Top Research Papers on Neural Networks

This book represents a valuable contribution to the tield of statistical computing for theoretical researchers and applied practitioners alike and if everyone who used the methods covered by this book followed the author’s guidelines, the quality of research with these methods would be greatly improved.

An affective topic model is proposed with the intention to bridge the gap between social media materials and a reader’s emotions by introducing an intermediate layer and can be used to classify the social emotions of unlabeled documents and to generate a social emotion lexicon.

The human brain performs perceptual tasks such as visual pattern recognition, distinguishing acoustical harmonics, and speech understanding remarkably well, but such cognitive tasks remain difficult for digital computers to accomplish.

In this work, a neural network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle, and these associations are incorporated into the weights of the network.

A variety of artificial neural networks are reviewed, including feed‐forward networks, recurrent networks, associative memories such as the Hopfield network, and the self‐organizing map, as are methods that have been developed for training them.

This chapter presents the use of ANNs to control the behavior of robots and presents an overview of learning in ANNs using the Hebbian rule.

This chapter will detail different types of algorithms used for both Feedforward Neural Networks (FNNs) as well as Convolutional Neural networks (CNNs) and include several case studies and examples of game projects to show the utility of these methods for game design and development.

Artificial neural networks have emerged from the studies of how brain performs and are made up of simplified individual models of the biological neuron that are connected together to form a network.

This chapter elaborates on the connections and interdisciplinary links between knowledge discovery in databases (KDD) and neural networks and neurocomputing, in general, and identifies a number of basic categories of synergistic links existing therein.

Neural networks are the concept of making computer works similar to human brain that is able to solve complex hypothetical queries at an instance as like a human brain and respond in the same ways as human do.

This book is suitable for undergraduates from Computer Science and Electrical Engineering courses who are taking a one module course on neural networks, and for researchers and computer science professionals who need a quick introduction to the subject.

Applications of neural nets are listed, with brief comments on nets' suitability to a few of them, and types of learning are discussed.

If the number of hidden units is appropriately chosen multi layer perceptrons are universal approximators, i.e. they can solve, at least theoretically, any association problem (nonlinearly separable classification, nonlinear regression and prediction problems).

An overview of current research on artificial neural networks is presented, emphasizing a statistical perspective, that views neural networks as parameterized graphs that make probabilistic assumptions about data and learning algorithms as methods for finding parameter values that look probable in the light of the data.

This tutorial demonstrates a small neural network composed chiefly of multiply and add operations, which is really all that happens inside a neural network.

The theory of neural networks, as it has emerged in the last ten years or so within the physics community, is reviewed, emphasizing questions of biological relevance over those of importance in mathematical statistics and machine learning theory.

This study presents the Yolov4-based vehicle detection, classification, and counting model approach, which has counted the number of vehicles: cars, motorcycles, buses, and trucks.

An overview of neural networks is provided, from a statistician's vantage point, why neural networks might be attractive and how they compare to other modern regression techniques.

An approach to combine evidence present at the segmental and suprasegmental levels to improve the performance of the text-dependent speaker veri(cid:12)cation sys-tem is proposed.

A system that applies a Neural Network to a video surveillancesystem that consists of a pre—processing unit that extracts high level information from images and intruduces it in the Neural Network that can learn in operational conditions while under the supervision of an unskilled operator.