Have you been ever stuck while the neural network executes smoothly across epochs but the loss doesn't decrease ? Or may be the loss decreases but not the way you would like it to ? Debugging a deep neural network is helpful if not essential for a lot of use cases.
Read more
Deep Learning has been making quite a lot of progress in computer vision tasks of late. In this post, I go on to explain how to use 2D U Net (one of the most popular papers of 2015-16 in computer vision) for segmenting out overlapping chromosomes on a slide used for cytogenetics.
Read more
In most of the cab rides I had my conversation with the cab owner tending towards to the ever-so-important question - “How to generate maximum revenue?” Do I drive at night? Where do I start my trip? What do I optimize for – longer rides in a longer time or repeated shorter rides in the same time? How long do I drive? and alike questions. This post tries to solve some of those questions along with bringing out some interesting insights about traffic in NYC.
Read more
Of late, we have heard a lot of talk about unsupervised learning being the way forward. A lot of research at major R&D organisations like Open AI is focussed on unsupervised learning.Why is unsupervised learning so important ?
Read more
Any heated argument on AI these days soon ends up in a predictable trajectory - so DeepMind's AlphaGo beats Go champ,Tesla to compete with Uber using AI driven cars, ethical dilemma of driver-less cars and finally - would robots overpower humankind
Read more