An investigation on deep learning with beta stabilizer

Reading books is one of the most effective ways to reduce stress. In today's digital era, access to finding and buying books is getting easier, so reader reviews are important in choosing books that match interests. However, with a large number of reviews, Natural Language Processing (NLP) with the Long Short-Term Memory (LSTM) method is used to help analyze positive and negative sentiments from many book reviews. This sentiment analysis is useful for readers to evaluate the quality of books, as well as for authors and sellers to find out the opinions of readers and improve the quality of their work. In this study, the book review dataset "Vera Wong's Unsolicited Advice for Murderers" from the Goodreads website is used, which is then divided into training data and validation data with a ratio of 75%: 25%. The Long Short-Term Memory (LSTM) method is used to analyze the sentiment of the reviews. The model architecture built consists of Embedding Layer, LSTM Layer with 128 neuron units, 3 Dense Layer with ReLU activation function, 3 Dropout Layer, and Fully Connected Layer with and Sigmoid activation function, Binary Cross Entropy loss function, and RMSprop optimizer. The model training process was conducted with 30 epochs. The evaluation results show that the model achieved an accuracy of 90%, indicating the model performs relatively well in correctly classifying positive sentiments.

Extreme weather modeling is a challenge for modeling experts in Indonesia and the world. Extreme weather prediction is a complex problem because the chances of it happening are very small, so the developed models often have a low level of accuracy. The purpose of this research is to combine the classic model, Autoregressive Integrated Moving Average (ARIMA), recurrent neural network (RNN) model using Adam and SGD estimation (RNN-Adam and RNN-SGD) with the reLU, tanh, sigmoid and gaussian activation functions. In addition, the ARIMA-RNN mix model was also demonstrated in this study. These models are applied to monthly period extreme weather data obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) of West Sulawesi Province which are converted into training data and test data. The RMSE value is used to see the level of prediction accuracy in both training data and test data. Based on the research results, the best model obtained for modeling Indonesia’s extreme weather is the ARIMA-RNN-Adam mix model with the reLU activation function based on the RMSE value on the training and test data. At n = 50, the smallest RMSE and MSE values of the third model are the ARIMA-RNN-Adam model which is 0.23212 using the reLU activation function, then the ARIMA-RNN-SGD model which is 0.25432 with the same activation function, while the ARIMA value is 0.3270. At n=100 it can be seen that the smallest RMSE and MSE values of the three models are the ARIMA-RNN-Adam model which is equal to 0.25149 using the reLU activation function, then the ARIMA-RNN-SGD model which is equal to 0.25256 with the same activation function, while the ARIMA value is 0.2644.

Over the past few decades, research has focused heavily on automatic speech recognition (ASR). Although ASR for a few languages is close to reality; ASR for the low resource languages like Malayalam is still in its infancy. Here, in this work, the authors discuss the experiment conducted on accented data of Malayalam speech using two approaches. One approach uses the spectral features for modeling using deep convolutional neural network and the other uses the influential features of speech signals for modeling using LSTM-RNN approach. The proposed methodology comprises three distinct stages; dataset preparation, feature extraction, classification, and hence the construction of deep learning models that recognize the accent-based spoken sentences in the Malayalam language. Mel-frequency cepstral coefficient (MFCC) algorithm, short-term Fourier transform (STFT), and mel spectrogram methodologies are used for feature engineering and hence the features that represent the speech signals are used for constructing the accented ASR system for the Malayalam language using long short-term memory (LSTM) a recurrent neural network (RNN). The spectrogram dataset has been constructed for the speech dataset and used for constructing the ASR model with deep convolutional neural network (DCNN). The result of the experiment shows that LSTM-based RNN outperforms DCNN for the proposed dataset that has been constructed for the experiment in the natural recording environment.

In recurrent neural networks such as the long short-term memory (LSTM), the sigmoid and hyperbolic tangent functions are commonly used as activation functions in the network units. Other activation functions developed for the neural networks are not thoroughly analyzed in LSTMs. While many researchers have adopted LSTM networks for classification tasks, no comprehensive study is available on the choice of activation functions for the gates in these networks. In this paper, we compare 23 different kinds of activation functions in a basic LSTM network with a single hidden layer. Performance of different activation functions and different number of LSTM blocks in the hidden layer are analyzed for classification of records in the IMDB, Movie Review, and MNIST data sets. The quantitative results on all data sets demonstrate that the least average error is achieved with the Elliott activation function and its modifications. Specifically, this family of functions exhibits better results than the sigmoid activation function which is popular in LSTM networks.

The recurring neural network is a deep learning algorithm that is commonly used to develop prediction systems. There are many variants of RNN such as RNN itself, long-short-term memory (LSTM), and gated recurring unit, so it is frequently debatable which algorithm from the RNN family has the most optimal efficiency and computation time. When developing a prediction system, sequential or time series data is required so that an accurate prediction can be made. Sequential or time series data involve data arranged in a time sequence, such as weather data, financial data, carbon emission data, and traffic data recorded over time. This research will be carried out by predicting the three RNN models against historical Bitcoin value data. The research method used is Experimental Design by comparing the performance between the three models on bitcoin value time series data, testing is done by involving hyperparameters such as Tanh, Sigmoid, and ReLU activation functions, batch size, and epochs. The aim of this research is to find out which RNN model can produce the most optimal performance and find out what performance measures can be used to evaluate and compare the performance between the three models. The results of the study show that LSTM is the most effective model with RMSE 0.012441 and MSE 0.000155 but inefficient because it takes 3 minutes 24 seconds to run the computation; in the meantime, the Tanh activation function gives the most optimal prediction than Sigmoid and RelU and therefore should be the main candidate to be used with RNN models when predicting Bitcoin prices.

In order to solve the deep self-coding neural network training process, the Sigmoid function back-propagation gradient is easy to disappear, a method based on ReLU activation function is proposed for training the self coding neural network. This paper analyzes the performance of different activation functions and comparing ReLU with traditional Tanh and Sigmoid activation function and in Reuters-21578 standard for experiments on the test set. The experimental results show that using ReLU as the activation function, not only can improve the network convergence speed, and can also improve the accuracy.

Maxout neurons for deep convolutional and LSTM neural networks in speech recognition

<p dir="ltr">Recurrent Neural Networks (RNNs) are a major class of Artificial Neural Networks (ANNs). Suitable network architecture is vital for RNNs to achieve high performance. However, designing the architecture of deep RNNs (DRNNs) is a complicated and time-consuming process. Each layer of a DRNN contains numerous hyper-parameters. It is challenging to optimize the hyper-parameters of all layers jointly to achieve the best possible learning performance. Trial-and-error methods for designing DRNNs have been proven to be laborious and highly costly in practice. Therefore, an efficient automatic architecture search technique is needed to design DRNNs.</p><p dir="ltr">Genetic Algorithm (GA) is a popular evolutionary computation based approach. Existing research works already explored the use of GAs in designing ANNs. But, most of the existing approaches focus on the design of fixed-depth ANNs. However, it is not easy to fix the depth of DRNNs in advance, since different problems need DRNNs of different depths. Hence, the potential of GA has to be further explored to evolve the architecture of DRNNs of varying depths.</p><p dir="ltr">The primary goal of this thesis is to develop advanced GA approaches for designing Long Short Term Memory (LSTM) based DRNN architectures of varying depths effectively and efficiently.</p><p dir="ltr">Firstly, this thesis proposes a GA-based algorithm called Two-Stage Surrogate-Assisted GA (TS-SA-GA) with a progressive incremental strategy to design the architecture of LSTM networks of varying depths. The progressive approach can effectively extend well-designed shallow networks to high performing deep networks. Moreover, the new GA-based algorithm adopts newly designed knowledge-driven crossover and mutation operators to identify and repair LSTM network designs affected by inappropriate use of activation functions, thereby significantly reducing the chances for GA to evolve hard-to-train LSTM network architectures. Furthermore, this thesis proposes a two-stage surrogate method to predict the trainability and fitness of LSTM networks. This improves the efficiency and effectiveness of the GA-based algorithm to evolve LSTM networks.</p><p dir="ltr">Secondly, this thesis proposes a new algorithm called Evolutionary Design of LSTM Ensembles (ED-LSTM-Ensemble) based on multi-objective optimization techniques to evolve LSTM networks and ensembles simultaneously to directly utilize the ensemble performance to drive the evolution of base LSTM networks. Additionally, this thesis proposes a connection weight inheritance strategy to evolve LSTM networks and ensembles efficiently and effectively.</p><p dir="ltr">Thirdly, this thesis proposes a new algorithm called Skip Connections through Evolutionary and Differential Architecture search (SCEDA) to design LSTM networks together with appropriate skip connections automatically. Designing LSTM networks together with skip connections is highly challenging. This thesis hybridize gradient-based DAS and evolutionary architecture search to optimize the architecture of LSTM networks with suitable skip connections in a single evolutionary process to improve the efficiency and effectiveness of the search process.</p><p dir="ltr">Finally, this thesis conducts an in-depth empirical analysis of the impact of activation functions on the trainability of LSTM networks based on the concept of Edge Of Chaos. The analysis reveals the strong interrelation between the activation functions across multiple layers of an LSTM network and the trainability of the network. The analysis also highlights the importance of controlling activation functions to avoid generating untrainable LSTM networks. On the basis of the analysis, this thesis proposes a machine learning model to guide the use of activation functions in LSTM networks.</p>

While the growing accessibility of technology improves usability, it also creates more opportunities for cybercriminals to exploit vulnerabilities, significantly accelerating the proliferation of cybersecurity attacks. Deep learning (DL) approaches present significant advancements over conventional machine learning (ML) techniques by automating feature selection and extraction while minimizing external dependencies. This study proposes a deep learning-based model to enhance cyberattack detection and ensure that data security goals are achieved. This study employs a quantitative research design, utilizing simulation and modeling as the primary analytical tools. The dataset used is the Canadian Institute for Cybersecurity Intrusion Detection System (CIC-IDS-2017) dataset. Three distinct DL algorithms are used to design the detection models, namely, Deep Neural Network (DNN), Long Short-Term Memory (LSTM), and Recurrent Neural Network (RNN). The performance comparison metrics are F1-score, accuracy, sensitivity, false positive rate (FPR), specificity, positive predictive value (PPV), false negative rate (FNR), and negative predictive value (NPV). Optimization concepts are integrated to enhance the detection efficiency in web-based systems, including loss functions, gradient-based optimization, and efficient model generalization techniques. The results of k-fold cross-validation show LSTM’s higher scores for F1-score (94.6%), recall (94.7%), accuracy (94.8%), and precision (94.6%). LSTM outperformed RNN and DNN, achieving the highest accuracy, precision, specificity, and sensitivity at 94.7%, 94.3%, 98.9%, and 94.7% respectively, validating LSTM's superior generalizability for cyberattack detection tasks.

Advances in information technology have given rise to online hotel reservation options. The user review feature is an important factor during the online booking of hotels. Generally, most online hotel booking service providers provide review and rating features for assessing hotels. However, not all service providers provide rating features or recap reviews for every aspect of the hotel services offered. Therefore, we propose a method to summarise reviews based on multiple aspects, including food, room, service, and location. This method uses long short-term memory (LSTM), together with hidden layers and automation of the optimal number of hidden neurons. The F1-measure value of 75.28% for the best model was based on the fact that (i) the size of the first hidden layer is 1,200 neurons with the tanh activation function, and (ii) the size of the second hidden layer is 600 neurons with the ReLU activation function. The proposed model outperforms the baseline model (also known as standard LSTM) by 10.16%. It is anticipated that the model developed through this study can be accessed by users of online hotel booking services to acquire a review recap on more specific aspects of services offered by hotels

Deep learning is a subfield of machine learning which uses artificial neural networks that is inspired by the structure and function of the human brain. Despite being a very new approach, it has become very popular recently. Deep learning has achieved much higher success in many applications where machine learning has been successful at certain rates. In particular It is preferred in the classification of big data sets because it can provide fast and efficient results. In this study, we used Tensorflow, one of the most popular deep learning libraries to classify MNIST dataset, which is frequently used in data analysis studies. Using Tensorflow, which is an open source artificial intelligence library developed by Google, we have studied and compared the effects of multiple activation functions on classification results. The functions used are Rectified Linear Unit (ReLu), Hyperbolic Tangent (tanH), Exponential Linear Unit (eLu), sigmoid, softplus and softsign. In this Study, Convolutional Neural Network (CNN) and SoftMax classifier are used as deep learning artificial neural network. The results show that the most accurate classification rate is obtained using the ReLu activation function.

This study investigates the classification of sediment distribution and types in inland waters using Artificial Neural Network (ANN) models based on multibeam echosounder data. Multibeam Echosounder Technology (MBES) is an acoustic instrument that emits high-speed sound pulses to map the bottom of water bodies. Valuable information about sediment characteristics can be obtained by analyzing the backscattering phenomenon, which measures the acoustic intensity reflected from the water bottom. The angular response curve (ARC) method, developed by Fonseca and Calder, is employed to analyze the relationship between backscatter intensity and the angle of reflection. The ANN models in this study are trained and tested using intensity values and angular response curves obtained from multibeam echo sounders. The ANN model architecture consists of an input layer, three hidden layers, and an output layer. The sigmoid activation function is utilized in the output layer, while the ReLU activation function is applied to the input and hidden layers. Performance evaluation demonstrates that the ANN model using uncorrected data achieves remarkable accuracy, with 100% accuracy obtained in both the training and testing stages. The model exhibits a training loss value of 0.059443 and a testing loss value of 0.110030, indicating its effectiveness in capturing patterns and reducing errors. Visualizing the sediment distribution in Waduk Selorejo reveals a relatively balanced presence of Clavey sand and Sandy silt sediment types. However, noticeable differences arise between the corrected and uncorrected data, which can be attributed to the alterations made during the data correction process. The best-performing ANN model achieves a testing accuracy of 0.75, indicating that it does not perfectly predict the given data. Acknowledging the potential for prediction errors when using corrected data is important.

An artificial neural network(ANN) is a type of computing system that mimics the functioning of the neural networks in a biological brain. In this paper, an ANN has been simulated on an Field Programmable Gate Array (FPGA) for the application of handwritten digit recognition using the sigmoid and hyperbolic tangent(tanh) activation functions. Both software and hardware simulations have been carried out, using python and Verilog HDL respectively. The two activation functions were implemented on an Artix-7 FPGA. A comparison has been made between the sigmoid and tanh activation functions based on speed, accuracy, and hardware required, and it has been inferred that the tanh function is best for the application of handwritten digit recognition as it has 3% higher accuracy and uses 5 less LUTs than the sigmoid activation function.

Semiconductor optical amplifier (SOA) is a promising solution for future O-band optical amplification. However, the SOA-induced nonlinearity will affect the quality of the signals and cause bit errors. Nowadays, the neural network is a hot topic in communication networks and has been considered a practical algorithm for signals equalization. In this paper, we investigate the performance of the three types of neural networks: deep neural networks (DNN), convolutional neural network (CNN), and long short term memory (LSTM) neural networks for the compensation of the SOA-induced nonlinearity. We first compare the fitting ability of the three neural networks on the saturated response of SOA. Based on the simulation result, LSTM has the best nonlinear expressiveness for the SOA-induced nonlinearity. Subsequently, we do some experimental validations in an intensity modulation and direct-detection (IM/DD) system, where the 100 Gbit/s pulse-amplitude-modulation-4 (PAM4) signals are transmitted over 80 km at O-band using an 18 GHz electro-absorption modulated laser (EML). The bit-error-ratio (BER) results show that the cell states in LSTM play a crucial role in nonlinearity compensation. Furthermore, LSTM offers the best equalization performance and can achieve a receiver sensitivity of −18.0 dBm.

Recently, deep neural networks (DNNs) have been widely studied and achieved tremendous success in a variety of real-world applications, such as computer vision, natural language processing, medical diagnosis, and machine translation. Deep reinforcement learning (DRL), as an emerging powerful deep learning technique, combines DNNs with reinforcement learning into an interactive system that enables the agent to learn the best policy from the environment to optimize their rewards. DRL opens up many new applications in domains such as healthcare, robotics, and smart grids. With the rapid evolution of IT infrastructures, cloud computing has been witnessed as the most common computing paradigm. The underlying infrastructure of cloud computing relies on a large amount of data centers. Nowadays, with the fast development of communication technologies, such as 5G, cloud computing is now evolving into yet another new paradigm called edge computing, providing for emerging applications, especially in the Internet-of-Things. The energy efficiency issue from both "cloud" and "edge" are becoming more crucial and calls for more attention. To solve the real-world energy efficiency problems, we take advantage of the deep learning and deep reinforcement learning techniques for efficient modeling of both "edge" and "cloud" applications. On the "edge" side, wearable technologies and the Internet of Things (IoT) are becoming increasingly popular in both personal and commercial applications with the employment of the embedded system technologies. Non-Volatile Processors (NVPs) have been proposed for the intermittent power supply problem, to ensure the instant on/off for embedded systems under the unstable power supply. We proposed neural network-based prediction techniques to derive the best power extraction policy and converter parameters optimization technique for NVPs. In cloud computing, we formulated a novel optimal power management problem of data centers to minimize the total cost by proposing the long short term memory (LSTM) neural network-based method for the prediction of future data center power consumption, and further we presented a novel DRL-based hierarchical framework for solving the overall resource allocation and power management problem in cloud computing systems. Furthermore, we explored the effectiveness of the DRL-based framework for high dimensional action and state spaces problem-dynamic treatment regimes, to model real-life complexity in heterogeneous disease progression and treatment choices, to provide doctors and patients the data-driven personalized decision recommendations. Last but not least, we explored the efficiency of deep neural networks. Structured weight pruning is a representative model compression technique of DNNs to reduce both the storage and computation requirements and meanwhile accelerate inference. An automatic hyperparameter determination process is necessary due to a large number of flexible hyperparameters. We propose an automatic structured pruning framework to compress the DNNs. Our framework outperforms the prior works on automatic model compression by up to 33× in pruning rate (120× reduction in the actual parameter count) under the same accuracy. Significant inference speedup has been observed from the proposed framework on actual measurements on the smartphone.