Department of Computer Science & Engineering

Research Interests :

Publications : (Last Five, while at IITM)DBLP | View All

• On the Interpretability of Attention Networks. 
  
  Authors : Lakshmi Narayan Pandey, Rahul Vashisht, Harish Guruprasad
  Appeared in Asian Conference on Machine Learning, ACML 2022, 12-14 December 2022, Hyderabad, India. (ACML 2022) ,Proceedings of Machine Learning Research, Vol 189, pp.832-847, Dec 2022
• Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets. 
  
  Authors : Depen Morwani, Harish Guruprasad
  Appeared in International Conference on Algorithmic Learning Theory, 29-1 April 2022, Paris, France., Proceedings of Machine Learning Research, Vol 167, pp.827-880, Apr 2022
• Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization. 
  
  Authors : Saurabh Desai, Harish Guruprasad
  Appeared in IEEE Winter Conference on Applications of Computer Vision, WACV 2020, Snowmass Village, CO, USA, March 1-5, 2020 (WACV 2020) ,pp.972-980, Mar 2020
• On Knowledge distillation from complex networks for response prediction. 
  
  Authors : Siddhartha Arora, Mitesh Khapra, Harish Guruprasad
  Appeared in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp.3813-3822, Jun 2019
• On Controllable Sparse Alternatives to Softmax. 
  
  Authors : Anirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh Khapra, Karthik Sankaranarayanan, Harish Guruprasad
  Appeared in Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montral, Canada., pp.6423-6433, Dec 2018

(Recent) Teaching : View All  |  Back to top

(Current) Advisees View All  |  Back to top

Awards and Recognitions :View All  |  Back to top

• Best Paper Award, 2020