Close
Description
Deep learning is a modern and exciting approach to machine learning that is delivering state-of-the-art performance in many real-world applications of data science. Deep learning achieves its flexibility and power by representing the world as a nested hierarchy of concepts based on networks of primitive processing units, much like a neural architecture. This module provides an introduction to the goals and methods of deep learning with particular focus on its application to problems in the processing of speech signals and natural language text. Topics will include the history of deep learning and its relationship to other machine learning approaches, the mathematical and computational infrastructure of deep learning, a review of popular deep learning architectures and strategies, applications of deep learning to word semantics, parsing, machine translation and question answering, applications of deep learning to speech recognition, speech synthesis and paralinguistics, and the relationship between deep learning and general artificial intelligence.
The course will be presented as a mixture of seminars and hands-on laboratory sessions with deep learning tools. The course is designed to be accessible to psychology and linguistics students. While there is no formal requirement for programming skills, students should have basic skills in Python or a similar language such as R. Materials and help for self-study will be provided but acquiring basic skills in Python is not part of in-person sessions. By the start of Week 3, students are expected have a basic understanding of programming concepts like variables, functions and classes, and to be familiar with working with packages.
The course will be presented as a series of interactive seminars and laboratory sessions. The seminars will be used to introduce concepts of deep learning and to describe and demonstrate deep learning applications in speech and natural language processing. The seminars will be based around a set of internet materials which students will have been expected to study before the meeting. The laboratory sessions will provide 鈥渉ands-on鈥� experience of the design, training and operation of deep learning models. This will be achieved using Python and TensorFlow, and web-based tools such as Google Colaboratory.
Indicative Topics
The topics will be similar to those of the last year but are subject to change due to the development of deep learning.
Topics covered were:
- Principles of deep learning and machine learning
- Preparation of text and speech for machine learning
- Lexical semantics and word embeddings
- Multilayer perceptrons
- Convolutional and recurrent neural networks
- Sequence-to-sequence models
- Language modelling
- Human-machine-dialogue systems
- Ethics of AI
Module Aims
- To provide an introduction to machine learning as a means to build applications in speech and natural language in contrast to knowledge-based approaches
- To provide an introduction to the deep learning approach to machine learning in terms of its history, its methods, and its mathematical and computational foundations
- To provide an overview of essential elements of deep learning systems in terms of data representation, node types, network structure, loss functions, and optimization algorithms
- To demonstrate how deep learning is being used to build applications in speech and natural language processing
- To provide practical experience in building, training and running deep learning systems on speech and text data
听
听
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 8th April 2024.
听