Explore research papers, tutorials, and technical deep-dives written by our members.
Reinforcement LearningA reinforcement learning study that uses the Rubik's Cube as a hard-exploration environment. The work compares standard PPO, manually designed curriculum learning, and an online teacher approach based on an epsilon-decay-greedy strategy.
Explainable AIA study exploring explainability techniques for medical imaging, including Gradients, Integrated Gradients, XRAI, Grad-CAM, and Counterfactual Explanations. The work also examines sanity checks and execution-cost considerations.
Deep LearningA research project exploring deep learning as a way to build an automatic, experiment-specific framework for physical discovery. It represents an earlier research direction within the RSC program.
Computer VisionA computer vision project focused on detecting road lanes and vehicles for autonomous driving applications.