Limiting the reconstruction capability of generative neural network using negative learning
- Asim Munawar
- Phongtharin Vinayavekhin
- et al.
- 2017
- MLSP 2017
Links
Professional Associations: IEEE Member | ACM
More information: Google Scholar | LinkedIn | Twitter
Profile
Short Bio
Dr. Asim Munawar is a Program Director for Neuro-Symbolic AI at IBM Research. Dr. Munawar received his PhD from Hokkaido University, Japan in evolutionary algorithms. He joined IBM Research in 2012 and has been working in the field of deep learning since 2013. Dr. Munawar has led many deep learning-related research projects and customer engagements in various application domains including but not limited to computer vision, robotics, acoustic analysis, and NLP. His main research interest is the creation of next-generation AI by combining symbolic knowledge and reasoning with data driven learning methods. He is also interested in learning techniques that better mimic the learning process in a human brain. This include low power neuromorphic computing with spiking neural networks and model-free/model-based reinforcement learning algorithms that can learn from weak reward signals. Dr. Munawar has over 50 publications in international journals and peer-reviewed conferences.
Awards & Certifications
Best Paper Awards
Academic Awards
Professional Awards
Certifications
Invited Talks