Conducting eXplainable Artificial Intelligence (XAI) Research with an Emphasis on Computer Vision, Object Detection, and Image Generation [LinkedIn] [Scholar]
I am a machine learning researcher and engineer with over 6 years of experience implementing, developing, and training state-of-the-art machine learning models. My expertise is in computer vision, LLMs, and generative image/video models. Much of my research focuses on eXplainable Artificial Intelligence (XAI), which gives me a unique insight into the inner workings of black-box machine learning algorithms. I enjoy using these visually intuitive explanations of complex machine learning models to create AI models that are interpretable, trustworthy, and reliable. This includes creating inherently interpretable models, and using XAI as a tool to debug and enhance models through novel architecture and training schema.
- 2020-2025 Henry M. Rowan College of Engineering, Rowan University Ph.D. in Electrical and Computer Engineering
- 2016-2020 Henry M. Rowan College of Engineering, Rowan University B.S. in Electrical and Computer Engineering
-
[DOI] Transformers in time-series analysis: A tutorial.
Circuits, Systems, and Signal Processing 42, no. 12 (2023): 7433-7466.
Sabeen Ahmed, Ian E. Nielsen, Aakash Tripathi, Shamoon Siddiqui, Ravi P. Ramachandran, and Ghulam Rasool. -
[DOI] Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks
IEEE Signal Processing Magazine, vol. 39, no. 4, pp. 73-84, (2022).
Ian E. Nielsen, Dimah Dera, Ghulam Rasool, Ravi P Ramachandran, Nidhal Carla Bouaynaya. -
[DOI] EvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models
IEEE Access, vol. 11, pp. 82556-82569, (2023).
Ian E. Nielsen, R. P. Ramachandran, N. Bouaynaya, H. M. Fathallah-Shaykh and G. Rasool -
[DOI] Targeted Background Removal Creates Interpretable Feature Visualizations
2023 IEEE 66th International Midwest Symposium on Circuits and Systems (MWSCAS), Tempe, AZ, USA, pp. 1050-1054, (2023).
Ian E. Nielsen, R. P. Ramachandran, N. Bouaynaya, H. M. Fathallah-Shaykh and G. Rasool