Home / IT & Computer Science / Deep Learning for Bioscientists / Practical: Adjusting hyperparameters
Practical: Adjusting hyperparameters
A link to a practical in Colab, which demonstrates adjusting hyperparameters for the training of a simple deep learning model.
© The University of Nottingham
A look at adjusting training hyperparameters and other settings.
In the linked Colab notebook we will try to improve the performance of our simple network both in terms of accuracy and speed.
In the notebook we will cover the following:
- dataset size and batch size
- GPU acceleration with CUDA
- changing the learning rate
- setting up a scheduler to change the learning rate during training.
Follow the link below and work through the Colab notebook step by step.
You may wish to open the link in a new browser tab so you can refer back here quickly.
Please leave any questions or comments below.
Reach your personal and professional goals
Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.
Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.
