Elena Mocanu

About

Elena Mocanu is a leading researcher in artificial intelligence, with a primary focus on efficient machine learning, deep reinforcement learning, and probabilistic modeling. Her work addresses critical challenges in making AI systems more practical and resource-aware, particularly for real-world applications like robotics and user tracking. In her influential 2014 paper, "Inexpensive user tracking using Boltzmann Machines," she pioneered a cost-effective probabilistic approach to user localization, tackling the inherent uncertainties in healthcare, human-computer interaction, and security domains. This foundational work has garnered 9 citations and laid the groundwork for accessible tracking solutions. More recently, her 2023 study, "Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning," introduces a novel method for robots to autonomously distinguish relevant information from noise during task execution—a critical capability for household robots managing complex environments. By leveraging dynamic sparse training, Mocanu enables more efficient and focused learning, reducing computational overhead. Her contributions are shaping the next generation of adaptive, noise-resilient AI systems, with growing impact in both academic research and practical robotics applications.

Research Focus

Key Achievements

Top Papers

1. 1
   Inexpensive user tracking using Boltzmann Machines

   9 citations · 2014
2. 2
   Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning

   2 citations · 2023

Key Collaborators

Contact & Links