For modeling nonlinear systems we present a new type of Cellular Neural Networks (CNN) with nonlinear weight and output functions defined by tabulated functions. Training algorithms are used to adjust the behaviour of CNN solutions to those of a system represented only by it ́s output values. A few output values of the system reveal to be sufficient to determine the parameters of the CNN. The pr...

Pluripotent stem cells can potentially be used in clinical applications as a model for studying disease progress. This tracking of disease-causing events in cells requires constant assessment of the quality of stem cells. Existing approaches are inadequate for robust and automated differentiation of stem cell colonies. In this study, we developed a new model of vector-based convolutional neural...

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained CNN model (in the case of image data), and reusing it for other purposes is a field of interest, as it provides access to the visual descriptors pr...

The paper presents energy based medical imaging segmentation methods by using Cellular Neural Networks (CNN). By implementing the proposed algorithm on FPGA (Field Programmable Gate Array) with an emulated digital CNN-UM (CNN-Universal Machine), due to complete parallel processing, computing-time reduction is achieved and there is a possibility to meet the requirements for medical image segment...

We consider a Cellular Neural Network (CNN) with a bias term in the integer lattice Z on the plane Z. We impose a space-dependent coupling (template) appropriate for CNN in the hexagonal lattice on Z. Stable mosaic patterns of such CNN are completely characterized. The spatial entropy of a (p1, p2)-translation invariant set is proved to be well-defined and exists. Using such a theorem, we are a...

In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN). In this comparative study, we extract features from different layers from different CNN models, and then train linear SVM classifiers. Experimental results with 10-fold cross validations show that features from first few convolution layers are eno...

Let M = [ttUiSi /_i be completely nonnegative (CNN), i.e., every minor of Mis nonnegative. Two methods for reducing the eigenvalue problem for M to that of a CNN, tridiagonal matrix, T = [?,-,] (r,-,= 0 when |i — j\ > 1), are presented in this paper. In the particular case that M is nonsingular it is shown for one of the methods that there exists a CNN nonsingular 5 such that SM = TS.

Convolutional Neural Networks (CNN) are the most popular of deep network models due to their applicability and success in image processing. Although plenty of effort has been made in designing and training better discriminative CNNs, little is yet known about the internal features these models learn. Questions like, what specific knowledge is coded within CNN layers, and how can it be used for ...

In the Drosophila early embryo, the centrosome coordinates assembly of cleavage furrows. Currently, the molecular pathway that links the centrosome and the cortical microfilaments is unknown. In centrosomin (cnn) mutants, in which the centriole forms but the centrosome pericentriolar material (PCM) fails to assemble, actin microfilaments are not organized into furrows at the syncytial cortex [6...

A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN archi...