The 20th aeon turned out to be an era of exponential growth in the field of apparatus learning. The 3000-year-old age-old game of ‘Go’ that computer scientists predicted will take addition decade to crack was made accessible by Google Brain teams AlphaGo AI, defeating multiple-time world best Lee Sudol.

And, by the way, this Chinese game has more combinations than predicted atoms in the cosmos or, in short, this game can’t be won just by active through all the accessible moves, what IBM Blue did in 1997, defeating world best Gary Kasparov.

Then, the rise of OpenAI’s bot in DOTA2 and other fun (potentially harmful) stuff like Deepfake. Research communities are advancing in ML, from 100 papers submitted annually 10 years ago, to 100 per day in 2019 on arXiv alone.

But, befitting aggregate aside, the point is that ML is highly math-intensive.

While libraries like TensorFlow and PyTorch have made a cogent addition in making ML attainable to all the developers out there, we still have a steep acquirements curve to know how to create models, train them, and save it to later use it for our tasks.

That is where ml5.js comes in, a library based on TensorFlow.js, which was launched last year in March, taking the vision even further.

Why ml5.js

“ml5.js aims to make apparatus acquirements attainable for a broad admirers of artists, artistic coders, and students. The library provides access to apparatus acquirements algorithms and models in the browser.” — Official developers

In the browser. Yes! No installation required, which takes you away from the pain of installing assorted data-science libraries and making sure aggregate works in accord with the versions you’ve installed, which, accept me, is at times no easy task.