# Hello tensorflow

May 22, 2018 · 4 min read

Machine Learning (ML) is the dope new thing that everyone’s talking about, because it’s really good at learning from data so that it can predict similar things in the future. Doing ML by hand is pretty annoying since it usually involves matrix math which is zero fun in JavaScript (or if you ask me: anywhere 😅). Thankfully, TensorFlow.js is here to help! It’s an open source library that has a lot of built-in Machine Learning-y things like models and algorithms so that you don’t have to write them from scratch.

# Is your problem a Machine Learning problem?

Machine Learning is good at classifying and labelling data. The premise of every machine learning problem is:

• Someone gives us some data that was generated according to a secret formula. This data could be a bunch of points (that are generated based on some math equation), but could also be fun, like images (the secret formula could be “some of these images are chihuahuas and some are blueberry muffins) or bus schedules.

# A fun demo!

If you want to get started, predicting numbers tends to be easier than predicting images, so in this example we’re trying to fit a curve to a bunch of data (this is the same example from the TensorFlow site but with waaaaay more code comments and a prettier graph).

We are given a bunch of points (for `x` between -1 and 1, calculate a `y` according to `y = a * x^3 + b * x^2 + c * x + d` – we know this is the secret formula but we don’t know the values of those `a,b,c,d` coefficients.) Our goal is to learn these coefficients, so that if we’re given a new `x` value, we can say what the `y` value should be.

The blue dots are the training points we were given. The red dots would be our guesses, based on our initial, default coefficients (hella incorrect!). Once you click the `train` button, the green dots show how our coefficients are getting better. After you see the default example, check what happens if you change the shape of the data, or we are given fewer data points or fewer iterations!

It looks like this (because Medium won’t let me iframe demos) but you can play with it here!

# How it works

Most machine learning algorithms follow this pattern:

• We have to figure out the “features” of the secret formula that generated the data we were given, so that we can learn them. In my opinion, this is like 80% of the complexity of solving an ML problem. In this example, we were told the shape of the secret formula (it’s a cubic!), so the features we have to learn are the coefficients in the polynomial. For something more complex like the “is this a dog or a blueberry muffin” problem, we’d have to look at pixels and colours and formations and what makes a dog a dog and not a muffin.

# The code

You can look at the code for the demo on Glitch. I tried to comment most lines of the code with either what the algorithm or TensorFlow are doing (especially when TensorFlow is actually doing a looooot of heavy lifting behind the scenes). I hope it helps!

Originally published at meowni.ca.

## Dev Channel

Developers Channel - the thoughts, opinions and musings…

## Dev Channel

Developers Channel - the thoughts, opinions and musings from members of the Chrome team.

Written by

## Monica Dinculescu

✨Emojineer✨ on @polymer & @googlechrome. Looks like she will bite; usually doesn't. Unless you're pizza. I made @to_emoji, a 💯 🤖

## Dev Channel

Developers Channel - the thoughts, opinions and musings from members of the Chrome team.