Search results for: explainable machine learning

Authors: Vincenzo Capalbo, Gianpaolo Ghiani, Emanuele Manni

Abstract:

Global e-commerce sales have reached unprecedented levels in the past few years. As this trend is only predicted to go up as we continue into the ’20s, new challenges will be faced by companies when planning and controlling e-commerce logistics. In this paper, we survey the related literature on Optimization and Machine Learning as well as on combined methodologies. We also identify the distinctive features of next-generation planning algorithms - namely scalability, model-and-run features and learning capabilities - that will be fundamental to cope with the scale and complexity of logistics in the next decade.

Keywords: e-commerce, hardware acceleration, logistics, machine learning, mixed integer programming, optimization

Procedia PDF Downloads 258

Authors: Pawel Twardowski, Maciej Tabaszewski, Jakub Czyżycki

Abstract:

The main goal of the work was to use machine learning to predict cutting-edge wear. The research was carried out while milling hardened steel with sintered carbide cutters at various cutting speeds. During the tests, cutting-edge wear was measured, and vibration acceleration signals were also measured. Appropriate measures were determined from the vibration signals and served as input data in the machine-learning process. Two approaches were used in this work. The first one involved a two-state classification of the cutting edge - suitable and unfit for further work. In the second approach, prediction of the cutting-edge state based on vibration signals was used. The obtained research results show that the appropriate use of machine learning algorithms gives excellent results related to monitoring cutting edge during the process.

Keywords: milling of hardened steel, tool wear, vibrations, machine learning

Procedia PDF Downloads 61

Authors: Yizhen Zhao, Adam S. Z. Belloum, Goncalo Maia Da Costa, Zhiming Zhao

Abstract:

Machine learning has evolved from an area of academic research to a real-word applied field. This change comes with challenges, gaps and differences exist between common practices in academic environments and the ones in production environments. Following continuous integration, development and delivery practices in software engineering, similar trends have happened in machine learning (ML) systems, called MLOps. In this paper we propose a framework that helps to streamline and introduce best practices that facilitate the ML lifecycle in an industrial setting. This framework can be used as a template that can be customized to implement various machine learning experiment. The proposed framework is modular and can be recomposed to be adapted to various use cases (e.g. data versioning, remote training on cloud). The framework inherits practices from DevOps and introduces other practices that are unique to the machine learning system (e.g.data versioning). Our MLOps practices automate the entire machine learning lifecycle, bridge the gap between development and operation.

Keywords: cloud computing, continuous development, data versioning, DevOps, industrial setting, MLOps

Procedia PDF Downloads 268

Authors: Diego Liberati

Abstract:

Standard molecular modeling is traditionally done through Schroedinger equations via the help of powerful tools helping to manage them atom by atom, often needing High Performance Computing. Here, a full portfolio of new tools, conjugating statistical inference in the so called eXplainable Artificial Intelligence framework (in the form of Machine Learning of understandable rules) to the more traditional modeling and simulation control theory of mixed dynamic logic hybrid processes, is offered as quite a general purpose even if making an example to a popular chemical physics set of problems.

Keywords: understandable rules ML, k-means, PCA, PieceWise Affine Auto Regression with eXogenous input

Procedia PDF Downloads 33

Authors: Talal Alshammari, Nasser Alshammari, Mohamed Sedky, Chris Howard

Abstract:

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

Keywords: activities of daily living, classification, internet of things, machine learning, prediction, smart home

Procedia PDF Downloads 358

Authors: Ng Liang Shen, Hau Yuan Wen

Abstract:

Arrhythmia analysis of ECG signal plays a major role in diagnosing most of the cardiac diseases. Therefore, a single arrhythmia detection of an electrocardiographic (ECG) record can determine multiple pattern of various algorithms and match accordingly each ECG beats based on Machine Learning supervised learning. These researchers used different features and classification methods to classify different arrhythmia types. A major problem in these studies is the fact that the symptoms of the disease do not show all the time in the ECG record. Hence, a successful diagnosis might require the manual investigation of several hours of ECG records. The point of this paper presents investigations cardiovascular ailment in Electrocardiogram (ECG) Signals for Cardiac Arrhythmia utilizing examination of ECG irregular wave frames via heart beat as correspond arrhythmia which with Machine Learning Pattern Recognition.

Keywords: electrocardiogram, ECG, classification, machine learning, pattern recognition, detection, QRS

Procedia PDF Downloads 376

Authors: Vishnu Pratap Singh Kirar, Madhuri Saxena

Abstract:

Advancement in sequence data generation technologies is churning out voluminous omics data and posing a massive challenge to annotate the biological functional features. With so much data available, the use of machine learning methods and tools to make novel inferences has become obvious. Machine learning methods have been successfully applied to a lot of disciplines, including computational biology and bioinformatics. Researchers in computational biology are interested to develop novel machine learning frameworks to classify the huge amounts of biological data. In this proposal, it plan to employ novel machine learning approaches to aid the understanding of how apparently innocuous mutations (in intergenic DNA and at synonymous sites) cause diseases. We are also interested in discovering novel functional sites in the genome and mutations in which can affect a phenotype of interest.

Keywords: genome wide association studies (GWAS), next generation sequencing (NGS), deep learning, omics

Procedia PDF Downloads 100

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 212

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 127

Authors: Jun Wang, Ge Zhang

Abstract:

Machine learning has been used in many areas today. It thrives at reviewing large volumes of data and identifying patterns and trends that might not be apparent to a human. Given the huge potential benefit and the amount of data available in the financial market, it is not surprising to see machine learning applied to various financial products. While future prices of financial securities are extremely difficult to forecast, we study them from a different angle. Instead of trying to forecast future prices, we apply machine learning algorithms to predict the direction of future price movement, in particular, whether a sector Exchange Traded Fund (ETF) would outperform or underperform the market in the next week or in the next month. We apply several machine learning algorithms for this prediction. The algorithms are Linear Discriminant Analysis (LDA), k-Nearest Neighbors (KNN), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Neural Networks (NN). We show that these machine learning algorithms, most notably GNB and NN, have some predictive power in forecasting out-performance and under-performance out of sample. We also try to explore whether it is possible to utilize the predictions from these algorithms to outperform the buy-and-hold strategy of the S&P 500 index. The trading strategy to explore out-performance predictions does not perform very well, but the trading strategy to explore under-performance predictions can earn higher returns than simply holding the S&P 500 index out of sample.

Keywords: machine learning, ETF prediction, dynamic trading, asset allocation

Procedia PDF Downloads 101

Authors: Senol Dogan, Gunay Karli

Abstract:

Identification of relevant publications based on a Medline query is time-consuming and error-prone. An all based process has the potential to solve this problem without any manual work. To the best of our knowledge, our study is the first to investigate the ability of machine learning to identify relevant articles accurately. 5 different machine learning algorithms were tested using 23 predictors based on several metadata fields attached to publications. We find that the Boosted model is the best-performing algorithm and its overall accuracy is 96%. In addition, specificity and sensitivity of the algorithm is 97 and 93%, respectively. As a result of the work, we understood that we can apply the same procedure to understand cancer gene expression big data.

Keywords: prediction of publications, machine learning, algorithms, bariatric surgery, comparison of algorithms, boosted, tree, logistic regression, ANN model

Procedia PDF Downloads 210

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Due to increasing cost pressure in global markets, artificial intelligence is becoming a technology that is decisive for competition. Predictive quality enables machinery and plant manufacturers to ensure product quality by using data-driven forecasts via machine learning models as a decision-making basis for test results. The use of cross-process Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: predictive quality, hydraulics, machine learning, classification, supervised learning

Procedia PDF Downloads 233

Authors: Hy Dang, Bo Mei

Abstract:

The development of machine learning methods and techniques has opened doors for investigation in many areas such as medicines, economics, finance, etc. One active research area involving machine learning is stock market prediction. This research paper tries to consider multiple techniques and methods for stock movement prediction using historical price or price factors. The paper explores the effectiveness of some deep learning frameworks for forecasting stock. Moreover, an architecture (TimeStock) is proposed which takes the representation of time into account apart from the price information itself. Our model achieves a promising result that shows a potential approach for the stock movement prediction problem.

Keywords: classification, machine learning, time representation, stock prediction

Procedia PDF Downloads 148

Authors: Asmaa El Harat, Toumi Hicham, Youssef Baddi

Abstract:

This survey delves into the complex realm of Internet of Things (IoT) security, highlighting the urgent need for effective cybersecurity measures as IoT devices become increasingly common. It explores a wide array of cyber threats targeting IoT devices and focuses on mitigating these attacks through the combined use of deep learning and machine learning algorithms, as well as edge and cloud computing paradigms. The survey starts with an overview of the IoT landscape and the various types of attacks that IoT devices face. It then reviews key machine learning and deep learning algorithms employed in IoT cybersecurity, providing a detailed comparison to assist in selecting the most suitable algorithms. Finally, the survey provides valuable insights for cybersecurity professionals and researchers aiming to enhance security in the intricate world of IoT.

Keywords: internet of things (IoT), cybersecurity, machine learning, deep learning

Procedia PDF Downloads 35

Authors: Peng Liu, Chyng Wen Tee, Xiaofei Xu

Abstract:

This paper integrates machine learning forecasting techniques into the multi-period portfolio optimization framework, enabling dynamic asset allocation based on multiple future periods. We explore both theoretical foundations and practical applications, employing diverse machine learning models for return forecasting. This comprehensive guide demonstrates the superiority of multi-period optimization over single-period approaches, particularly in risk mitigation through strategic rebalancing and enhanced market trend forecasting. Our goal is to promote wider adoption of multi-period optimization, providing insights that can significantly enhance the decision-making capabilities of practitioners and researchers alike.

Keywords: multi-period portfolio optimization, look-ahead constrained optimization, machine learning, sequential decision making

Procedia PDF Downloads 50

Authors: Leidy M. Aldana, Jorge E. Camargo

Abstract:

Adversarial Machine Learning has gained importance in recent years as Cybersecurity has gained too, especially malware, it has affected different entities and people in recent years. This paper shows a literature review about defense methods created to prevent adversarial machine learning attacks, firstable it shows an introduction about the context and the description of some terms, in the results section some of the attacks are described, focusing on detecting adversarial examples before coming to the machine learning algorithm and showing other categories that exist in defense. A method with five steps is proposed in the method section in order to define a way to make the literature review; in addition, this paper summarizes the contributions in this research field in the last seven years to identify research directions in this area. About the findings, the category with least quantity of challenges in defense is the Detection of adversarial examples being this one a viable research route with the adaptive approach in attack and defense.

Keywords: Malware, adversarial, machine learning, defense, attack

Procedia PDF Downloads 73

Authors: Jacquelyn Burkell, Jane Bailey

Abstract:

Artificial intelligence (AI) solutions deployed within the justice system face the critical task of providing acceptable explanations for decisions or actions. These explanations must satisfy the joint criteria of public and professional accountability, taking into account the perspectives and requirements of multiple stakeholders, including judges, lawyers, parties, witnesses, and the general public. This research project analyzes and integrates two existing literature on explanations in order to propose guidelines for explainable AI in the justice system. Specifically, we review three bodies of literature: (i) explanations of the purpose and function of 'explainable AI'; (ii) the relevant case law, judicial commentary and legal literature focused on the form and function of reasons for judicial decisions; and (iii) the literature focused on the psychological and sociological functions of these reasons for judicial decisions from the perspective of the public. Our research suggests that while judicial ‘reasons’ (arguably accurate descriptions of the decision-making process and factors) do serve similar explanatory functions as those identified in the literature on 'explainable AI', they also serve an important ‘justification’ function (post hoc constructions that justify the decision that was reached). Further, members of the public are also looking for both justification and explanation in reasons for judicial decisions, and that the absence of either feature is likely to contribute to diminished public confidence in the legal system. Therefore, artificially automated judicial decision-making systems that simply attempt to document the process of decision-making are unlikely in many cases to be useful to and accepted within the justice system. Instead, these systems should focus on the post-hoc articulation of principles and precedents that support the decision or action, especially in cases where legal subjects’ fundamental rights and liberties are at stake.

Keywords: explainable AI, judicial reasons, public accountability, explanation, justification

Procedia PDF Downloads 127

Authors: Fatima Al-Aswadi, Chan Yong

Abstract:

With the large volume of unstructured data that increases day by day on the web, the motivation of representing the knowledge in this data in the machine processable form is increased. Ontology is one of the major cornerstones of representing the information in a more meaningful way on the semantic Web. The goal of Ontology learning from text is to elicit and represent domain knowledge in the machine readable form. This paper aims to give a follow-up review on the ontology learning systems from text and some of their defects. Furthermore, it discusses how far the ontology learning process will enhance in the future.

Keywords: concept discovery, deep learning, ontology learning, semantic relation, semantic web

Procedia PDF Downloads 525

Authors: Amy M. Kwon

Abstract:

Support vector machine (SVM) is a well-known algorithm in machine learning due to its superior performance, and it also functions well in multiple-instance (MI) problems. Our study proposes a schematic algorithm to select instances based on Hausdorff distance, which can be adapted to SVMs as input vectors under the MI setting. Based on experiments on five benchmark datasets, our strategy for adapting representation outperformed in comparison with original approach. In addition, task execution times (TETs) were reduced by more than 80% based on MissSVM. Hence, it is noteworthy to consider this representation adaptation to SVMs under MI-setting.

Keywords: support vector machine, Margin, Hausdorff distance, representation selection, multiple-instance learning, machine learning

Procedia PDF Downloads 36

Authors: Shohoni Mahabub

Abstract:

Health Information Systems (HIS) are essential to contemporary healthcare; nonetheless, they frequently encounter challenges such as data fragmentation, inefficiencies, and an absence of real-time analytics. The advent of machine learning (ML) and artificial intelligence (AI) provides a revolutionary potential to address these difficulties via AI-driven data fusion ecosystems. These ecosystems integrate many health data sources, including electronic health records (EHRs), wearable devices, and genetic data, with sophisticated machine learning techniques such as natural language processing (NLP) and predictive analytics to produce actionable insights. Through the integration of strong data intake layers, secure interoperability protocols, and privacy-preserving models, these ecosystems provide individualized treatment, early illness diagnosis, and enhanced operational efficiency. This paradigm change enhances clinical decision-making and rectifies systemic inefficiencies in healthcare delivery. Nonetheless, adoption presents problems such as data privacy concerns, ethical considerations, and scalability constraints. The study examines options such as federated learning for safe, decentralized data sharing, explainable AI for transparency, and cloud-based infrastructure for scalability to address these issues. These ecosystems aim to address health equity disparities, particularly in resource-limited environments, and improve public health surveillance, notably in pandemic response initiatives. This article emphasizes the revolutionary potential of AI-driven data fusion ecosystems in redefining Health Information Systems by providing an implementation roadmap and showcasing successful deployment case studies. The suggested method promotes a cooperative initiative among legislators, healthcare professionals, and technology to establish a cohesive, efficient, and patient-centric healthcare model.

Keywords: AI-powered healthcare systems, data fusion ecosystem, predictive analytics, digital health interoperability

Procedia PDF Downloads 16

Authors: Salahaeddine Sbai

Abstract:

Air quality analysis using machine learning models is a method employed to assess and predict air pollution levels. This approach leverages the capabilities of machine learning algorithms to analyze vast amounts of air quality data and extract valuable insights. By training these models on historical air quality data, they can learn patterns and relationships between various factors such as weather conditions, pollutant emissions, and geographical features. The trained models can then be used to predict air quality levels in real-time or forecast future pollution levels. This application of machine learning in air quality analysis enables policymakers, environmental agencies, and the general public to make informed decisions regarding health, environmental impact, and mitigation strategies. By understanding the factors influencing air quality, interventions can be implemented to reduce pollution levels, mitigate health risks, and enhance overall air quality management. Climate change is having significant impacts on Morocco, affecting various aspects of the country's environment, economy, and society. In this study, we use some machine learning models under python environment to predict and analysis air quality change over North of Morocco to evaluate the climate change impact on agriculture.

Keywords: air quality, machine learning models, pollution, pollutant emissions

Procedia PDF Downloads 93

Authors: Medjadj Tarek, Ghribi Hayet

Abstract:

This study aims to develop a flood sensitivity assessment tool using machine learning (ML) techniques and geographic information system (GIS). The importance of this study is integrating the geographic information systems (GIS) and machine learning (ML) techniques for mapping flood risks, which help decision-makers to identify the most vulnerable areas and take the necessary precautions to face this type of natural disaster. To reach this goal, we will study the case of the city of M'sila, which is among the areas most vulnerable to floods. This study drew a map of flood-prone areas based on the methodology where we have made a comparison between 3 machine learning algorithms: the xGboost model, the Random Forest algorithm and the K Nearest Neighbour algorithm. Each of them gave an accuracy respectively of 97.92 - 95 - 93.75. In the process of mapping flood-prone areas, the first model was relied upon, which gave the greatest accuracy (xGboost).

Keywords: Geographic information systems (GIS), machine learning (ML), emergency mapping, flood disaster management

Procedia PDF Downloads 95

Authors: Ioannis P. Panapakidis, Marios N. Moschakis

Abstract:

The Greek Energy Market is structured as a mandatory pool where the producers make their bid offers in day-ahead basis. The System Operator solves an optimization routine aiming at the minimization of the cost of produced electricity. The solution of the optimization problem leads to the calculation of the System Marginal Price (SMP). Accurate forecasts of the SMP can lead to increased profits and more efficient portfolio management from the producer`s perspective. Aim of this study is to provide a comparative analysis of various machine learning models such as artificial neural networks and neuro-fuzzy models for the prediction of the SMP of the Greek market. Machine learning algorithms are favored in predictions problems since they can capture and simulate the volatilities of complex time series.

Keywords: deregulated energy market, forecasting, machine learning, system marginal price

Procedia PDF Downloads 216

Authors: Jeff Clarine, Chang-Shyh Peng, Daisy Sang

Abstract:

Bioassay is the measurement of the potency of a chemical substance by its effect on a living animal or plant tissue. Bioassay data and chemical structures from pharmacokinetic and drug metabolism screening are mined from and housed in multiple databases. Bioassay prediction is calculated accordingly to determine further advancement. This paper proposes a four-step preprocessing of datasets for improving the bioassay predictions. The first step is instance selection in which dataset is categorized into training, testing, and validation sets. The second step is discretization that partitions the data in consideration of accuracy vs. precision. The third step is normalization where data are normalized between 0 and 1 for subsequent machine learning processing. The fourth step is feature selection where key chemical properties and attributes are generated. The streamlined results are then analyzed for the prediction of effectiveness by various machine learning algorithms including Pipeline Pilot, R, Weka, and Excel. Experiments and evaluations reveal the effectiveness of various combination of preprocessing steps and machine learning algorithms in more consistent and accurate prediction.

Keywords: bioassay, machine learning, preprocessing, virtual screen

Procedia PDF Downloads 276

Authors: Anne-Lena Kampen, Øivind Kure

Abstract:

Machine learning (ML) can be implemented in Wireless Sensor Networks (WSNs) as a central solution or distributed solution where the ML is embedded in the nodes. Embedding improves privacy and may reduce prediction delay. In addition, the number of transmissions is reduced. However, quality factors such as prediction accuracy, fault detection efficiency and coordinated control of the overall system suffer. Here, we discuss and highlight the trade-offs that should be considered when choosing between embedding and centralized ML, especially for multihop networks. In addition, we present estimations that demonstrate the energy trade-offs between embedded and centralized ML. Although the total network energy consumption is lower with central prediction, it makes the network more prone for partitioning due to the high forwarding load on the one-hop nodes. Moreover, the continuous improvements in the number of operations per joule for embedded devices will move the energy balance toward embedded prediction.

Keywords: central machine learning, embedded machine learning, energy consumption, local machine learning, wireless sensor networks, WSN

Procedia PDF Downloads 156

Authors: Prachi Desai, Ankita Gandhi, Mitali Acharya

Abstract:

Rainfall forecast is mainly used for predictions of rainfall in a specified area and determining their future rainfall conditions. Rainfall is always a global issue as it affects all major aspects of one's life. Agricultural, fisheries, forestry, tourism industry and other industries are widely affected by these conditions. The studies have resulted in insufficient availability of water resources and an increase in water demand in the near future. We already have a new forecast system that uses the deep Convolutional Neural Network (CNN) to forecast monthly rainfall and climate changes. We have also compared CNN against Artificial Neural Networks (ANN). Machine Learning techniques that are used in rainfall predictions include ARIMA Model, ANN, LR, SVM etc. The dataset on which we are experimenting is gathered online over the year 1901 to 20118. Test results have suggested more realistic improvements than conventional rainfall forecasts.

Keywords: ANN, CNN, supervised learning, machine learning, deep learning

Procedia PDF Downloads 205

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 139

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 97

Authors: Fuad M. Alkoot

Abstract:

The main component of a machine learning system is the classifier. Classifiers are mathematical models that can perform classification tasks for a specific application area. Additionally, many classifiers are combined using any of the available methods to reduce the classifier error rate. The benefits gained from the combination of multiple classifier designs has motivated the development of diverse approaches to multiple classifiers. We aim to investigate using fractal geometry to develop an improved classifier combiner. Initially we experiment with measuring the fractal dimension of data and use the results in the development of a combiner strategy.

Keywords: fractal geometry, machine learning, classifier, fractal dimension

Procedia PDF Downloads 220

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 59