Vishnu Naresh Boddeti is an Assistant Professor in the Department of Computer Science and Engineering at Michigan State University (MSU) and the Director of the Human Analysis Lab
Modern machine learning systems are critically dependent on data representations. My research in this area focuses on designing computationally and statistically efficient algorithms for learning such representations and understanding their behavior through concepts such as, convergence, complexity, privacy, fairness and security. I am specifically interested in developing novel modeling paradigms that afford explicit control over the semantic information content in a representation. My research agenda is directly motivated by, and contributes to, applications in machine learning, computer vision, biometric recognition and medical imaging.
Hiring: I am always looking for motivated students with strong mathematical background. Please read this before sending me an email, otherwise do not expect a reply. I value people who are attentive to details.
- 12/03/2019 Pre-print on Multi-Criterion Evolutionary Design of Deep Convolutional Neural Networks now available on Arxiv.
- 11/13/2019 Delivered a talk at IIT Madras titled “Towards Semantically Controllable Representation Learning”
- 11/13/2019 Delivered a talk at GIST titled “Advances in Deep Learning: Present and Future”
- 07/17/2019 Congratulations to Zhichao Lu, whose paper NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search received the Best Paper Award (EML Track) at GECCO 2019.
- 02/21/2019 Dr. Boddeti will be a Tutorial Chair at IJCB 2020
- 12/05/2018 Congratulations to Rahul Dey, whose paper RankGAN: A Maximum Margin Ranking GAN for Generating Faces received the Best Student Paper Award at ACCV 2018.
- 02/01/2018 Dr. Boddeti will be a Area Chair at BTAS 2018