The proceedings contain 48 papers. The topics discussed include: a taxonomy of foundation model-based systems through the lens of software architecture;investigating the impact of SOLID design principles on machine le...
ISBN:
(纸本)9798400705915
The proceedings contain 48 papers. The topics discussed include: a taxonomy of foundation model-based systems through the lens of software architecture;investigating the impact of SOLID design principles on machinelearning code understanding;identifying architectural design decisions for achieving green ML serving;modeling resilience of collaborative ai systems;an exploratory study of V-model in building ML-enabled software: a systems engineering perspective;engineering challenges in industrial AI;what about the data? a mapping study on dataengineering for AI systems;unmasking data secrets: an empirical investigation into data smells and their impact on data quality;an exploratory study of dataset and model management in open source machinelearning applications;developer experiences with a contextualized AI coding assistant: usability, expectations, and outcomes;innovating translation: lessons learned from BWX generative language engine;and towards a responsible AI metrics catalogue: a collection of metrics for AI accountability.
This paper focuses on employing various machinelearning algorithms- K Nearest Neighbors and Extra Trees. By analyzing patterns in behavioral, physiological, and contextual data, the model aims to identify early indic...
详细信息
machinelearning applied to fire alarm systems is an increasingly common optimization problem. In this paper, a method based on comprehensive evaluation and machinelearning is proposed. Firstly, relying on the litera...
详细信息
The widespread adoption of deep learning has led to recurring data security issues. Consequently, there is an even greater need to preserve data privacy, resulting in data becoming increasingly challenging to share an...
详细信息
ISBN:
(纸本)9798350388732;9798350388725
The widespread adoption of deep learning has led to recurring data security issues. Consequently, there is an even greater need to preserve data privacy, resulting in data becoming increasingly challenging to share and creating what are often referred to as 'data islands', which FL effectively addresses. FL, a new deep learning paradigm, enables collaborative model training across multiple terminals distributively, facilitating data sharing and machinelearning modeling while ensuring robust data privacy protection. Individual client could be backdoor attacked by poisoning the data. This paper introduces a robust defense method for backdoor attacks based on reverse trigger engineering, model hardening, and attention distillation mechanisms. In this paper, we conduct a lot of experiments on different classical datasets with different settings, and the results demonstrates that the proposed strategy improve robustness by reducing the attack success rate while preserving main task accuracy.
The branch of mathematics known as 39;linear algebra39; deals with vectors, matrices, and linear transformations. It is useful in a variety of disciplines, including computer science, physics, engineering, and mac...
详细信息
machinelearning models are increasingly utilized to predict ADHD based on various features and behavioural indicators. These models analyze demographic, clinical, and behavioural data to distinguish individuals with ...
详细信息
To better cater to the needs of job seekers and provide enhanced career development directions, this study proposes a novel employment guidance and career planning system integrating machinelearning algorithms, along...
详细信息
Power load forecasting is one of the important tasks in controlling system costs, and accurate and effective load forecasting can reasonably arrange the operating status of power grid generators. machinelearning, as ...
详细信息
With an emphasis on the incorporation of the Wasserstein Generative Adversarial Network (WGAN) algorithm, this study examines the revolutionary potential of AI-Powered Predictive Cybersecurity in detecting new risks u...
详细信息
machinelearning (ML) - enabled systems capture new frontiers of industrial use. The development of such systems is becoming a priority course for many vendors due to the unique capabilities of Artificial Intelligence...
详细信息
ISBN:
(纸本)9798400705915
machinelearning (ML) - enabled systems capture new frontiers of industrial use. The development of such systems is becoming a priority course for many vendors due to the unique capabilities of Artificial Intelligence (AI) techniques. The current trend today is to integrate ML functionality into complex systems as architectural components. There are a lot of relevant challenges associated with this strategy in terms of the overall system architecture and in the context of development workflow (MLOps). The probabilistic nature, crucial dependency on data, and work in an environment of high uncertainty do not allow software engineers to apply traditional software development methodologies. As a result, there is a community request to systematize the most relevant experience in building software architectures with ML components, to create new approaches to organizing the process of developing ML-enabled systems, and to build new models for assessing the system quality. Our research contributes to all mentioned directions and aims to create a methodology for the efficient implementation of ML-enabled software and AI components. The results of the research can be used in the design and development in industrial settings, as well as a basis for further studies in the research field, which is of both practical and scientific value.
暂无评论