Explore the vast range of titles available.

Artificial neural networks (ANNs) have very successfully been used in numerical simulations for a series of computational problems ranging from image classification/image recognition, speech recognition, time series analysis, game intelligence, and computational advertising to numerical approximations of partial differential equations (PDEs). Such numerical simulations suggest that ANNs have the capacity to very efficiently approximate high-dimensional functions and, especially, indicate that ANNs seem to admit the fundamental power to overcome the curse of dimensionality when approximating the high-dimensional functions appearing in the above named computational problems. There are a series of rigorous mathematical approximation results for ANNs in the scientific literature. Some of them prove convergence without convergence rates and some of these mathematical results even rigorously establish convergence rates but there are only a few special cases where mathematical results can rigorously explain the empirical success of ANNs when approximating high-dimensional functions. The key contribution of this article is to disclose that ANNs can efficiently approximate high-dimensional functions in the case of numerical approximations of Black-Scholes PDEs. More precisely, this work reveals that the number of required parameters of an ANN to approximate the solution of the Black-Scholes PDE grows at most polynomially in both the reciprocal of the prescribed approximation accuracy

Convolutional neural networks (CNNs) are the specific architecture of feed‐forward artificial neural networks. It is the de‐facto standard for various operations in machine learning and computer vision. To transform this performance towards the task of network anomaly detection in cyber‐security, this study proposes a model using one‐dimensional CNN architecture. The authors' approach divides network traffic data into transmission control protocol (TCP), user datagram protocol (UDP), and OTHER protocol categories in the first phase, then each category is treated independently. Before training the model, feature selection is performed using the Chi‐square technique, and then, over‐sampling is conducted using the synthetic minority over‐sampling technique to tackle a class imbalance problem. The authors' method yields the weighted average f‐score 0.85, 0.97, 0.86, and 0.78 for TCP, UDP, OTHER, and ALL categories, respectively. The model is tested on the UNSW‐NB15 dataset.

Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting, which, due to its non‐linear nature, remains a challenging task. Recently, deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks, from image classification to machine translation. Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry, but a comprehensive and sound comparison among different—also traditional—architectures is not yet available in the literature. This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting, by contrasting deep learning architectures on short‐term forecast (one‐day‐ahead prediction). Specifically, the focus is on feedforward and recurrent neural networks, sequence‐to‐sequence models and temporal convolutional neural networks along with architectural variants, which are known in the signal processing community but are novel to the load forecasting one.

The adiabatic capacitive artificial neuron (ACAN) has been previously shown to offer the potential for ultra‐low power computation in full custom analogue ASIC designs. However, it did not consider how a real‐world, software‐trained, artificial neuron (AN) could be mapped robustly onto the circuit. In this paper, we describe how an AN, with positive‐valued weights, bias and a binary activation function, can be mapped directly and precisely onto an ACAN. The functional equivalence and properties of the mapping are demonstrated with ANs extracted from an artificial neural network (ANN) trained against a binarized MNIST dataset using an open‐source software AI framework.

This book is a compilation of eleven quality articles exploring a variety of aspects on applications of ANN. Various authors of the articles from India and abroad have presented their work around the applications of ANN in healthcare and self-medication behaviour, Stock Market Analytics, ANN integrated application for industries including regulatory complaining aspect in Banking Industry, Deep Learning Framework in Medical Diagnosis, Face Recognition, Mobile Learning in Medical Education, Process and Applications of ANN using MATLAB, etc.

A second edition of the bestselling guide to exploring and mastering deep learning with Keras, updated to include TensorFlow 2.x with new chapters on object detection, semantic segmentation, and unsupervised learning using mutual information.

Autism spectrum disorder (ASD) is a complex psychological syndrome characterized by persistent difficulties in social interaction, restricted behaviours, speech, and nonverbal communication. The impacts of this disorder and the severity of symptoms vary from person to person. In most cases, symptoms of ASD appear at the age of 2 to 5 and continue throughout adolescence and into adulthood. While this disorder cannot be cured completely, studies have shown that early detection of this syndrome can assist in maintaining the behavioural and psychological development of children. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre‐trained convolutional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. Transfer learning was applied to every model included in the study to achieve higher results than the initial models. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models. The proposed method also outperformed the state‐of‐the‐art models in terms of accuracy and computational cost. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre‐trained convolutional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models.

In this letter, the authors address the challenge in forecasting non‐stationary financial time series by proposing a meta‐learning based forecasting model equipped with a convolution neural network (CNN) predictor and a long short‐term memory (LSTM) meta‐learner. The model is applied to a set of short subseries which are the result of dividing a long non‐stationary financial time series. As a result, a promising performance can be achieved by the proposed model in terms of making more accurate prediction than the traditional CNN predictor and auto regressive (AR)‐based forecasting models in non‐stationary conditions. In this letter, we address the challenge in forecasting non‐stationary financial time series by proposing a meta‐learning based forecasting model equipped with a CNN predictor and a LSTM meta‐learner. The model is applied to a set of short subseries which are the result of dividing a long non‐stationary financial time series. The experimental results demonstrate that our model can effectively deal with non‐stationarity by meta‐learner’s adjustments and significantly enhance the accuracy of future price value forecasting over traditional CNN predictor

Mezinárodní časopis o problematice neuronových a paralelních výpočetních a informačních systémů

The next generations of wireless communications systems are pushing the limits of the channel estimation methods utilized in the orthogonal frequency division multiplexing receptors. This letter proposes a novel channel estimation method using a densely connected neural network considering the time‐variant frequency‐selective fading channel model. A fully connected deep neural network for the AWGN channel case is also proposed. The comparative complexity of the estimation for different channel models is also discussed. The simulation results demonstrate that the densely connected neural network method surpasses the minimum mean‐square error method performance for a signal‐to‐noise ratio ranging from 0 to 25 dB in the frequency‐selective channel. This letter proposes a novel channel estimation method using a densely connected neural network considering the time‐variant frequency‐selective fading channel model. A fully connected deep neural network for the AWGN channel case is also proposed. The comparative complexity of the estimation for different channel models is also discussed.