A theory of formal synthesis via inductive learning

Growth in system complexity increases the need for automated techniques dedicated to different log analysis tasks such as Log-based Anomaly Detection (LAD). The latter has been widely addressed in the literature, mostly by means of a variety of deep learning techniques. However, despite their many advantages, that focus on deep learning techniques is somewhat arbitrary as traditional Machine Learning (ML) techniques may perform well in many cases, depending on the context and datasets. In the same vein, semi-supervised techniques deserve the same attention as supervised techniques since the former have clear practical advantages. Further, current evaluations mostly rely on the assessment of detection accuracy. However, this is not enough to decide whether or not a specific ML technique is suitable to address the LAD problem in a given context. Other aspects to consider include training and prediction times as well as the sensitivity to hyperparameter tuning, which in practice matters to engineers. In this paper, we present a comprehensive empirical study, in which we evaluate a wide array of supervised and semi-supervised, traditional and deep ML techniques w.r.t. four evaluation criteria: detection accuracy, time performance, sensitivity of detection accuracy and time performance to hyperparameter tuning. Our goal is to provide much stronger and comprehensive evidence regarding the relative advantages and drawbacks of alternative techniques for LAD. The experimental results show that supervised traditional and deep ML techniques fare similarly in terms of their detection accuracy and prediction time on most of the benchmark datasets considered in our study. Moreover, overall, sensitivity analysis to hyperparameter tuning with respect to detection accuracy shows that supervised traditional ML techniques are less sensitive than deep learning techniques. Further, semi-supervised techniques yield significantly worse detection accuracy than supervised techniques.

In recent years, machine learning has been vastly used in many scientific experiments to analyze and predict the data [1]. Since there are many types of machine learning and each of them has additional further branches, it's necessary to understand which one can predict or summarize the data with more accuracy. This paper mainly focuses on traditional machine learning and active learning. To compare the effects of these two types of machine learning, the paper uses a dataset about using metal oxide semiconductor (MOX) to measure the concentration of carbon monoxide (CO). In the first part, the paper tests the accuracy of predicting CO concentration with 3 types of traditional machine learning: Decision Tree, Random Forest and K-nearest neighbors. In the second part, the paper chooses the traditional machine learning which has the best performance in the first part and compares the accuracy of it with the active learning on predicting CO concentration. The result is that the classification accuracy of Random Forest is 0.625, which is the highest among them. And active learning is generally better than traditional machine learning when training samples are small, and they have a similar accuracy when the training sample is enough.

Program synthesis is the mechanized construction of software, dubbed ‘self-writing code’. Synthesis tools relieve the programmer from thinking about how the problem is to be solved; instead, the programmer only provides a description of what is to be achieved. Given a specification of what the program should do, the synthesizer generates an implementation that provably satisfies this specification. From a logical point of view, a program synthesizer is a solver for second-order existential logic. Owing to the expressiveness of second-order logic, program synthesis has an extremely broad range of applications. We survey some of these applications as well as recent trends in the algorithms that solve the program synthesis problem. In particular, we focus on an approach that has raised the profile of program synthesis and ushered in a generation of new synthesis tools, namely counter-example-guided inductive synthesis (CEGIS). We provide a description of the CEGIS architecture, followed by recent algorithmic improvements. We conjecture that the capacity of program synthesis engines will see further step change, in a manner that is transparent to the applications, which will open up an even broader range of use-cases.This article is part of the themed issue ‘Verified trustworthy software systems’.

Cochlear implants substantially improve spoken language in children with severe to profound sensorineural hearing loss, yet outcomes remain more variable than in children with healthy hearing. This variability cannot be reliably predicted for individual children using age at implant or residual hearing. Development of an artificial intelligence clinical tool to predict which patients will exhibit poorer improvements in language skills may enable an individualized approach to improve language outcomes. To compare the accuracy of traditional machine learning (ML) with deep transfer learning (DTL) algorithms to predict post-cochlear implant spoken language development in children with bilateral sensorineural hearing loss using a binary classification model of high vs low language improvers. This multicenter diagnostic study enrolled children from English-, Spanish-, and Cantonese-speaking families across 3 independent clinical centers in the US, Australia, and Hong Kong. A total of 278 children with cochlear implants were enrolled from July 2009 to March 2022 with 1 to 3 years of post-cochlear implant outcomes data. All children underwent pre-cochlear implant 3-dimensional volumetric brain magnetic resonance imaging (MRI). ML and DTL algorithms were trained to predict high vs low language improvers in children with cochlear implants using neuroanatomical features from presurgical brain MRI. Data were analyzed from August 2023 to April 2025. Cochlear implants. The accuracy, sensitivity, and specificity of prediction models based on brain neuroanatomic features using traditional ML and DTL learning. Of 278 children, 137 (49.3%) were female, and the mean (SD) age at cochlear implant was 25.7 (18.8) months. DTL prediction models using bilinear attention-based fusion strategy achieved an accuracy of 92.39% (95% CI, 90.70%-94.07%), sensitivity of 91.22% (95% CI, 89.98%-92.47%), specificity of 93.56% (95% CI, 90.91%-96.21%), and area under the curve of 0.98 (95% CI, 0.97-0.99). DTL outperformed traditional ML models in all outcome measures. The results of this diagnostic study suggest that DTL prediction of language improvement on the individual child level using neuroanatomic features demonstrates greater accuracy, sensitivity, and specificity than traditional ML prediction. DTL was substantially improved by direct capture of discriminative and task-specific information that are advantages of representation learning enabled by this approach vs ML. The results support the feasibility of a single DTL prediction model for language prediction for children served by cochlear implant programs worldwide. Prediction of low improvement may enable targeted early and customized intervention to improve language.

This book explores the significant role of granular computing in advancing machine learning towards in-depth processing of big data. It begins by introducing the main characteristics of big data, i.e., the five Vs—Volume, Velocity, Variety, Veracity and Variability. The book explores granular computing as a response to the fact that learning tasks have become increasingly more complex due to the vast and rapid increase in the size of data, and that traditional machine learning has proven too shallow to adequately deal with big data. Some popular types of traditional machine learning are presented in terms of their key features and limitations in the context of big data. Further, the book discusses why granular-computing-based machine learning is called for, and demonstrates how granular computing concepts can be used in different ways to advance machine learning for big data processing. Several case studies involving big data are presented by using biomedical data and sentiment data, in order to show the advances in big data processing through the shift from traditional machine learning to granular-computing-based machine learning. Finally, the book stresses the theoretical significance, practical importance, methodological impact and philosophical aspects of granular-computing-based machine learning, and suggests several further directions for advancing machine learning to fit the needs of modern industries.

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

We present a sound and automated approach to synthesize safe digital feedback controllers for physical plants represented as linear, time-invariant models. Models are given as dynamical equations with inputs, evolving over a continuous state space and accounting for errors due to the digitization of signals by the controller. Our counterexample guided inductive synthesis (CEGIS) approach has two phases: We synthesize a static feedback controller that stabilizes the system but that may not be safe for all initial conditions. Safety is then verified either via BMC or abstract acceleration; if the verification step fails, a counterexample is provided to the synthesis engine and the process iterates until a safe controller is obtained. We demonstrate the practical value of this approach by automatically synthesizing safe controllers for intricate physical plant models from the digital control literature.

The Turkish Music Emotion Dataset in the CL database is a dataset for music emotion classification, which contains many music samples and their corresponding emotion labels. This paper presents a comparative analysis of the performance of the traditional random forest machine learning model and the XGBoost model on the given dataset. The findings indicate that the traditional random forest machine learning model outperforms the XGBoost model in terms of accuracy, accuracy, and recall rate. The traditional random forest machine learning model achieves an accuracy of 80.8%, whereas the XGBoost model achieves an accuracy of 75%. The recall rate of the traditional random forest machine learning model is 80.8%, whereas the recall rate of the XGBoost model is 77.2%. The traditional random forest machine learning model achieved an F1 score of 80.5%, whereas the XGBoost model attained an F1 score of 75.3%. The comprehensive evaluation of the XGBoost model outperforms the traditional random forest machine learning model. Generally, the traditional random forest machine learning model demonstrates strong performance in the domain of music emotion classification. It exhibits favorable qualities such as robustness and interpretability, and possesses the ability to effectively handle noise and missing data. The XGBoost model, on the other hand, can be trained and predicted quickly, with high accuracy and generalization ability. Therefore, in practical application, it is necessary to select the appropriate model according to the specific situation, and optimize and adjust it to obtain the best classification effect.

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

Large language models (LLMs) are increasingly adopted in educational contexts to provide personalized support to students and teachers. The unprecedented capacity of LLM‐based applications to understand and generate natural language can potentially improve instructional effectiveness and learning outcomes, but the integration of LLMs in education technology has renewed concerns over algorithmic bias, which may exacerbate educational inequalities. Building on prior work that mapped the traditional machine learning life cycle, we provide a framework of the LLM life cycle from the initial development of LLMs to customizing pre‐trained models for various applications in educational settings. We explain each step in the LLM life cycle and identify potential sources of bias that may arise in the context of education. We discuss why current measures of bias from traditional machine learning fail to transfer to LLM‐generated text (eg, tutoring conversations) because text encodings are high‐dimensional, there can be multiple correct responses, and tailoring responses may be pedagogically desirable rather than unfair. The proposed framework clarifies the complex nature of bias in LLM applications and provides practical guidance for their evaluation to promote educational equity. Practitioner notes What is already known about this topic The life cycle of traditional machine learning (ML) applications which focus on predicting labels is well understood. Biases are known to enter in traditional ML applications at various points in the life cycle, and methods to measure and mitigate these biases have been developed and tested. Large language models (LLMs) and other forms of generative artificial intelligence (GenAI) are increasingly adopted in education technologies (EdTech), but current evaluation approaches are not specific to the domain of education. What this paper adds A holistic perspective of the LLM life cycle with domain‐specific examples in education to highlight opportunities and challenges for incorporating natural language understanding (NLU) and natural language generation (NLG) into EdTech. Potential sources of bias are identified in each step of the LLM life cycle and discussed in the context of education. A framework for understanding where to expect potential harms of LLMs for students, teachers, and other users of GenAI technology in education, which can guide approaches to bias measurement and mitigation. Implications for practice and/or policy Education practitioners and policymakers should be aware that biases can originate from a multitude of steps in the LLM life cycle, and the life cycle perspective offers them a heuristic for asking technology developers to explain each step to assess the risk of bias. Measuring the biases of systems that use LLMs in education is more complex than with traditional ML, in large part because the evaluation of natural language generation is highly context‐dependent (eg, what counts as good feedback on an assignment varies). EdTech developers can play an important role in collecting and curating datasets for the evaluation and benchmarking of LLM applications moving forward.

In online courses, discussion forums play a key role in enhancing student interaction with peers and instructors. Due to large enrolment sizes, instructors often struggle to respond to students in a timely manner. To address this problem, both traditional Machine Learning (ML) (e.g., Random Forest) and Deep Learning (DL) approaches have been applied to classify educational forum posts (e.g., those required urgent responses vs. that did not). However, there lacks an in-depth comparison between these two kinds of approaches. To better guide people to select an appropriate model, we aimed at providing a comparative study on the effectiveness of six frequently-used traditional ML and DL models across a total of seven different classification tasks centering around two datasets of educational forum posts. Through extensive evaluation, we showed that (i) the up-to-date DL approaches did not necessarily outperform traditional ML approaches; (ii) the performance gap between the two kinds of approaches can be up to 3.68% (measured in F1 score); (iii) the traditional ML approaches should be equipped with carefully-designed features, especially those of common importance across different classification tasks. Based on the derived findings, we further provided insights to help instructors and educators construct effective classifiers for characterizing educational forum discussions, which, ultimately, would enable them to provide students with timely and personalized learning support.

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.

Background Artificial intelligence (AI) has revolutionized diagnostic radiology by improving accuracy, efficiency, and clinical decision-making. While numerous systematic reviews and meta-analyses have evaluated the performance of AI-based techniques, particularly traditional machine learning (ML) and deep learning (DL) models, a comprehensive synthesis of this evidence is lacking. An umbrella review is necessary to integrate and compare findings across various imaging applications, offering the highest level of evidence to inform clinical practice and policy. Objective This umbrella review aims to compare the diagnostic performance of traditional machine learning and deep learning methods in radiology by synthesizing evidence from existing systematic reviews and meta-analyses. Methods A systematic literature search was conducted in PubMed, Scopus, Web of Science, and Cochrane Library for systematic reviews and meta-analyses published between 2018 and 2024. Only peer-reviewed reviews evaluating diagnostic applications of AI in radiology were included. Methodological quality was assessed using the AMSTAR 2 tool, and risk of bias was evaluated using ROBIS. Results Seven systematic reviews and meta-analyses were included. Across multiple imaging domains—such as breast cancer screening, spinal stenosis, and tumor grading—deep learning consistently outperformed traditional ML in diagnostic accuracy and sensitivity. Evidence quality was rated moderate to high, though variability in reporting and a lack of external validation were noted. Explainability features in DL models were underutilized and poorly evaluated. Conclusion This umbrella review confirms the superior diagnostic performance of deep learning methods over traditional ML in radiology. Future research should prioritize model transparency, real-world validation, and standardization in clinical implementation.

Programming modern heterogeneous systems is becoming more and more challenging due to their complexity. To simplify software development for such architectures, more advanced compilers are being designed. Such compilers automatically optimize code and hide the complexity of the target heterogeneous architecture from the developer. An example of problems that these compilers need to solve is to decide whether to map (run) a piece of code on CPU or GPU (Graphics Processing Unit). State-of-the-art compilers use accurate optimization heuristics to solve such problems and decide about how to optimize a code automatically. Traditional machine learning and Deep Learning approaches have both been used to build such heuristics. While traditional machine learning is well suited for training on small datasets, it is not well suited for extracting a set of high-quality features, on the other hand, deep learning can automatically extract features, but it needs a large amount of data to get satisfactory results.In this paper, we propose a new machine-learning-based model that allows a compiler to automatically decide whether to map a piece of code to CPU or GPU. Our model uses traditional machine learning and deep learning by exploiting the advantages of each of them. We show that our proposed model, which requires a small amount of data and training time, matches and outperforms state-of-the-art pre-trained deep learning models that require large amounts of data.

ObjectivesTo determine the extent to which current Large Language Models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated various factors that can impact their adoption, including overall performance, calibration, fairness, and resilience to privacy protections that reduce data fidelity.Materials and MethodsWe evaluated GPT-3.5, GPT-4, and ML (as gradient-boosting trees) on clinical prediction tasks in EHR data from Vanderbilt University Medical Center and MIMIC IV. We measured predictive performance with AUROC and model calibration using Brier Score. To evaluate the impact of data privacy protections, we assessed AUROC when demographic variables are generalized. We evaluated algorithmic fairness using equalized odds and statistical parity across race, sex, and age of patients. We also considered the impact of using in-context learning by incorporating labeled examples within the prompt.ResultsTraditional ML (AUROC: 0.847, 0.894 (VUMC, MIMIC)) substantially outperformed GPT-3.5 (AUROC: 0.537, 0.517) and GPT-4 (AUROC: 0.629, 0.602) (with and without in-context learning) in predictive performance and output probability calibration (Brier Score (ML vs GPT-3.5 vs GPT-4): 0.134 versus 0.384 versus 0.251, 0.042 versus 0.06 versus 0.219). Traditional ML is more robust than GPT-3.5 and GPT-4 to generalizing demographic information to protect privacy. GPT-4 is the fairest model according to our selected metrics but at the cost of poor model performance.ConclusionThese findings suggest that LLMs are much less effective and robust than locally-trained ML for clinical prediction tasks, but they are getting better over time.