Deep learning
Machine learning using neural networks with many layers, each learning features from the one before. Suited to large volumes of text, images and audio, and hard to explain.
Where you will meet it
Deep learning appears in 3 learning outcomes on the CFA syllabus. A few of them:
- Explain what is meant by machine learning, artificial intelligence and big data
“Machine learning is the practical subset that infers a rule from data rather than being given one: supervised learning trains on labelled examples, unsupervised learning looks for structure in unlabelled data, and deep learning stacks layers to capture relationships too complex to specify in advance.”
- Explain what deep learning is, and what machine learning is in its supervised and unsupervised forms
“Deep learning uses neural networks with many hidden layers, each transforming the previous layer's output through weights and non-linear activation functions, which suits images, speech and text.”
- Explain deep, supervised and unsupervised learning and how investment managers use them
“Deep learning uses neural networks with many layers that learn their own features, suiting large volumes of text, images and audio.”
See also
Practise it
Practise deep learning until it is automatic: questions that explain every wrong option.
Take the free diagnostic →