Search results for "Neural"
showing 10 items of 2783 documents
Robust linear quadratic mean-field games in crowd-seeking social networks.
2013
We consider a social network where opinions evolve following a stochastic averaging process under the influence of adversarial disturbances. We provide a robust mean-field game model in the spirit of H∞-optimal control, establish existence of a mean-field equilibrium, and analyze its stochastic stability.
Biomaterials coated by dental pulp cells as substrate for neural stem cell differentiation
2011
[EN] This study is focused on the development of an in vitro hybrid system, consisting in a polymeric biomaterial covered by a dental pulp cellular stroma that acts as a scaffold offering a neurotrophic support for the subsequent survival and differentiation of neural stem Cells. In the first place, the behavior of dental pulp stroma on the polymeric biomaterial based on ethyl acrylate and hydroxy ethyl acrylate copolymer was studied. For this purpose, cells from normal human third molars were grown onto 0.5-mm-diameter biomaterial discs. After cell culture, quantification of neurotrophic factors generated by the stromal cells was performed by means of an ELISA assay. In the second place, s…
Systematic comparison of Artificial Neural Networks for a SHM procedure applied to Composite Structure
2014
The problems related to damage detection represents a primary concern, particularly in the framework of composite structure. In fact, for this kind of structures barely visible damage can occur. Moreover, one of the major in-service damage of composite aircraft strcutures is represented by disbonds between the stiffeners and the skin undergoing dynamic or post-buckling loads. The effective implementation of a SHM system relies on the synthesis of non-destructive technique (NDT), fracture mechanics, sensors technology, data manipulation and signal processing, and it can receive a great improvement through the use of an Artificial Neural Networks. Different architectures of Artificial Neural …
A convolutional neural network for virtual screening of molecular fingerprints
2019
In the last few years, Deep Learning (DL) gained more and more impact on drug design because it allows a huge increase of the prediction accuracy in many stages of such a complex process. In this paper a Virtual Screening (VS) procedure based on Convolutional Neural Networks (CNN) is presented, that is aimed at classifying a set of candidate compounds as regards their biological activity on a particular target protein. The model has been trained on a dataset of active/inactive compounds with respect to the Cyclin-Dependent Kinase 1 (CDK1) a very important protein family, which is heavily involved in regulating the cell cycle. One qualifying point of the proposed approach is the use of molec…
Are Neural Networks Imitations of Mind?
2015
Artificial neural networks are often understood as a good way to imitate mind through the web structure of neurons in brain, but the very high complexity of human brain prevents to consider neural networks as good models for human mind;anyway neural networks are good devices for computation in parallel. The difference between feed-forward and feedback neural networks is introduced; the Hopfield network and the multi-layers Perceptron are discussed. In a very weak isomorphism (not similitude) between brain and neural networks, an artificial form of short term memory and of acknowledgement, in Elman neural networks, is proposed.
Interactive Effects of Explicit Emergent Structure: A Major Challenge for Cognitive Computational Modeling
2015
International audience; David Marr's (1982) three-level analysis of computational cognition argues for three distinct levels of cognitive information processingnamely, the computational, representational, and implementational levels. But Marr's levels areand were meant to bedescriptive, rather than interactive and dynamic. For this reason, we suggest that, had Marr been writing today, he might well have gone even farther in his analysis, including the emergence of structurein particular, explicit structure at the conceptual levelfrom lower levels, and the effect of explicit emergent structures on the level (or levels) that gave rise to them. The message is that today's cognitive scientists …
The Insect Mushroom Bodies: a Paradigm of Neural Reuse
2013
This paper is devoted to discuss the implementation of models,which are inspired by the fly Drosophila melanogaster and able to handle open problems in the field of robotics such as attention, expectation and sequence learning. The role of the Mushroom Bodies (MBs) in solving these tasks is analyzed in detail and a unifying plausible biologically inspired model is proposed. The developed neural structure is able to show different capabilities in line with the paradigm of neural reuse. The same neural circuit can be exploited to accomplish multiple tasks showing interesting capabilities such as attention, expectation and delayed match-to-sample. The simulation results here reported suggest a…
Contributions Regarding the Utilization of Neural Networks in SME's Management
2014
Due to the fact that there isnt a clear definition of the terms neural network" and "neuronal network" [1,2], the current paper aims to establish it by a range of comparative research. With the help of some charts, based on the structure of some SMEs (Small and Medium Enterprises), the parts that define the structure of the neuron will be compared with the general structure of an organization, in order to reproduce the neuron in the structuring level of an organization and give a meaning to the term of "organizational neuron. Sometimes it is necessary to take managerial decisions under uncertainty and / or risk, so any method that gives forecasting information to the manager is welcome [3,4…
Employing artificial neural networks to find reaction coordinates and pathways for self-assembly
2021
Capturing the autonomous self-assembly of molecular building blocks in computer simulations is a persistent challenge, requiring to model complex interactions and to access long time scales. Advanced sampling methods allow to bridge these time scales but typically require to construct accurate low-dimensional representations of the transition pathways. In this work, we demonstrate for the self-assembly of two single-stranded DNA fragments into a ring-like structure how autoencoder architectures based on unsupervised neural networks can be employed to reliably expose transition pathways and to provide a suitable low-dimensional representation. The assembly occurs as a two-step process throug…
An In-Depth Experimental Comparison of RNTNs and CNNs for Sentence Modeling
2017
The goal of modeling sentences is to accurately represent their meaning for different tasks. A variety of deep learning architectures have been proposed to model sentences, however, little is known about their comparative performance on a common ground, across a variety of datasets, and on the same level of optimization. In this paper, we provide such a novel comparison for two popular architectures, Recursive Neural Tensor Networks (RNTNs) and Convolutional Neural Networks (CNNs). Although RNTNs have been shown to work well in many cases, they require intensive manual labeling due to the vanishing gradient problem. To enable an extensive comparison of the two architectures, this paper empl…