BSc Neuroscience and Psychology 2023-2024
Machine Learning in Neuroscience
(6PASNMLN)
Module Guide
Educational aims of the module
Machine learning is the field of study that gives algorithms the ability to learn without
being explicitly programmed. Machine learning methods are being applied across a
wide range of contexts, including neuroscience.
This module will introduce students to core categories of machine learning. We will first
explore regression, demonstrating its translation from an inferential statistical method
to a form of supervised machine learning designed to make predictions about new
instances of data. Students will subsequently learn about classification, and its use for
predicting categorical labels, such as disease status. Alongside both types of
supervised learning, students will learn about related methods for robust model fitting
and evaluation. The module will then introduce unsupervised learning for data
decomposition and dimensionality reduction. Students will also be introduced to ideas
behind deep learning. The module will conclude with an introduction to reinforcement
learning.
Core concepts will be introduced in interactive lectures, before in-depth exploration of
machine learning applications to open neuroscientific and behavioral data during
hands-on workshops using the Python programming language.
Module Learning Outcomes
G1. Apply machine learning methods to neuroscientific data.
G2. Demonstrate understanding and use of key machine learning methods,
including model selection, application and evaluation.
G3. Explain core categories of machine learning, including supervised,
unsupervised, reinforcement and deep learning.
1
6PASNMLN v1.1 – FV & RL, Last Updated: 18th December 2023
, G4. Demonstrate programming skills in Python.
Module delivery
The content and teaching for this module will be delivered via in-person interactive
lectures and through computer-based workshops. Lectures will include a combination
of traditional presentations, interactive questions, discussions and demonstrations.
This module will consist of 10 weeks, with one 1h lectures and one 2h programming
practical session each week. You are expected to attend all practical sessions.
Additionally, there are two 2h workshop sessions in weeks 6 and 7 to provide support
regarding the main summative assessment (programming assignment with
presentation).
A range of supporting materials will be available to you in the form of copies of the
presentation slides, core and optional reading as well as videos with additional
material.
Online support
You will have access to support from the module leader and teaching staff throughout
the module. Our preferred method of answering questions is in person, before / during /
after the lecture or practical. However, there is also a designated Q&A forum where you
can post questions related to the module. The module team will aim to respond to
questions posted on this forum within two working days. Important information about
the module will be posted in the Announcements forum.
Independent study
Core reading: Each topic is accompanied by a core reading material, drawn
primarily from peer-reviewed journal articles. Students are expected to read these
materials in advance of or during the study of that topic.
Optional reading: Additional reading material will be provided each week.
Additionally, a reference list will be provided at the end of each lecture. These
provide a useful starting point for a broader understanding of each topic.
Guest lectures: On selected weeks, a pre-recorded guest lecture will be shared
through KEATS, which will provide a research-oriented perspective on material
covered in the live lecture.
Programming practice: you are advised to continue work on the code from
programming workshops during your own time, in order to be comfortable with all of
the tasks presented.
2
6PASNMLN v1.1 – FV & RL, Last Updated: 18th December 2023
Machine Learning in Neuroscience
(6PASNMLN)
Module Guide
Educational aims of the module
Machine learning is the field of study that gives algorithms the ability to learn without
being explicitly programmed. Machine learning methods are being applied across a
wide range of contexts, including neuroscience.
This module will introduce students to core categories of machine learning. We will first
explore regression, demonstrating its translation from an inferential statistical method
to a form of supervised machine learning designed to make predictions about new
instances of data. Students will subsequently learn about classification, and its use for
predicting categorical labels, such as disease status. Alongside both types of
supervised learning, students will learn about related methods for robust model fitting
and evaluation. The module will then introduce unsupervised learning for data
decomposition and dimensionality reduction. Students will also be introduced to ideas
behind deep learning. The module will conclude with an introduction to reinforcement
learning.
Core concepts will be introduced in interactive lectures, before in-depth exploration of
machine learning applications to open neuroscientific and behavioral data during
hands-on workshops using the Python programming language.
Module Learning Outcomes
G1. Apply machine learning methods to neuroscientific data.
G2. Demonstrate understanding and use of key machine learning methods,
including model selection, application and evaluation.
G3. Explain core categories of machine learning, including supervised,
unsupervised, reinforcement and deep learning.
1
6PASNMLN v1.1 – FV & RL, Last Updated: 18th December 2023
, G4. Demonstrate programming skills in Python.
Module delivery
The content and teaching for this module will be delivered via in-person interactive
lectures and through computer-based workshops. Lectures will include a combination
of traditional presentations, interactive questions, discussions and demonstrations.
This module will consist of 10 weeks, with one 1h lectures and one 2h programming
practical session each week. You are expected to attend all practical sessions.
Additionally, there are two 2h workshop sessions in weeks 6 and 7 to provide support
regarding the main summative assessment (programming assignment with
presentation).
A range of supporting materials will be available to you in the form of copies of the
presentation slides, core and optional reading as well as videos with additional
material.
Online support
You will have access to support from the module leader and teaching staff throughout
the module. Our preferred method of answering questions is in person, before / during /
after the lecture or practical. However, there is also a designated Q&A forum where you
can post questions related to the module. The module team will aim to respond to
questions posted on this forum within two working days. Important information about
the module will be posted in the Announcements forum.
Independent study
Core reading: Each topic is accompanied by a core reading material, drawn
primarily from peer-reviewed journal articles. Students are expected to read these
materials in advance of or during the study of that topic.
Optional reading: Additional reading material will be provided each week.
Additionally, a reference list will be provided at the end of each lecture. These
provide a useful starting point for a broader understanding of each topic.
Guest lectures: On selected weeks, a pre-recorded guest lecture will be shared
through KEATS, which will provide a research-oriented perspective on material
covered in the live lecture.
Programming practice: you are advised to continue work on the code from
programming workshops during your own time, in order to be comfortable with all of
the tasks presented.
2
6PASNMLN v1.1 – FV & RL, Last Updated: 18th December 2023
