Datasets and dataloaders
Any deep learning project will need a way to efficiently handle your data. This is where datasets and dataloaders come in. These are objects in PyTorch, but similar object types …
Course: Deep Learning for Bioscientists
Machine learning versus deep learning
How do they differ? Before we look more closely at convolutional neural networks, and the layers and the other components they are made out of, let’s just recap the fundamentals …
Convolutional neural network overview
In the following exercises we will begin to look at how we can make CNNs using PyTorch. This video gives an overview of the different steps we will need to …
Tensors
What are tensors? In the previous activity we looked at the layers and other functions that make up convolutional neural network architectures. You can think of tensors as the signals …
Practical: Using Pytorch in Colab
In the first practical of the course we will work through a short Colab notebook introducing PyTorch in Colab In the linked Colab notebook we will look at the following: …
GPU acceleration
A brief overview of GPU acceleration, CUDA, and their use in PyTorch and Colab. Though to an extent we don’t need to worry too much about GPU acceleration with CUDA, …
Introduction to PyTorch
In the previous video we mentioned we will be using the Python deep learning library PyTorch on this course. In this article, we will give a brief introduction to PyTorch, …
Deep learning layers
An overview of some of the main components found in convolutional neural networks, including: convolution layers max pooling layers activation functions. We’ll go into each these components in more detail …
Deep learning libraries
A discussion of the main deep learning libraries, in particular the one we will be using for the course, PyTorch. The code we will use during this course is written …
Recap of machine learning
What is the difference between machine learning and deep learning? A recap of some of the familiar ideas from machine learning that we can transfer to deep learning, and what …
Introduction to the course
Welcome to Deep Learning for Bioscientists. The course is designed to take around two to three hours a week over five weeks to complete. It is aimed at bioscience professionals, …
Introduction to week 5
Welcome to the final week of the course. Hopefully by now you should have a good ida of how deep learning, and in particular convolutional neural networks (CNNs), can be …
Introduction to week 4
Welcome to week 4. So far, we have learned about what deep learning is, how to put together simple deep learning networks using PyTorch, and looked at how to train …
Introduction to week 3
Welcome to Week 3 of the course. Once we have built a network using the software tool of choice (we are using PyTorch), the next step is to train the …
Introduction to week 2
Welcome to week 2 of the course. In the first week we had a broader look at the main differences between traditional machine learning and deep learning, and introduced PyTorch …