BB8, Dum-E, Wall-E, C-3PO, R2-D2, Optimus Prime, you name it, I don't think there is anyone who hasn't been captivated by these robots. After all, who does not want a friend that can assist us to commute while we lay back and lift our boxes while we move out? Ever since I started learning machine … Continue reading Challenges for building Neural Network-based Autonomous Robots

Paper Status: Accepted to ICRA 2019 Link to the paper, code, presentation, videos, poster. Learning to make decisions in the real world is hard for a plethora of reasons. The decision-making architecture or controller has to not only find a good representation but also has to display a high degree of adaptability and versatility. This whole … Continue reading Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Lately, I have been thinking deeply (pun intended) of Imitation Learning and its prospects for enabling fully autonomous robots and cobots. This will help us not do what we really do not want to do. Well, you might say, "look Sanjay, there is nothing groundbreaking about this idea and you are definitely not the first and … Continue reading Learning from Demonstrations – I

By the virtue of its ability to approximate any function([1], [2]), Neural Network~(NN) based architectures have achieved massive success in learning complex input-output mappings from data. However, mere knowledge of the input-output mapping falls short on a lot of situations especially that need to integrate beliefs in the model or where data is limited. Bayesian … Continue reading The very Basics of Bayesian Neural Networks

Friends, Romans, Countrymen lend me your ear. Today I am gonna list my wishlist. These are the things that I would want to look back from later in future and say, "Kudos mate, I am so glad you did these things." instead of saying, "I wish I had done them.". These are the things that … Continue reading Things I want to do before I die

Hi everyone, as a result of my desperate attempts to kick-off my life as some Artificial Intelligence (AI) researcher I present to you my most recent findings and endeavors on the lines of creating better AI. All views are mine and subjective. And please let me know if there is any room for improvement in … Continue reading Installing Experience into Artificially Intelligent Agents

It is said that a picture is worth a thousand words. But the question is can we make the image enough appealing to its beholder to grasp and digest those 1000 words. Image rendering to generate artificial yet realistic looking images is the field where ways are being devised to do so.

Well, you'll find a lot of motivational pieces of stuff in various books, magazines, and of course the internet. But I am going to write here about the thing that I feel is the most important to do during the preparation time, where the competition is neck to neck and no opponent is weak. The … Continue reading The key to win depends the extra mile you take

Hii everyone here. Today, I am going to write about the research project that I did at LATECE, UQAM during the summer of 2015. It was one of the most important experiences I have obtained so far in my life. Here I discuss why such a research is required to be done and its importance. … Continue reading Detection of antipatterns in Mobile Architectures and resolving them