A
Aleksander Malinowski
Researcher at Bradley University
Publications - 63
Citations - 2458
Aleksander Malinowski is an academic researcher from Bradley University. The author has contributed to research in topics: The Internet & Artificial neural network. The author has an hindex of 15, co-authored 58 publications receiving 2330 citations. Previous affiliations of Aleksander Malinowski include University of Louisville.
Papers
More filters
Proceedings ArticleDOI
Sensitivity analysis for minimization of input data dimension for feedforward neural network
TL;DR: The search for redundant data components is performed for networks with continuous outputs and is based on the concept in sensitivity of linearized neural networks, which could lead to smaller networks and reduced-size data vectors.
Journal ArticleDOI
Perturbation method for deleting redundant inputs of perceptron networks
TL;DR: The search for redundant input data components proposed in the paper is based on the concept of sensitivity in linearized models and the mappings considered are R I → R K with continuous and differentiable outputs.
Journal ArticleDOI
Comparison of Embedded System Design for Industrial Applications
Aleksander Malinowski,Hao Yu +1 more
TL;DR: Several platforms for embedded systems, including microcontrollers, microprocessors, field-programmable gate arrays, digital signal processors, and application-specific integrated circuits are discussed and compared and examples of real-life design decisions specific to development of such systems are presented.
Proceedings ArticleDOI
Efficient algorithm for training neural networks with one hidden layer
TL;DR: An efficient second order algorithm for training feedforward neural networks that has a similar convergence rate as the Lavenberg-Marquardt (LM) method and it is less computationally intensive and requires less memory.