EXPLODE – a new model of exploratory learning environment for neural networks to improve learning outcomes

ABSTRACT

The paper proposes EXPLODE, a new model of exploratory learning environment for teaching and learning neural networks. The EXPLODE model is about pedagogically instrumenting a software development environment to transform it into an exploratory learning environment for neural networks. Such an environment is particularly aimed for students who are skilled in programming and meets typical challenges in teaching and learning neural networks, related to the lack of prerequisite knowledge in mathematics. By providing such students with a familiar learning environment and allowing them to programmatically experiment with neural networks, the EXPLODE model aims at improving the students’ learning outcomes and learning experience. The effectiveness of the model was evaluated in an experimental study with 77 final-year IT students. The results have shown that the students from the experimental group, that is, those who were exposed to the EXPLODE model, scored higher on the knowledge test. Furthermore, the perceived learning experience of the experimental group was better than that of the control group. The results have also suggested that the proposed model helps students better understand learning topics that require practical experience and facilitates a deeper understanding of the internal operations of neural networks.

KEYWORDS:

• Neural networks
• exploratory learning
• learning environment
• simulation
• educational technology

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia under project number 47003.

Notes on contributors

Zoran Sevarac

Dr. Zoran Sevarac is an associate professor at the Department of Software Engineering at the University of Belgrade. He is a researcher at Laboratory for Artificial Intelligence at the same department. His interests include neural networks, software engineering, and educational technologies.

Jelena Jovanovic

Dr. Jelena Jovanović is a Professor at the Department of Software Engineering, University of Belgrade. Her broad research interests include semantic technologies, learning analytics, and technology-enhanced learning. She is particularly interested in combining human and machine intelligence for a better understanding of the learning processes and making thus obtained insights actionable through appropriate instructional interventions.

Vladan Devedzic

Dr. Vladan Devedzic is a Professor of Software Engineering at the University of Belgrade. His long-term professional objective is to bring close together ideas from the broad fields of intelligent systems and software engineering. His current interests include software engineering, programming education, intelligent software systems, and technology-enhanced learning.

Bojan Tomic

Dr. Bojan Tomić is an associate professor at the Faculty of organizational sciences, University of Belgrade. His research focuses on technology-enhanced learning, software engineering, artificial intelligence, rule-based systems and also on the use of digital credentials in higher education.