V-ML: VISUALIZATIONS FOR MACHINE LEARNING
Ankit Katre, Viraj Chogle, Pratyusha Parashar · Journal of Emerging Technologies and Innovative Research · 2021
Data visualization is a quite new and promising field in computer science. It uses computer graphic effects to reveal the patterns, trends and relationships out of datasets. However, there is a dearth of visualization tools for deep learning algorithms along with the details buried in the algorithms that are properly accounted for. Gaining an understanding of this technology is somewhat difficult. While the theory is important, it is also helpful for novices and users not familiar with machine learning to develop an intuitive feel for the effect of different hyperparameters and structural variations. We propose a visualization tool for some of these algorithms along with the description of “intricate details” that often result in novices describing them as ‘black boxes’.