Ioannis Mollas
Papers
1
Total Citations
14
H-Index
1
About
Ioannis Mollas is a leading researcher in the field of explainable artificial intelligence (XAI), with a primary focus on developing transparent and interpretable machine learning models. His most notable contribution is the creation of **LioNets**, a novel framework for local interpretation of neural networks that decodes the penultimate layer to provide clear, instance-level explanations. This work, which has garnered over 14 citations, addresses a critical need in high-stakes domains such as smart homes, autonomous vehicles, healthcare, and robotics—where regulatory compliance and user trust are paramount. Mollas’s research directly tackles the "black box" problem in deep learning, offering practical tools for understanding model decisions without sacrificing performance. His achievements are particularly significant in the context of reinforced legal frameworks, such as the EU’s GDPR, which demand algorithmic accountability. By bridging the gap between complex neural architectures and human-understandable reasoning, Mollas has positioned himself as a key contributor to the growing movement toward responsible AI, empowering researchers and practitioners to build safer, more trustworthy intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1