CODEX

It’s the year 2030, we are living in an age of increasing automation and artificially intelligent bots are powering this. All the trivial decisions are driven by machines and they are redesigning our ways of life. Lorem Ipsum is frustrated with the work lately and has a splitting headache, the automated recommendations from his Google health don't help and he gets an appointment with his doctor. It takes him just 30 minutes to go get through all the arduous stages of his brain test until he sees the doctor finally. “The scan results look negative for any abnormality, the brain…


Artificial Intelligence wields a wide influence in today’s world and yet deciphering human intelligence is an elusive problem. We have made significant strides in developing models that mimic a subset of activities humans can perform. We have deep learning models that can even outperform humans but what we are lacking is the comprehension of how our brain works. Most of our models are heavily parameterized and are too abstract to be interpreted. They are like black boxes giving out outputs whose reason cannot be decoded. To this end, there is a dire need for a model that is efficient while…


Thinking about how our mind thinks is one of my favorite pastimes. I have always been fascinated by the workings of the brain, or psychology as they call it scientifically. The quest I began, to learn more about this led to a whole new world of rediscovery in me and my perspectives, it has answers to all my questions on our thoughts, intuitions, and the innumerable biases we are prone to fall for leading up to critical decisions that make or break our life. This knowledge I have imbibed is only a speck of information available out there, but in…


We all know about the Convolutional Neural Networks and their efficiency in learning non-linear and complex representations. But the issue with learning these representations is that as our problem gets more complex, we add more layers and make the model deeper, and then we see multiple issues come to surface. This makes handling deep neural networks tricky.

Over the last decade, we have seen a multitude of deep network architectures successfully address these issues, but the one thing common in all of these is they use some novelty to curb the problem of vanishing gradients, overfitting and parameter explosion. We…


An intuition to the effect of attention in joint image-text representation learning and the application with respect to image retrieval problem

Intuition

Almost always, a machine learning based solution to any problem that needs some sort of supervision usually is inspired by the ways of working of the human brain. Ultimately all our efforts in the domain are to achieve a model that is basically a super-powerful and intelligent version of the human brain.

Along similar lines, any computer vision problem involving learning the image representations derives its methods from the way the human brain and optical system interacts. One main…


Since my association with Data Science and Machine Learning, the one question that has always fascinated me is the humongous amount of data humans generate and our inability to effectively utilize it in the sophisticated algorithms available at our disposal. The only shortcoming in all our ideas to apply deep learning and to save the world(a bit too late for that) is the effort and time involved in data preprocessing and not the data itself, which we have in abundance. Just to get a sense of this, we generate close to 3 quintillion bytes (10¹⁸) of data every day! That…

Sumanth S Rao

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store