2019-2020 IEEE Projects on Machine Learning
In the last years, the design, implementation and delivery of web-based education systems, such as the Learning Management Systems, has grown exponentially, thanks to the fact that neither students nor teachers are bound to a specific location. Moreover, this form of computer-based education is virtually independent of any specific hardware platform and, as an important consequence, these systems are storing a large amount of educational data that could be used to improve the learning, the teaching and the administration processes. Extracting useful information represents a new challenge involving Machine Learning, Data Mining and Learning Analytics. Machine Learning is concerned with a large number of algorithms that improve their performance with experience, in many fields of research such as those learning contexts where students interact with learning systems leaving useful tracks. Educational Data Mining is the science of extracting useful information from the large data sets or databases containing students interactions during their learning, for example in a virtual environment. Finally, Learning Analytics is a set of steps for understanding and optimizing the whole learning process, together with the environment in which it occurs. It is composed by several steps, where the first is strictly related to Educational Data Mining for capturing data by some machine learning algorithms. In this paper, we discuss the intersections and correlations between these three areas of research, trying to discuss their relationships and steps to give a useful overview on the learning processes from different points of views. Different models are introduced and discussed.
2019 IEEE Projects on Machine Learning
Applying machine learning techniques to solve production problems within electronic design automation is complex.
This is because production engineering applications have accuracy, scalability, complexity, verifiability, and usability
requirements that are not met by traditional machine learning approaches. These additional challenges are often not well understood
or adequately solved in practice, which causes production machine learning approaches to fail. This invited paper examines these engineering-specific
challenges and presents some effective solutions
based on Solido's experience developing a suite of successful applied machine learning solutions for EDA over the past twelve years.