406 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of AlbertaCA19 papers
- Intel (United States)US4 papers
- Kyushu UniversityJP3 papers
- Nanyang Technological UniversitySG3 papers
- Technical University of MunichDE3 papers
- University of CalgaryCA3 papers
- Alberta Bone and Joint Health InstituteCA2 papers
- American College of RadiologyUS2 papers
- Aminu Kano Teaching HospitalNG2 papers
- Athinoula A. Martinos Center for Biomedical ImagingUS2 papers
- Baylor College of MedicineUS2 papers
- Brigham and Women's HospitalUS2 papers
7 papers · 1 filter
Federated Learning Enables Big Data for Rare Cancer Boundary Detection
Sarthak Pati, Ujjwal Baid, Brandon Edwards +276
Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally shar…
Reward-Respecting Subtasks for Model-Based Reinforcement Learning
Richard S. Sutton, Marlos C. Machado, G. Zacharias Holland +4
To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning…
Maximum Reward Formulation In Reinforcement Learning
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall +6
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several cruc…
Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
Farzane Aminmansour, Taher Jafferjee, Ehsan Imani +3
Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environme…
Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison
Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski +1
Modern automation systems rely on closed loop control, wherein a controller interacts with a controlled process, based on observations. These systems are increasingly complex, yet…
Gene Expression based Survival Prediction for Cancer Patients: A Topic Modeling Approach
Luke Kumar, Russell Greiner
Cancer is one of the leading cause of death, worldwide. Many believe that genomic data will enable us to better predict the survival time of these patients, which will lead to bett…
General Value Function Networks
Matthew Schlegel, Andrew Jacobsen, Zaheer Abbas +3
State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent…