Who’s Who of Deep Learning Eco-System

by Ankit Sachan • April 1, 2020

        Alexnet, which started the deep learning revolution, was loosely based on a network architecture(LENet) proposed by Yann Lecun in 1998. However, back then, we didn’t have the compute or the training data to train and produce the results like Alexnet. Alex used Nvidia GPUs for training, in fact he used two GPUs to train which […]

Continue Reading

Intro to AI and Machine Learning for Technical Managers

by Ankit Sachan • March 2, 2020

  In 2013, Google acquired a company called DeepMind for 400 Million dollars. DeepMind at the time had no product and no revenue, but what they had was a team of the best brains in the world who worked on Machine learning and Deep Learning. In fact, between 2013 and 2015, all the technology giants(Facebook, […]

Continue Reading

Human pose estimation using Deep Learning in OpenCV

by Ankit Sachan • February 13, 2020

I recently came across a very interesting use-case of computer vision and AI. Runners Need is a UK based sports shoe brand. They offer automated gait analysis using computer vision before they sell you a customized shoe. Gait analysis is a method for identifying biomechanical abnormalities in the way in which you walk or run. A video […]

Continue Reading

Introduction to Generative Adversarial Network

by Ankit Sachan • January 19, 2020

Artificial Intelligence has improved quite a lot in the last decade. By improvement I mean we’re able to do things better than before as well as we can now do things that we didn’t even imagine, but now we and machines both can imagine. What ! machines can imagine ? Yes you heard it right ! […]

Continue Reading

Getting started with Recurrent Neural Networks

by Ankit Sachan • November 20, 2019

In some previous tutorials, we learned how to build image classifiers using convolutional neural networks or build object detectors using CNNs. In both examples, all the information required to identify the dog or cat is present in the image. However, there are many use-cases where the current prediction not only depends on the current input […]

Continue Reading