Research/Blog

Recently I presented a session on Optimization-based Meta Learning, Part 3 of the Meta Learning Series, at the CellStrat AI Lab. The previous parts are found here – Part 1 (Metric-based Meta Learning), Part 2 (Model-based Meta Learning) Meta Learning, of course, refers to “Learning to Learn“. Quick Recap (Metric-based Meta Learning) Meta-Learning deals with […]

Introduction Moving up the value chain CellStrat would like to encourage discussions and webinars focusing on the application of AI in Real Life problem-solving. A beginning has already been made and this is another step in that direction. The use of Deep Learning and Reinforcement Learning to solve a complex Strategic Negotiation is a very […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Recently I presented Part 2 of the Meta Learning Workshop series at the CellStrat AI Lab. The topic was Model-based Meta Learning. A Quick Recap Meta-Learning deals with creating models which either learn and optimize fast or models which generalize and adapt to different tasks easily. Few-Shot classification frames image classification […]

Survey forms, invoices, bills, memos, tenders, and myriad such documents which businesses face on daily basis. These are full of numbers, characters, images, signatures etc…in almost all languages worldwide…. hard to imagine our world without any languages. Think about how many text and voice data we face every day. What about determining meaning from this […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Recently, I presented a session on Metric-based Meta Learning at the CellStrat AI Lab (where I am an AI Researcher). Metric-based Meta Learning might be considered a domain of Artificial General Intelligence (AGI). This is due to the fact that Meta Learning helps us create generalized systems with relatively less data. […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Recently, we conducted our first Product Showcase for our new world-class Healthcare AI application platform. Given the times, COVID-19 detection is our top focus in terms of product development, but we also have other exciting healthcare AI applications being developed related to brain, eye and cancer issues. The following demos were presented […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Recently, our AI Lab Researcher Bismillah Kani presented a superb session on Grad-CAM, which is used to detect “why they predict what they predict“. In other words, it explains the AI algorithms, specifically, it explains the results of vision applications. Introduction :- Deep Learning in Computer Vision has achieved breakthrough performance […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Recently, our AI Lab Researcher Gouthaman Asokan presented an amazing session on Relational Graphical Convolutional Networks (Relational GCN). These are particularly useful for mining heterogeneous groups. Table of Contents :- GCN HOMOGENEOUS AND HETEROGENEOUS GRAPHS KEY IDEAS OF RELATIONAL GCN FINDING PAGERANK USING MESSAGE PASSING BUILDING A RELATIONAL GCN FOR THE […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars I presented a session on Multi-Agent RL recently at the CellStrat AI Lab. Introduction :- In the normal Reinforcement Learning setup, you have one agent which interacts with the environment. It uses the Observation from the environment, performs actions and observes the rewards. In real life, many applications will involve several agents […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Last Saturday, our AI Lab Researcher Niraj Kale presented an excellent session on OpenPose, an algorithm to efficiently detect the 2D pose of multiple people in an image. Pose skeleton represents orientation of a person in graphical format. Each coordinate in the skeleton is known as keypoint. A valid connection between […]