A Neurobiological Standpoint

Often we hear success stories in media that are cultivated because of hard work and practice. To take an example, Michael Jordan, one of the greatest basketball players of all time didn’t even qualify for the high school team the first time he tried. What did he do to become better? He PRACTICED!

Photo by Markus Spiske on Unsplash

We have all experienced that repeating a physical task does make us better and faster at it. The more well…


Exploring the scope of bitcoin as a safe haven against apparent inflation

Photo by Bermix Studio on Unsplash

The overnight currency ban in India and the irresponsible money printing that lead to hyperinflation in Zimbabwe are just a few instances where careless government policies around money have uprooted the daily lives of its citizens.

One of the major responsibilities of a government is to generate and regulate currency. The currency, since its inception, has always been backed by precious metals like gold and silver. This was common because these metals hold intrinsic value, they are mined, refined, and minted which makes them precious and worthy of…


Why Oxygen is used as a biosignature and how it came to be on Earth

Image depicting the Archean eon on Earth. Taken from here

Around 3 billion years ago in the Archaean eon, Earth was very different than it is today. The planet was predominantly covered with water(only 2–3% land) which was mostly green in color due to a large amount of iron. The atmosphere was free of oxygen and was composed of Nitrogen, Carbon dioxide, and Methane. I know you must be thinking that life is almost impossible without oxygen but at that time, simpler microscopic life thrived using anaerobic respiration.

Respiration that proceeds in the absence of oxygen is anaerobic respiration


A simple solution to change pixel values in an excel file to .jpg using Python

The field of data science and machine learning has shown significant growth in the past decade. With an increasing number of students interested in the cool applications these fields offer, it is hard not to google “how to get started with machine learning?”.

As anyone would expect the result of this query is filled with online courses and follow-along projects. This blog however is not to teach anyone about these fields but serve as a helping hand in getting started. A lot of applications for machine learning stem from image processing and image understanding. To train a neural net for…


What is a control system and why does it matter

Coming from a robotics background I can not understate the importance of control systems. Today, control theory and its applications are used everywhere. From simple machines like a water dispenser to a more complicated machine like an electric car, all are based in some form on control theory.

In general terms, a control system is a combination of electrical and mechanical mechanisms that operate together to provide the desired response from any system.

The more basic question, you might want to ask now is what is a system.

A system also referred to as a plant in control theory is…


An entrepreneur's guide to storytelling and developing a brand.

My company logo

I started my own venture, Sphere (a startup that developed an automatic crash response system), during my undergrad back in India. A couple of friends and I used to stay back every day after college to work. We were building a safety product for cars that aimed to reduce the mortality rate on the roads and make car-owning and driving experience safer.

After reading countless articles, books, and attending multiple business plan competitions, I realized one thing: A story sells better than any product.

Advertising is an old school practice and the modern public is far too aware to be…


Implementation of Genetic Programming with RNN for Music Composition

Image from here

Creativity has always been associated with human talent, but can it be taught to computers as well?

In this article, I discuss a project that I was a part of during my Master’s in Robotics. It explores the possibility of enabling computers to compose music through the implementation of genetic programming and machine learning methods including neural networks and naïve Bayes classifiers.

Here, genetic programming is used to evolve a set of notes and functions augmented by outputs from a recurrent neural network to produce snippets of music that sound similar to human-composed music.

The full story is published in Predict, click here to read the full story.


Implementation of Genetic Programming with RNN for Music Composition

Image from here

Creativity has always been associated with human talent, but can it be taught to computers as well?

In this article, I discuss a project that I was a part of during my Master’s in Robotics. It explores the possibility of enabling computers to compose music through the implementation of genetic programming and machine learning methods including neural networks and naïve Bayes classifiers.

Here, genetic programming is used to evolve a set of notes and functions augmented by outputs from a recurrent neural network to produce snippets of music that sound similar to human-composed music.

What is genetic programming?

Genetic Programming is a technique to solve complex problems by evolving programs. It is derived from Darwin’s theory of evolution where only the…


Design fundamentals with a focus on functionality.

Buying is fueled with emotion and justified with logic

Animation by Pablo Stanley

Today, there is a necessity for products to look aesthetic and appealing, and at the same time function flawlessly. When a product looks appealing, it ignites a sense of want in the customer. When it performs its function as promised, it allows the customer to justify the buy. This two-fold experience induces a sense of joy in people. As the creator of a product, your aim should be to generate this emotion at every stage of interaction with the consumer.

The visual aesthetic of a product is the responsibility of the designer. They understand market trends and come up with…


An Autonomous Robot

Fig: Front view of Edward

Edward is an autonomous 4-wheel differential drive robot. DF Robot’s Baron platform is used as the robot’s chassis. Multiple other sensors are used to perform the task of object identification and retrieval. It has a servo-motor controlled gripper which is useful for picking up objects of interest. Edward’s core controlling system is a Raspberry Pi which runs Python code on a Linux environment. The Pi Camera is the primary perception module.

Sanchit Gupta

A Roboticist, An Entrepreneur and a tad bit Curious

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