Related papers: A Collaborative and Pattern-Based Training Approac…

Federated machine learning is growing fast in academia and industries as a solution to solve data hungriness and privacy issues in machine learning. Being a widely distributed system, federated machine learning requires various system…

An instructor teaching a course on Software Architecture needs to be more reflective to engage students productively in the learning activities. In this reflective essay, the author identifies a few decisive moments referred to as…

Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image…

The article highlights the promising ways of providing access to the cloud-based learning and research software in higher educational institutions. It is emphasized that the cloud computing services implementation is the actual trend of…

This paper proposes a reinforcement learning framework for performance-driven structural design that combines bottom-up design generation with learned strategies to efficiently search large combinatorial design spaces. Motivated by the…

Progress in machine learning (ML) has been fueled by scaling neural network models. This scaling has been enabled by ever more heroic feats of engineering, necessary for accommodating ML approaches that require high bandwidth communication…

In this paper we presented a novel constructive approach for training deep neural networks using geometric approaches. We show that a topological covering can be used to define a class of distributed linear matrix inequalities, which in…

Case study-based learning has been successfully integrated into various courses, including software engineering education. In the context of software design courses, the use of case studies often entails sharing of real successful or failed…

The software patterns provide building blocks to the design and implementation of a software system, and try to make the software engineering to progress from experience to science. The software patterns were made famous because of the…

In this paper, we investigate collaborative active learning, a paradigm in which multiple collaborators explore a new domain by leveraging their combined machine learning capabilities without disclosing their existing data and models.…

What is the relationship between model architecture and the ability to perform in-context learning? In this empirical study, we take the first steps toward answering this question. We evaluate thirteen model architectures capable of causal…

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…

In particular, large-scale deep learning and artificial intelligence model training uses a lot of computational power and energy, so it poses serious sustainability issues. The fast rise in model complexity has resulted in exponential…

The rapid emergence of generative AI tools is transforming the way software is developed. Consequently, software engineering education must adapt to ensure that students not only learn traditional development methods but also understand how…

Higher education courses teaching about agile software development (ASD) have increased in commonality as the ideas behind the Agile Manifesto became more commonplace in the industry. However, a lot of the literature on how ASD is applied…

Learning by observation can be of key importance whenever agents sharing similar features want to learn from each other. This paper presents an agent architecture that enables software agents to learn by direct observation of the actions…

Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown preliminary effectiveness in…

With the recent rapid increase in digitization across all major industries, acquiring programming skills has increased the demand for introductory programming courses. This has further resulted in universities integrating programming…

Cognitive biases distort the process of rational decision-making, including architectural decision-making. So far, no method has been empirically proven to reduce the impact of cognitive biases on architectural decision-making. We conducted…

Advancement in information system leads organizations to apply e-learning system to train their employees in order to enhance its performance. In this respect, applying web based training will enable the organization to train their…