Skip to content
/ ml Public

ML experiments in tensorflow and tensorflowjs

Notifications You must be signed in to change notification settings

MAGSON-dev/ml

Repository files navigation

Gitter

Magson - Machine Learning Experiments

This is the official repositories with all of Magson's machine learning experiments and notes.

Experiments

Table of Contents

Tensorflow in Python
TensorflowJS

Notes

ML Terminology

Machine learning systems learn how to combine input to produce useful predictions on never-before-seen data.
  • Labels: is what we try to predict. E.g. the y variable in linear regression.
  • Features: is an input variable. E.g. the x variable in linear regression.
  • Model: defines the relationship between features and labels.

Regression VS. Classification

Regression model predicts continous values. E.g:

  • What is the value of the house?
  • What is the probability that a user clicks an ad?

Classification model predicts discrete values:

  • Is mail spam or not spam?
  • Is this image of a dog or cat?

Linear regression

y = mx + b
  • y is the value we try to predict
  • m is the slope of the line
  • x is the input feature
  • b is the y-intercept

By convention in machine learning, you'll write the equation for a model slightly differently:

y = b + wx
  • y = predicted labels
  • b = biases
  • w = weights
  • x = features