Deep Learning for Bioscientists

Elevate your research with deep learning

Deep learning, a popular branch of machine learning, enables computers to process data like the human brain, using similar approaches to how we believe our brains process information, to help with solving complex problems and generating highly accurate insights.

On this five-week course, you’ll develop essential knowledge of deep learning to understand how it can help your research in bioscience.

You’ll be guided through deep learning techniques and gain practical skills you can use outside of the course.

Explore techniques for using PyTorch

You’ll start by discussing how deep learning differs from machine learning as you’re introduced to a commonly used deep learning software package, PyTorch.

Throughout the course, you’ll take part in practical exercises to cement your knowledge and ensure you can use your skills in your context.

Develop your understanding of convolutional neural networks

You’ll then go on to explore convolutional networks in detail as you discover some common network architectures and their applications.

This includes classification, regression, and 2D approaches as well as more advanced topics such as multi-task learning.

Learn from the experts at the University of Nottingham and the University of Lincoln

Throughout the course, you’ll benefit from the specialist knowledge of experts from the University of Nottingham and University of Lincoln.

With their guidance, you’ll finish with the skills and knowledge to apply deep learning to benefit your research.

This course is designed for researchers and other professionals working in the field of plant phenotyping or related bioscience disciplines who want to learn more about what deep learning is and how it can be applied.

It will also be useful to any scientist who wishes to use AI approaches to analyse images.

• Introduction to deep learning
• Machine learning versus deep learning
• Deep learning libraries and PyTorch
• Summary and review
• Convolutional neural networks
• Network components
• Tensors and dimensionality
• A simple CNN
• Summary and review
• Training CNNs
• The training loop
• Hyperparameters
• Datasets and dataloaders
• Summary and review
• Classification and regression
• Encoder architectures
• Making an image classifier in PyTorch
• Regression using deep learning
• Summary and review
• Spatial approaches and more
• Encoder-decoder architectures
• More advanced topics
• Summary and review