AI and machine learning

machine Learning lead is how AI learns

  • Sentient robots
  • Humans no longer being needed
  • The rise of machines over mankind

artificial intelligence

  • AI (kill all humans)
  • Machine learning (this not AI)
  • Deep learning (subset of Machine learning)

is this the End us all?? Absolutely!

This future can not be stopped, so let's just make the best of things now until they come for us.

WHY should
Machines learn things????

for Humans

We got Problems

They need decisions.

This can be hard.

 

"Given a decision where the logic is unknown to us, but we have observations about the decision process, it is possible to use statistical analyses of these observations to create an approximation of the decision logic." - Ryan Case

 towardsdatascience.com

https://towardsdatascience.com/why-machine-learning-303e6bdaa29d

Big Problems

with Lots of data

we use this right now!!

What do machines learn about right now?

  • Media - Netflix Movies
  • Retail - Amazon Shopping
  • Manufacturing - Output Lines
  • Healthcare - Clinical similarity between patients
  • Finance - Fraud Detection

facebook

Text

USE: Computer Vision

Netflix

USE: Thumbnails

Amazon

All the things... they do it so much they sell it because they sell everything

Locally

This is all happening in Eugene right now.

 

I KNOW

Working on Machine Learning in Eugene

Parts of MacHine learning

VOCABULARY mostly

Types of learniNg

Unsupervised learning

Learn the mapping of the data

Supervised learning

Data is mapped

Y = f(x)

Reinforced learning

Trial and ErroR with a feedback lOop

https://cai.tools.sap/blog/the-future-with-reinforcement-learning-part-1/

General ML Terms

DATA SET

A collection of examples

TRAINING

The process of determining the ideal parameters comprising a model

Model

THE REPRESENTATION OF WHAT A MACHINE LEARNING SYSTEM HAS LEARNED FROM THE TRAINING DATA

feature engineering

Creating PredictIon VARIABLES

Classification

labels for predictions

Loss

Loss is a number indicating how bad the model's prediction was on a single example. If the model's prediction is perfect, the loss is zero; otherwise, the loss is greater.

My first Experiment

What did I try??

 

Movie gross prediction based on a string containing genre and names attached to the film

Data Set Example

{"text":"Action Adventure Sci-Fi Bryan Singer Patrick Stewart Hugh Jackman Ian McKellen Famke Janssen","category":"150"}

157 million gross

Predict gross for: Action movie with Jackman and Singer??

const brain = require('brain.js');
const data = require('./movies.json');
const network = new brain.recurrent.LSTM();
const trainingData = data.map(item => ({
  input: item.text,
  output: item.category
}));

network.train(trainingData, {
  iterations: 100
});
let movie = 'Action Bryan Singer Hugh Jackman');
const output = network.run(movie);
console.log('Category:' + output);

My Brain.js Prediction = 100Million

X2: X-Men United (2003)

$110 Million

MY DATA WASN'T GREAT

I forgot movies can have 2 directors, no data on new actors, etc...

Take aways

AI and Machine Learning come with ethical questions

This technology is already everywhere

This is the future

Made with Slides.com