Krithi Shailya
I am currently a Post Baccalaureate Fellow at IIT Madras, holding an undergraduate degree in Electrical Engineering from IIT Tirupati. With a background in deep learning for disease diagnosis, I’m now delving into the …
Deep Learning
Adithya Sai Lenka
I have completed my B. Tech (Hons.) in Computer Science and Engineering at SASTRA University, Thanjavur. During the course of my program, I developed a keen interest in Computer Vision and Deep Learning. At RBCDSAI, I am …
Adhil Ahmed P M Shums
My name is Adhil Ahmed P M Shums. I have completed my B.E. in Automobile Engineering from MIT, Anna University. I am also doing an online B.S in Data Science and Applications from IIT Madras, in parallel. Apart from …
Parse Challenge 2022: Pulmonary Arteries Segmentation Using Swin U-net Transformer(Swin UNETR) and U-net
In this paper, we describe a deep neural network architecture based on Swin UNETR and U-Net for segmenting the pulmonary arteries from CT scans. The final segmentation masks were created using an ensemble of six models, …
Roshan M S B
I am a PhD scholar working with Dr Nirav P Bhatt. My areas of interest span many topics on artificial intelligence applications in biology. I am currently working to develop algorithms by leveraging both artificial …
CDiNN – Convex difference neural networks
Scaling Graph Propagation Kernels for Predictive Learning
Many real-world applications deal with data that have an underlying graph structure associated with it. To perform downstream analysis on such data, it is crucial to capture relational information of nodes over their …
Towards Building ASR Systems for the Next Billion Users
Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the …
Smooth Imitation Learning via Smooth Costs and Smooth Policies
Imitation learning (IL) is a popular approach in the continuous control setting as among other reasons it circumvents the problems of reward mis-specification and exploration in reinforcement learning (RL). In IL from …
Unsupervised Deep Video Denoising
Deep convolutional neural networks (CNNs) for video denoising are typically trained with supervision, assuming the availability of clean videos. However, in many applications, such as microscopy, noiseless videos are not …
Semi-Supervised Deep Learning for Multiplex Networks
Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer. Such graphs are used to investigate …
Coffee shop banter: Symbolic or Deep Learning? Promising directions of AI
Sparks flew when friends, Prof. Sriraam Natarajan, UT Dallas and Prof. Kristian Kersting, TU Darmstadt decided to get together over a cup of coffee and discuss on the topic “Symbolic or Deep Learning? Promising …
Levelling up NLP for Indian Languages
We are working towards building a better ecosystem for Indian languages while also keeping up with the recent advancements in NLP. To this end, we are releasing IndicNLPSuite, which is a collection of various resources …
Deep Learning Model for Chest X-ray Imaging
In India, chest X-rays are given as a standard diagnostic imaging procedure (X-ray CT included) for patients with covid-19 symptoms. The impact of covid-19 on an infected person’s lung is quite severe as reported …
Interpretability of Deep Learning Models in Healthcare
Towards Autonomous PDE Solvers Automated Generation of Robust Numerical
We wish to work towards creating autonomous PDE solvers – solvers that will require zero to minimal interventions from humans in the loop. Three fundamental problems preclude current solvers from autonomy (a) Lack of …
Developing Temporal Convolutional Neural Networks comprising Nonlinear Oscillators for Non-Destructive Evaluation using Active Thermographic images
The aim of Non-Destructive Evaluation (NDE) is to probe materials and structures to detect and characterize defects and discontinuities without disturbing the target material. In active thermography the material being …
Attention Mechanisms in Deep Neural Networks
Recently the Deep Learning community has shown great interest in attention mechanisms to train neural networks – the network pays attention to only certain parts of the input or to certain parts of the network structure …
Ablation-CAM: Making AI trustworthy
As machine learning is set to change every aspect of our life, a key dilemma plagues the minds of researchers and its users- Can we trust machines to make key life decisions for us? Can we rely solely on the machine to …
Deep learning in biomedical image analysis
Medical imaging, specifically radiologic imaging is the most commonly used diagnostic tool for disease diagnosis and treatment assessment for a wide variety of conditions. Over the last decades the image acquisition …
Ananya Sai
I have completed my Masters at IIT Madras. Currently working as a Project officer on dialogue evaluation systems and metrics at RBC-DSAI
Mitesh M. Khapra
Mitesh M Khapra has recently joined the Department of Computer Science and Engineering at IIT Madras as an Assistant Professor. While at IIT Madras he plans to pursue his interests in the areas of Deep Learning, …
Safety and Stability Preserving Reinforcement Learning
While reinforcement algorithms have achieved notable successes recently, the use of such approaches in controlling real physical systems is not really prevalent. The primary reason for this is the lack guarantees …
Yadav Mahesh Lorik
“I am currently a MS Research Scholar at IIT Madras. My research area is in Deep Learning.”
Demystifying Brain Tumor Segmentation Networks: Interpretability and Uncertainty Analysis
The accurate automatic segmentation of gliomas and its intra-tumoral structures is important not only for treatment planning but also for follow-up evaluations. Several methods based on 2D and 3D Deep Neural Networks …
Rahul Vashisht
I am currently pursuing PhD at Department of Computer Science and Engineering under the guidance of Harish G. Ramaswamy. My topic of research is theoretical deep learning.
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks
Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, …
A neural attention based approach for clickstream mining
E-commerce has seen tremendous growth over the past few years, so much so that only those companies which analyze browsing behaviour of users, can hope to survive the stiff competition in market. Analyzing customer …
Training a deep learning architecture for vehicle detection using limited heterogeneous traffic data
Video image processing of traffic camera feeds is useful for counting and classifying vehicles, estimating queue length, traffic speed and also for tracking individual vehicles. Unlike homogeneous traffic, heterogeneous …
Correlational Neural Networks
Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical …