to well known SVM but with a much lower complexity and avoiding complicated operators (exponential, etc.) - well suited for embedded systems. Related papers related are included in the above link.
Faster version is accelerated two orders of magnitude using .MEX files (runs under Octave 4.0.0). Available on GitHub


SFSVC: Another (even faster, 10-50 times more than SVM and ELM on the same platform) was  presented in a paper accepted at the COMM 2016 conference); SFSVC is well suited for embbeded systems, there is no need for updating synaptic weights, while support vectors are simply selected from the training dataset.  A Python version optimized for speed will be soon (july 2018) made available on GitHub


Fast-ELM - Efficient classifier for embedded systems (Extreme Learning Machine, Python, optimized for speed under MKL-based Python distributions) - Available on GitHub (including the COMM-2018 paper reporting on it)

- ADBIOSONAR - research project (2008-2011) financed by the Romanian Research Founding Authority, concluded with a cellular automata based software simulator for virtual experiments using sound propagation (initially conceived for robotics). Related papers here.  

 
AutoVoice- Database:  A database with vocal commands in noisy environment  (inside an automobile) made by Mihai Bucurica as part of his doctoral studies.  More details here (including a paper reporting research using this database, please the cite this paper if you find it useful for your research).  



Relevant lectures: 

April 2018 - "Some fast and compact neural network solutions for artificial intelligence applications"
Invited lecture given at the
Doctoral School of Elelctronics at University "Politehnica" of Bucharest


Teaching activities

Doctoral studies: Prof. Radu DOGARU is habilitated since 2008 to conduct doctoral studies within ETTI's Doctoral School (6 graduated thesis so far)

Master degree studies: Prof. Dogaru  coordinates (since 2011) the master programme IISC (Information Engineering and Computer Science)

Courses taught by our group members (Ioana Dogaru and Radu Dogaru  - a detailed list in Romanian language here):
    Master degree: Natural Computing Systems, Applied Neuro-informatics, Nonlinear Biodynamics, Complex Nonlinear Networks;
    Licenta (Bachelor) degree: Embbeded Computational Intelligence, Reconfigurable Computing Systems, Object Oriented Programming, Internet Programming, Software for Medical Equipment