Machine learning is a broad topic, with a wide range of applications in scientific research. 

In this series of lectures, we will introduce the fundamental concepts of unsupervised and supervised learning, including the training, testing and evaluation of models for classification and regression.  We also explore the basic theory of neural networks and discuss their applications to deep learning.

 Examples will be provided using Orange data science environment.  No prior experience of programming is required.

Syllabus:

• Unsupervised learning
  • Clustering
• Supervised learning
  • Generalised linear models
  • Logistic regression
  • Decision trees
• Evaluating performance
  • Cross-validation
  • ROC curves
• Improving performance
  • Feature selection
  • Ensemble methods
• Artificial neural networks
  • Multi-layer perceptron
  • Stochastic gradient descent
  • Activation functions
  • Deep learning applications

Learning Outcomes:

After completing this workshop, you will be better able to:

• Explain the difference between supervised and unsupervised learning.
• Select a suitable machine learning method for a given application.
• Prepare your own training and testing data sets.
• Evaluate the performance of a machine learning experiment.

Dates & Booking Information

Please select a date and book on via Inkpath using your Imperial Single-Sign-On.