Advanced: End-to-End Machine Learning

Overview

Course details

The course introduces you to basic neural networks using the scikit-learn Python package. It covers the key concepts, techniques and technologies for training and prediction using multilayer perceptrons and the Keras Python package. 

The course also includes specialised and advanced coverage of modern deep learning techniques and tools, based on both the Keras and TensorFlow Python packages. 

You will learn:

• custom neural net models using Tensorflow
• deep computer vision using convolutional neural networks
• modelling time-series data with recurrent neural networks and
• artificial intelligence (AI) generation of images using autoencoders, generative adaptive networks, and diffusion techniques. 

Advanced Python code is supplied and explained for each topic.

Your primary learning outcome is the ability to deploy and assess the state-of-the-art technologies that underpin modern AI-based machine learning and data science. 

Who is this course for?

The course is aimed at professionals with a high level of numeracy who are seeking to understand the core concepts, methods and technologies that underpin modern deep learning using artificial neural networks (ANNs). 

The topics explain the key methods used to derive predictive models using multilayer perceptrons, convolutional and recurrent neural networks (CNNs and RNNs), and generative AI to produce high-quality new data.  

The ability to perform Deep Learning workflows is a core skill in many fields including:

• finance (prediction of future stock values) 
• healthcare (tumour detection in scans) 
• marketing (personalising the user experience). 

Teaching format

This is a self-paced online learning short course with lecture content, interactive elements, and access to a masterclass with the course leader after completion of the course. 

Course requirements

The course is suitable for advanced Python programmers (including notebooks, packages, data manipulation, design and use of pipelines, model evaluation functions, image pre-processing, ability to understand and work with Keras and Tensorflow documentation). Completion of Intermediate: End-to-End Machine Learning will provide a good basis for completing this short course. 

The focus of the course is the use of released and curated Python machine learning code, rather than implementing algorithms from scratch. 

Coursework involves creating code to solve a specific problem, together with a short report that describes the approach taken and critically evaluates the results. This code can be developed either using learners’ equipment (such as a laptop or PC), or with cloud-based tools such as CoLab and Kaggle Notebooks, or Jupyter notebook. A good internet connection is more important than powerful computational equipment. 

The time commitment is typically six to eight hours per week.