Machine Learning - Learning Steps

Step 1
INTRODUCTION TO MACHINE LEARNING
Overview of Machine Learning
Supervised vs. Unsupervised Learning
Classification vs. Regression
Real-world Applications

Step 2
WORKING WITH REAL-WORLD DATA
Cleaning and mining real-world data
Data pre-processing
Exploratory data analysis and visualisation

Step 3
BUILDING YOUR FIRST CLASSIFICATION MODEL
The K Nearest Neighbour (KNN) algorithm
Reporting performance metrics
Decision boundary visualisation

Step 4
VALIDATION AND OPTIMISATION
Validation techniques
The bias-variance trade-off
Hyper-parameter tuning, grid search and model selection

Step 5
RANDOM FORESTS
Decision Trees
Ensemble models
Random Forests
Extremely Randomised Trees

Step 6
PRACTICE
Build and optimise a classifier on new real-world data

Step 7
NEURAL NETWORKS
Biological inspiration and architecture
Network topologies
Learning algorithms and cost functions

Step 8
DEEP LEARNING
Motivation and architecture
Real-world examples
Impact and limitations of Deep Learning

Like the below page to get update  
https://www.facebook.com/datastage4you
https://twitter.com/datagenx
https://plus.google.com/+AtulSingh0/posts
https://datagenx.slack.com/messages/datascience/