Incoming Graduate Student,
University of Montréal
Incoming Graduate Student,
Machine Learning Engineer
Founder & Researcher
Laboratory for Space Research,
Email, Scholar, GitHub,
Blog, Twitter, W&B Profile
I work on topics in continual learning, attention mechanisms, robustness and non-linear dynamics,
with a broad focus on theoretical deep learning, lifelong learning, representation learning and computer vision.
My previous work has mostly been at the intersection of dynamics and applied computer vision. I also work at the intersection of computer vision and astrophysical sciences.
Along with the applied deep learning aspects, I have a firm interest in abstract algebra and algebraic geometry.
Some recent topics:
As founder and researcher at my group Landskape, I collaborate and undertake research projects mostly at the intersection of analytical theory of deep learning and applied computer vision. Please visit our page for more details.
I will be joining MILA and Université de Montréal in Fall 2021 as a graduate student of computer science specializing in machine learning. Prior to this, I completed my undergraduate in Electronics and Electrical Engineering (EEE) from Kalinga Institute of Industrial Technology (KIIT) under the guidance of Asst. Prof. Dr. Bhargav Appasani.
In the past I have been fortunate to work with the likes of Dr. Amrita Chaturvedi from Indian Institute of Technology, Varanasi (IIT-BHU) in the field of biomedical data analysis and Vijay Kumar Verma from Indian Space Research Organization (ISRO) in the domain of Genetic Algorithms. I have presented my work at conferences in Bangkok and Kuala Lumpur and have been awarded the Research Travel Grant by KIIT.
I also had the honor of interning at Indian Institute of Technology, Kharagpur (IIT-KGP) under Prof Pawan Kumar where I learnt about traditional AI and functional languages like Prolog and Lisp.
I am currently mentored by Prof. Jaegul Choo (KAIST) on topics of super resolution and image reconstruction.
Collaboration Opportunities and Referrals:
At Landskape, we are open to new collaborations and research members for our selected ongoing projects. Please take a look at our projects to have an idea on the scope and domain of our current projects. To reach out to us, please fill in the contact form available on our page. If you're at MILA, feel free to reach out to me directly via email. Additionally, if you're interested in applying for any position at Weights & Biases, please do so via the official portal. Please do not contact me for referrals. You can take a look at the open positions at Weights & Biases here.
Recent projectsPublications listed below, in the present page.
Mish: A Self Regularized Non-Monotonic Neural Activation Function We propose a novel non-monotonic non-linear activation function known as Mish which outperforms conventional activation functions like ReLU and Swish. We further provide a highly optimized CUDA version of Mish along with linking the effect of non-monotonic smooth activation functions to the loss landscapes of deep neural networks.
Rotate to Attend: Convolutional Triplet Attention Module We propose a process that captures Cross-Dimenional Interaction (CDI). Using CDI as a foundation, we propose a novel attention mechanism for deep convolutional neural networks known as Triplet Attention.
Collaborators: Trikay Nalamada (Landskape/ Columbia University), Ajay Uppili Arasanipalai (Landskape/ UIUC), Qibin Hou (NUS)
Echo Echo is an OSS deep learning package with support for TensorFlow, PyTorch and MegEngine, containing novel validated methods, components and building blocks used in deep learning.
Collaborators: Alexandra Deis (X the Moonshot Factory), Soumik Rakshit (IBM), Ajay Uppili Arasanipalai (Landskape, UIUC), Sasikanth Kotti (TCS)
Robustness-Stability-Plasticity Trilemma We are investigating into the effects of Continual Learning methods on the adversarial and OOD robustness of neural networks. We aim to formulate a novel understanding of optimal lifelong learning with the preservation of generalization and robustness.
Collaborators: Himanshu Arora (Landskape, MILA, Workday), Norman Di Palo (Imperial College London), Mukund Varma T (IIT Madras)
Factorized Super Resolution We propose a novel blind super resolution framework aimed at improving consistency and reducing artefacts generation.
Collaborators: Himanshu Arora (Landskape, MILA, Workday) and Jaegul Choo (KAIST)
Sparse Domain Adaptation using Incremental Learning We explore the problem of sparse and continuous domain adaptation using incremental learning. Our motivation to approach this problem is from a standpoint of making networks adaptive to unseen classes from different domain.
Collaborators: Alex Gu (MIT)
Ensemble vs Dense Networks: An Empirical Study We explore and provide a comprehensive study of ensemble networks as compared to dense networks from the standpoint of performance, compute requirements, robustness, et cetera.
Collaborators: Abdul Wasay (Havard)
Avalanche: A Continual Learning Framework I am an active lead maintainer of the Reproducible Continual Learning framework by Avalanche and also actively work on the evaluation framework of Avalanche mainly in the direction of integration of Weights & Biases API.
Collaborators: Continual AI Team
Genetic Algorithm Optimized Inkjet Printed Electromagnetic Absorber on Paper Substrate We propose the design of printable electromagnetic absorbers for the X band. The design of the absorber is optimized using the Genetic Algorithm (GA) to enhance the absorptivity and the absorption bandwidth.
Collaborators: Rahul Pelluri (BITS Mesra), Vijay Kumar Verma (ISRO), Bhargav Appasani (KIIT) and Nisha Gupta (BITS Mesra).
Initiatives and Academic Services
Weights & Biases ML Reproducibility Challenge 2021 I am the lead organizer of the W&B MLRC 2021 where I actively support our challenge participants. Our mission of organizing this challenge is to make machine learning research reproducible, transparent and accessible to everyone. This initiative is also supported by our W&B MLRC Grant of $500 for each participant.
Neuromatch Academy 2021 I am responsible for developing the content for the Strategies section in the Continual Learning lecture of the Deep Learning Cohort of Neuromatch Academy 2021.
- May 2021: We are organizing the Spring Edition of the Weights & Biases ML Reproducibility Challenge. Visit our page to learn more.
- May 2021: I will be joining MILA as a graduate student this fall '21.
- January 2021: Our WACV paper's video is now out on YouTube. Watch it here.
- January 2021: I will be speaking at the W&B Deep Learning Salon on "From Smooth Activations to Robustness to Catastrophic Forgetting". I will be joined by Maithra Raghu from Google Brain. Watch it here.
- December 2020: I'm starting full time as a Machine Learning Engineer at Weights & Biases.
- October 2020: Our paper Rotate to Attend: Convolutional Triplet Attention Module is accepted to WACV 2021.
- September 2020: Gave a talk on my paper on Mish at the Robert Bosch Bangalore Research Office.
- August 2020: I completed my Undegraduate degree in Electronics and Electrical Engineering from Kalinga Institute of Industrial Technology (KIIT).
- August 2020: Gave a talk on Mish and Non-Linear Dynamics at Computer Vision Talks. Watch here.
- July 2020: My paper Mish: A Self Regularized Non-Monotonic Neural Activation Function is accepted at BMVC 2020.
- July 2020: CROWN: A comparison of morphology for Mish, Swish and ReLU produced in collaboration with Javier Ideami. Watch here.
- May 2020: Participated in an AMA for my paper on Mish at the Weights & Biases reading group.
- April 2020: Presented my views and discussed about Data Science on the The World is Ending Podcast. Listen to the episode here.
- February 2020: Talk on Mish and Non-Linear Dynamics at Sicara is out now. Watch here.
- February 2020: Podcast episode on Mish at Machine Learning Café is out now. Listen here.
- November 2019: Presented a talk on my paper on Mish at the University of Athens.
Mish: A Self Regularized Non-Monotonic Neural Activation Function
BMVC, 2020 [pdf][code][CV Talk Episode][ML Cafe Episode][Sicara Talk][Weights & Biases Salon Episode]
Rotate to Attend: Convolutional Triplet Attention Module
Diganta Misra, Trikay Nalamada, Ajay Uppili Arasanipalai, Qibin Hou
IEEE WACV, 2021 [pdf][supp][video][code]
Genetic Algorithm Optimized Inkjet Printed Electromagnetic Absorber on Paper Substrate
Diganta Misra, Rahul Pelluri, Vijay Kumar Verma, Bhargav Appasani, Nisha Gupta
IEEE AESPC, 2018 [Paper]