← All articles

Deep Learning and Neural Networks

Deep Learning and Neural Networks explainers and exam-revision guides from Full Marks Press.

AllAI Ethics and Responsible AIComputer VisionDeep Learning and Neural NetworksGenerative AI and NLPMachine LearningMaths, Programming and MLOpsRevision and Lecturer Resources
Activation functions compared: ReLU, Sigmoid and Tanh
Deep Learning and Neural Networks

Activation functions compared: ReLU, Sigmoid and Tanh

Activation functions introduce non-linear properties to neural networks, allowing them to learn complex patterns rather than just computing linear transforma

How do convolutional neural networks actually work?
Deep Learning and Neural Networks

How do convolutional neural networks actually work?

Convolutional neural networks (CNNs) work by sliding small grids of weights, called filters, over input data to detect local patterns like edges, textures, a

How to answer exam questions on deep learning architectures
Deep Learning and Neural Networks

How to answer exam questions on deep learning architectures

To answer exam questions on deep learning architectures correctly, you must match the specific data type and problem domain to the mathematical mechanics of

How to structure a deep learning essay for postgraduate modules
Deep Learning and Neural Networks

How to structure a deep learning essay for postgraduate modules

To structure a deep learning essay for a postgraduate module, you must explicitly divide your answer into problem definition, architectural justification, tr

Recurrent neural networks vs feedforward networks: key exam differences
Deep Learning and Neural Networks

Recurrent neural networks vs feedforward networks: key exam differences

The primary difference between a recurrent neural network and a feedforward neural network is how information flows through the architecture. Feedforward net

What are the common pitfalls when training neural networks?
Deep Learning and Neural Networks

What are the common pitfalls when training neural networks?

The most common pitfalls when training neural networks are overfitting to the training data, choosing an inappropriate learning rate, and encountering vanish

What is backpropagation and how do you calculate it in an exam?
Deep Learning and Neural Networks

What is backpropagation and how do you calculate it in an exam?

Backpropagation is the algorithm used to train neural networks by calculating the gradient of the loss function with respect to each individual weight and bi

Frequently asked questions

What does the Deep Learning and Neural Networks category cover?

It collects exam-focused Deep Learning and Neural Networks explainers and revision guides from Full Marks Press, written for university students.

Who writes these Deep Learning and Neural Networks guides?

Every article is written by Sotiris Spyrou, published by Full Marks Press.

Are these guides free?

Yes. Every article is free to read, and you can request a free review copy of the related guide at https://fullmarkspress.com/free.