Research
Explainable AI
The field of mechanistic interpretability concerns itself with "reverse engineering" deep artificial neural networks in order to understand them in terms of human-interpretable algorithms. Our prior work focused on studying concept acquisition in deep reinforcement learning (deepRL) systems such as DeepMind's AlphaZero, with the goal of identifying the acquisition of given human-like concepts by these systems. Our current research aims to expand the scope of study to large language models (LLMs) and other deep learning models, while also aiming to isolate novel concepts potentially beyond human current understanding. Of particular interest to us are concepts related to reasoning processes, and their potential relationship with human-like logical reasoning.
Selected publications
A. Marchiafava and A. Sen, “Comparing Concept Acquisition in Human & Superhuman DeepRL Models,” *International Journal On Advances in Intelligent Systems*, vol. 16, no. 3, pp. 19–30, Dec. 30, 2023, issn: 1942-2679. url: https://ns2.thinkmind.org/index.php?view=article&articleid=intsys_v16_n34_2023_1(visited on 06/04/2024).
Biodiversity AI
We are interested in the application of interpretable AI techniques to biodiversity science, ecological informatics and computational systematics generally, an intersection we call "Biodiversity AI". Our current research involves studying the impact of taxonomic and geo-spatial change using machine learning and computational reasoning, with the goal of impacting conservation decision-making. Our Biodiversity AI research is funded by the National Science Foundation.
Note:
We are hiring a new Biodiversity AI graduate student (Ph.D. or research M.S.)! If you want to work in the exciting field of AI and are interested in biodiversity and ecological sustainability, you may be a fit; please contact Prof. Sen by email with a CV and statement of interest. We invite applications from persons with computer science, biology, and related backgrounds.
Selected publications
A. Sen, B. Sterner, N. Franz, C. Powel, and N. Upham, “Combining Machine Learning & Reasoning for Biodiversity Data Intelligence,” en, in *Proceedings of the AAAI Conference on Artificial Intelligence*, Number: 17, vol. 35, May 2021, pp. 14 911–14 919. doi: 10.1609/aaai.v35i17.17750. (visited on 07/05/2023).