Questions

  • What is Machine Learning?
  • Why is Python good for ML?

Objectives

  • Understand the Python ecosystem and tools for Machine Learning.

This course builds on the foundations of Python programming. We will utilise common geosicence data types (geospatial, temporal, vector, raster, etc) to demonstrate a variety of practical workflows and showcase fundamental capabilities of Machine Learning with Python. We will carry out exploratory, analytical, computational and machine learning analyses on these datasets. At the end of the course you will be able to adapt these workflows to your own datasets.

Machine Learning

Machine Learning are types of algorithms that get better the more you use them!

Supervised learning algorithms build a mathematical model of a set of data. The data is known as training data. Each training example has one or more inputs (features) and the desired output (target). Through iterative optimization of an objective function, supervised learning algorithms learn a function that can be used to predict the output associated with new inputs.

Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. The algorithms learn from test data that has not been labeled, classified or categorized.

Deep learning refers to machine learning methods based on neural networks.

Artifical Intelligence is all of the above and more.

Just go read this review paper

Tools

  • Pandas, Numpy, Scipy - standard data analysis and math tools.
  • Scikit-learn Simple and efficient tools for predictive data analysis. General ML.
  • TensorFlow A focus on Deep Learning tasks.
  • PyTorch I can’t find a good reason to pick one over the other generally, but for specific problems choose what works easiest for your workflow!

Now let’s get into in the practical session!

Key points

  • Python is a programming language.
  • There is a rich ecosystem of tools around creating and deploying Python code for ML.