How I taught myself AI in the last 2 months

Photo credit: Sergey Galyonkin.

People are busy nowadays. There are a lot of things going on in our personal and professional lives. And lo and behold, something like artificial intelligence starts to gather steam, and you realize that your skill set is going to be terribly outdated in the next two years.

When I shut down my startup, Zeading, it was a rude awakening. I felt like I was missing out on something very unique. The relevance of a full-stack developer will not be enough in the changing scenario of things. In the next two years, full stack will not be full stack without AI skills.

It was time to take action—to update my skills as a developer, my mindset as a product guy, and my philosophy as an entrepreneur to become data-oriented.

As Spiros Margaris, renowned venture capitalist and thought leader in AI and fintech, so eloquently told me,

“If startups and companies rely only on cutting-edge AI and machine learning algorithms to compete ,  it will not be enough. AI will not be a competitive advantage but a requirement. Do you hear anyone saying they use electricity as a competitive edge?”

Building my first neural network

The common advice was to sign up for Andrew Ng’s course on Coursera. It is a great place to begin, but I found it hard to stay awake for long.  It’s not to say that the course was bad. I just really suck at paying attention to lectures. My mode of learning has always been by doing, so I thought, why the hell not implement my own neural network?

I did not jump straight to neural nets because I was trying to familiarize myself with all the words in the domain so I can learn to speak the language. The first assignment is not to learn but to familiarize.

Coming from a pure Javascript and Node.js background, I didn’t want to switch stacks just yet. So, I searched for a simple neural net module called nn and used it to implement an AND gate with a dummy input. Inspired by this tutorial, I chose the problem that for any three inputs X, Y, and Z, the output should be X AND Y.

var nn = require('nn')
var opts = {
    layers: [ 4 ],
    iterations: 300000,
    errorThresh: 0.0000005,
    activation: 'logistic',
    learningRate: 0.4,
    momentum: 0.5,
    log: 100   
}
var net = nn(opts)

net.train([
    { input: [ 0,0,1 ], output: [ 0 ] },
    { input: [ 0,1,1 ], output: [ 0 ] },            
    { input: [ 1,0,1 ], output: [ 0 ] },
    { input: [ 0,1,0 ], output: [ 0 ] },
    { input: [ 1,0,0 ], output: [ 0 ] },
    { input: [ 1,1,1 ], output: [ 1 ] },
    { input: [ 0,0,0 ], output: [ 0 ] }
    ])

// send it a new input to see its trained output
var output = net.send([ 1,1,0]) 
console.log(output); //0.9971279763719718

Such happiness!

Priming my mind for AI

Catching the chatbot train

Salt and pepper