Hardware-based Challenges for building Autonomous Robots

In my other blog post, I showed my optimism towards a world with Neural Networks (NN) based autonomous robots by listing the current pain points and their potential lines of solutions around such software systems. The development of NN infused robots has not seen as fast development as in fields like computer vision and NLP, … Continue reading Hardware-based Challenges for building Autonomous Robots

Challenges for building Neural Network-based Autonomous Robots

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

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

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

Learning from Demonstrations – I

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

The very Basics of Bayesian Neural Networks

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

Interfacing Tensorflow to Noobs

Hi there!! This post is supplementary to the presentation hosted here and all the codes can be found here. TensorFlow (TF) is an open-source numerical computation python library maintained by Google Inc. It has enabled long-standing powerful deep learning techniques accessible for both production and research. Owing to its strong community backing and flexible design it … Continue reading Interfacing Tensorflow to Noobs

Installing Experience into Artificially Intelligent Agents

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

Detection of antipatterns in Mobile Architectures and resolving them

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