The Role of Visualization in Machine Learning/Artificial Intelligence
Problem
Visual Analytics is a process supporting information discovery through a combination of automated analysis methods, interactive visual interfaces, human perception, and reasoning. It is an effective solution to make sense of the data. A possible automatic analysis method is supervised and unsupervised Machine Learning. More advanced methods are explored in the scope of the Cluster of Excellence Bilateral Artificial Intelligence (BilAI), where we are aiming to intertwine symbolic and sub-symbolic AI as well as visual approaches, to gain insights into complex heterogeneous data.
Aim
You should provide a systematic overview of existing approaches in scientific literature that use visualization in selected Machine Learning or other Artificial Intelligence approaches.
Other information
Starting point(s) for research:
Endert, A., Ribarsky, W., Turkay, C., Wong, B.L.W., Nabney, I.T., Diaz-Blanco, I. and Rossi, F. The State of the Art in Integrating Machine Learning into Visual Analytics. Computer Graphics Forum, 36(8):458–486, 2017. doi:10.1111/cgf.13092.
Chatzimparmpas, A., Martins, R. M., Jusufi, I., & Kerren, A. A Survey of Surveys on the Use of Visualization for Interpreting Machine Learning Models. Information Visualization, 19(3), 207-233, 2020. doi: 10.1177/1473871620904671.
Wang, Q., Chen, Z. , Wang, Y., and Qu, H. A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization, IEEE Transactions on Visualization & Computer Graphics, 28(12):5134-5153, 2022. doi: 10.1109/TVCG.2021.3106142.
T. Spinner, U. Schlegel, H. Schäfer and M. El-Assady, explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning, IEEE Transactions on Visualization and Computer Graphics, 26(1):1064-1074, 2020, doi: 10.1109/TVCG.2019.2934629.
Ono, J.P., Castelo, S., Lopez, R., Bertini, E., Freire, J., and Silva, C. PipelineProfiler: A Visual Analytics Tool for the Exploration of AutoML Pipelines, IEEE Transactions on Visualization & Computer Graphics, 27(02): 390-400, 2021. doi 10.1109/TVCG.2020.3030361.