Abstract
Advances in computer technologies in the past couple of decades has enabled data and computer scientists to employ deep neural networks to detect and analyze complex patterns in large and varied data repositories from a wide variety of application domains. Given the interest in big data and analytics coursework in most information systems departments, this paper provides a step-by-step tutorial on the design and implementation of deep neural networks using an open-source, low-code, intuitive analytics platform. This platform (KNIME) suits well for both technical and non-technical users. Although this tutorial focuses on an image processing (classification) project in the popular context of healthcare, we believe the provided guidelines, with slight modifications, can be applied to the design and implementation of various deep learning architectures built to analyze a wide variety of data types.
Recommended Citation
Davazdahemami, Behrooz; Zolbanin, Hamed; and Delen, Dursun, "Deep Learning with Minimal Coding Effort: A Tutorial on Theory and Implementation of Deep Artificial Neural Networks" (2021). Proceedings of the 2021 Pre-ICIS SIGDSA Symposium. 5.
https://aisel.aisnet.org/sigdsa2021/5