Branko Ster

Followers

Following

Co-authors

Public Views

Arnab Bhattacharya

IIT Kanpur

James Elkins

School of the Art Institute of Chicago

Adnene TLILI

ISET Nabeul

Justin Pargeter

New York University

Maciej Banach

Medical University of Lodz, Lodz, Poland

David Gortler

Yale University

Güzin Özdağoğlu

Dokuz Eylül University

Sergio Bydlowski

University of Sao Paulo

Donald Hoffman

University of California, Irvine

Dr. Anika Niambi Al-Shura, BSc, MSOM, PhD

Independent Academic Research Studies

Interests

Uploads

Papers by Branko Ster

Structural Properties of Recurrent Neural Networks

Neural Processing Letters, 2009

In this article we research the impact of the adaptive learning process of recurrent neural netwo... more In this article we research the impact of the adaptive learning process of recurrent neural networks (RNN) on the structural properties of the derived graphs. A trained fully connected RNN can be converted to a graph by defining edges between pairs od nodes having significant weights. We measured structural properties of the derived graphs, such as characteristic path lengths, clustering coefficients and degree distributions. The results imply that a trained RNN has significantly larger clustering coefficient than a random network with a comparable connectivity. Besides, the degree distributions show existence of nodes with a large degree or hubs, typical for scale-free networks. We also show analytically and experimentally that this type of degree distribution has increased entropy.

Download

Impact of Learning on the Structural Properties of Neural Networks

Lecture Notes in Computer Science

ABSTRACT We research the impact of the learning process of neural networks (NN) on the structural... more ABSTRACT We research the impact of the learning process of neural networks (NN) on the structural properties of the derived graphs. A type of recurrent neural network is used (GARNN). A graph is derived from a NN by defining a connection between any pair od nodes having weights in both directions above a certain threshold. We measured structural properties of graphs such as characteristic path lengths (L), clustering coefficients (C) and degree distributions (P). We found that well trained networks differ from badly trained ones in both L and C.

Selective Recurrent Neural Network

Neural Processing Letters, 2013

ABSTRACT It is known that recurrent neural networks may have difficulties remembering data over l... more ABSTRACT It is known that recurrent neural networks may have difficulties remembering data over long time lags. To overcome this problem, we propose an extended architecture of recurrent neural networks, which is able to deal with long time lags between relevant input signals. A register of latches at the input layer of the network is applied to bypass irrelevant input information and to propagate relevant inputs. The latches are implemented with differentiable multiplexers, thus enabling the derivatives to be propagated through the network. The relevance of input vectors is learned concurrently with the weights of the network using a gradient-based algorithm.

Experiments with Machine Learning in the Prediction of Coronary Artery Disease Progression

by Andrej Dobnikar and Branko Ster

Intelligent Data Analysis in Medicine and Pharmacology, 1997

Enhancing upper confidence bounds for trees with temporal difference values

2014 IEEE Conference on Computational Intelligence and Games, 2014

Validation of the Slovenian version of patient assessment of chronic illness care (PACIC) in patients with coronary heart disease

Collegium antropologicum, 2014

The Chronic Care Model (CCM) is a conceptual framework that supports the evidence-based proactive... more The Chronic Care Model (CCM) is a conceptual framework that supports the evidence-based proactive and planned care of chronic diseases. Our aim was to validate a Slovenian translation of Patient Assessment of Chronic Illness Care (PACIC)--a self-reported instrument designed to measure the extent to which patients with chronic illnesses receive care congruent with CCM--on a sample of patients with coronary heart disease. Secondary analysis of patients' evaluation of general practice care (EPA Cardio study) was done in patients with coronary heart disease in Slovenia. Patients completed a written questionnaire, which included the instrument for assessing chronic illness care (PACIC), the EUROPEP questionnaire and demographical data. Internal consistency was expressed in terms of Cronbach's alpha. Reliability was expressed as the intra class correlation coefficient (ICC). Correlation between PACIC and EUROPEP was considered as a measure of construct validity. Factor analysis wa...

Final year medical students’ understanding of family medicine

Acta Medica Academica, 2014

The European Academy of Teachers in General Practice / Family Medicine (EURACT) has developed an ... more The European Academy of Teachers in General Practice / Family Medicine (EURACT) has developed an educational agenda, the key document for teaching family medicine in Europe. The aim of our study was to find out how final year medical students at the beginning of their family medicine clerkship understand the discipline of family medicine. The attitudes toward family medicine were paraphrased and developed into a 164-item questionnaire, which was administered to 335 final-year medical students at the beginning of their clerkship. Using combinatorial optimization with genetic algorithms we selected 30 items which yielded the highest Cronbach alpha reliability coefficient. Finally, we performed a factor analysis to find which dimensions of family medicine were recognised by the students and compared them with the domains defined in the EURACT definition. The 30-item questionnaire had a Cronbach alpha reliability coefficient of 0.919. The differences between male and female students were not very significant (p=0.061). With the factor analysis we recognised seven factors, belonging to three out of six domains of the EURACT educational agenda: primary care management, personcenteredness and comprehensive approach. Final-year medical students at the beginning of their family medicine clerkship understand some of the dimensions of family medicine rather well, but they are not aware of some important competences of family doctors. There is a necessity to teach students about specific problem solving skills and the importance of balance between the health needs of an individual patient and the community.

Building Internal Maps of a Mobile Robot

by Branko Ster and Andrej Dobnikar

Motion Planning, 2008

Download

Designable DNA-binding domains enable construction of logic circuits in mammalian cells

Nature Chemical Biology, 2014

Electronic computer circuits consisting of a large number of connected logic gates of the same ty... more Electronic computer circuits consisting of a large number of connected logic gates of the same type, such as NOR, can be easily fabricated and can implement any logic function. In contrast, designed genetic circuits must employ orthogonal information mediators owing to free diffusion within the cell. Combinatorial diversity and orthogonality can be provided by designable DNA- binding domains. Here, we employed the transcription activator-like repressors to optimize the construction of orthogonal functionally complete NOR gates to construct logic circuits. We used transient transfection to implement all 16 two-input logic functions from combinations of the same type of NOR gates within mammalian cells. Additionally, we present a genetic logic circuit where one input is used to select between an AND and OR function to process the data input using the same circuit. This demonstrates the potential of designable modular transcription factors for the construction of complex biological information-processing devices.

Neural networks in medical diagnosis: Comparison with other methods

by Branko Ster and Andrej Dobnikar

Download

Modelling the Environment of a Mobile Robot with the Embedded Flow State Machine

by Branko Ster and Andrej Dobnikar

Journal of Intelligent and Robotic Systems, 2006

A type of topological approach to mobile robot navigation is discussed and experimentally evaluat... more A type of topological approach to mobile robot navigation is discussed and experimentally evaluated. The environment as experienced by a moving robot is treated as a dynamical system. Simple types of reactive behavior are supplemented with eventual decisions to switch between them. When switching criteria are defined, the system may be described in the form similar to a finite state machine. Since it is embedded in the environment and dependent on the sensory flow of the robot, we introduce the term "Embedded flow state machine" (EFSM). We implemented it with a recurrent neural network, trained on a sequence of sensory contents and actions. One of the main virtues of this approach is that no explicit localization is required, since the recurrent neural network holds the state implicitly. The EFSM is applicable to multi-step prediction of sensory information and the travelled distances between decision points, given a sequence of decisions at decision points. Thus, the optimal path to a specified goal can be sought. One of the main issues is, for how many steps ahead the prediction is reliable enough. In other words, is it feasible to perform environment modelling and path planning in this manner? The approach is tested on a miniature mobile robot, equipped with proximity sensors and a color video camera. Decision 'points,' where deviations from the wall-following behavior are allowed, are based on color object recognition. In the case of an experimental environment of medium complexity, this approach was successful.

Download

Adaptive radial basis decomposition by learning vector quantization

by Branko Ster and Andrej Dobnikar

Neural processing letters, 2003

A method for function approximation in reinforcement learning settings is proposed. The action-va... more A method for function approximation in reinforcement learning settings is proposed. The action-value function of the Q-learning method is approximated by the radial basis function neural network and learned by the gradient descent. Those radial basis units that are unable to fit the local action-value function exactly enough are decomposed into new units with smaller widths. The local temporal-difference error is modelled by a two-class learning vector quantization algorithm, which approximates distributions of the positive and of the negative error and provides the centers of the new units. This method is especially convenient in cases of smooth value functions with large local variation in certain parts of the state space, such that non-uniform placement of basis functions is required. In comparison with four related methods, it has the smallest requirements of basis functions when achieving a comparable accuracy.

Download

Markov random field model for segmenting large populations of lipid vesicles from micrographs

by Jernej Zupanc and Branko Ster

Journal of Liposome Research, 2011

Giant unilamellar lipid vesicles, artificial replacements for cell membranes, are a promising too... more Giant unilamellar lipid vesicles, artificial replacements for cell membranes, are a promising tool for in vitro assessment of interactions between products of nanotechnologies and biological membranes. However, the effect of nanoparticles can not be derived from observations on a single specimen, vesicle populations should be observed instead. We propose an adaptation of the Markov random field image segmentation model which allows detection and segmentation of numerous vesicles in micrographs. The reliability of this model with different lighting, blur, and noise characteristics of micrographs is examined and discussed. Moreover, the automatic segmentation is tested on micrographs with thousands of vesicles and the result is compared to that of manual segmentation. The segmentation step presented is part of a methodology we are developing for bio-nano interaction assessment studies on lipid vesicles.

Structural Properties of Recurrent Neural Networks

Neural Processing Letters, 2009

Download

Impact of Learning on the Structural Properties of Neural Networks

Lecture Notes in Computer Science