Machine Learning for Python Developers (Practical)

Overview

A hands-on introduction to core Machine Learning techniques, this course will familiarise you with the Machine Learning landscape as well as providing practical experience.

Learning Objectives

• To have a familiarity with the Machine Learning landscape
• Understand the different types of Machine Learning algorithms
• Identify suitable Machine Learning techniques for different types of data
• To be able to implement and evaluate basic Machine Learning algorithms using Python libraries

Who is this course for

This is ideally suited for Python developers. No Machine Learning experience is required.

Pre-requisites

• Proficiency in Python development including: array manipulations with NumPy, loading libraries, and plotting using Matplotlib.
• Laptop with the latest version of Python and
• A suitable IDE (PyCharm)
• Anaconda 3 interpreter
• TensorFlow 1.0

Course Outline Summary

Day 1: The Machine Learning Landscape

Introduction

• A high level overview of key Machine Learning concepts
• Overview of Machine Learning tools and resources for Python

Topic 1

• Introduction to Regression: a supervised learning technique
• Regression analysis
• Regression lab

Topic 2

• Working with data
• Feature transformation introduction and demonstration
• Feature selection introduction and demonstration
• Feature selection and transformation labs

Topic 3

• Introduction to clustering: an unsupervised learning technique
• Clustering lab

Topic 4

• Introduction to data classification
• Classifying data using Naïve Bayes lab

Topic 5

• Introduction to time-series analysis
• Time series analysis demonstration

Day 2: Neural Networks with TensorFlow

Introduction

• Introduction to Neural Networks
• Introduction to TensorFlow
• Demonstration

Topic 1

• A simple network: lab
• Tuning and hyperparameters

Topic 2

• More complex network labs:
• Image recognition
• Recurrent Neural Networks