Specialization : Machine Learning
Machine learning is an area of computer science in which algorithms learn and improve from experience. But systems are not explicitly programmed to do so. It comprises of various sub-fields like supervised learning, unsupervised learning, semi-supervised and reinforcement learning. From web search to bioinformatics machine learning has wide applications.
In reinforcement learning there is interaction between an agent and environment and learning is through rewards obtained. Typical applications are in robotics, autonomous vehicles and control in networks. The important factor in designing reinforcement learning algorithms is the balance between exploration and exploitation. Performance of algorithms can be studied empirically in applications or theoretically using sample complexity and regret bounds. The main challenge with these algorithms is how to deal with large state and action spaces, which is the case in real life applications.
In reinforcement learning there is interaction between an agent and environment and learning is through rewards obtained. Typical applications are in robotics, autonomous vehicles and control in networks. The important factor in designing reinforcement learning algorithms is the balance between exploration and exploitation. Performance of algorithms can be studied empirically in applications or theoretically using sample complexity and regret bounds. The main challenge with these algorithms is how to deal with large state and action spaces, which is the case in real life applications.
Sub Areas under Machine Learning:
Supervised Learning
Unsupervised Learning
Deep Learning
Reinforcement Learning
Robotics
Recent Publications:
- Madhushi Verma and K. K. Shukla (2016) Fuzzy Metric Space Induced by Intutionistic Fuzzy Points and its Application to the Orientering Problem, IEEE Transaction on Fuzzy Systems, vol. 24 (2), pp. 483-488, April 2016.
doi: 10.1109/TFUZZ.2015.2452948 - Mridula Verma & K. K. Shukla (2017) A new accelerated proximal gradient technique for regularized multitask learning framework, Pattern Recognition Letters, Vol. 95, pages 98-103 [ Link ]
- Mridula Verma & K. K. Shukla (2017) A new accelerated proximal technique for regression with high-dimensional datasets. Knowledge and Information Systems, pp. 1-16. ISSN: 0219-3116
- Ramesh C. Pandey, Sanjay K. Singh, Kaushal K. Shukla, Passive forensics in image and video using noise features: A review, Digital Investigation, Volume 19, December 2016, Pages 1-28, ISSN 1742-2876.
- Mridula Verma, Prayas Jain, K K Shukla (2016) A New Faster First Order Iterative Scheme for Sparsity-based Multitask Learning, Proceedings of 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary, pp. 1603-1608.
- Mridula Verma and K. K. Shukla, Performance comparison of proximal methods for regression with nonsmooth regularizers on real datasets, International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, pp. 447-453 (Acceptance Rate: 23%).
- Mridula Verma and K. K. Shukla (2017) Fast Multi-Modal Unified Sparse Representation Learning. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval (ICMR '17). ACM, New York, NY, USA, 443-447. DOI: https://doi.org/10.1145/3078971.3079040
- Ramashish Gaurav, Mridula Verma, and K K Shukla. 2016. Informed multimodal latent subspace learning via supervised matrix factorization. In Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP '16). ACM, New York, NY, USA, Article 36, 8 pages. DOI: https://doi.org/10.1145/3009977.3010012.
- S. Bhatnagar and Lakshmanan K., Multiscale Q-learning with Linear Function Approximation, Discrete Event Dynamic Systems, Vol 26, Issue 3, pp. 477-509, 2016.
- K. Lakshmanan, R. Ortner and D. Ryabko, Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning, Proceedings of The 32nd International Conference on Machine Learning (ICML) pp. 524-532, 2015.
- S. Bhatnagar and Lakshmanan K., An Online Actor–Critic Algorithm with Function Approximation for Constrained Markov Decision Processes, Journal of Optimization Theory and Applications, Vol 153, No. 3, pp. 688-708, 2012.
- Marwan M. Akeel, R. B. Mishra “Word Reorder and Agreement in ANN and Rule Based English into Arabic Machine Translation System”, International conference AISC-2012,IIT(BHU), Varanasi. 7-9 Dec. 2012.
- Vimal Mishra and R. B. Mishra, Non-Finite Verbs in English to Sanskrit Machine Translation, In Proceedings of IEEE-MTTS International Conference on Advances in Computing and Communication (ICACC-2011), April 08-10, pp 506-512, NIT Hamirpur, India, 2011.
Faculty:
Prof. K.K.Shukla
Prof. Rajeev Srivastava
Prof. S.K. Singh
Dr.K.Lakshmanan
Dr. Ruchir Gupta
Dr. Amrita Chaturvedi
Prof. Rajeev Srivastava
Prof. S.K. Singh
Dr.K.Lakshmanan
Dr. Ruchir Gupta
Dr. Amrita Chaturvedi
