Module: Introduction to Deep Learning

Module Specifications

Academic Year 2026 - 2027

Module Title	Introduction to Deep Learning
Module Code	CSC1207
Faculty	Engineering & Computing	School	Computing
NFQ level	8	Credit Rating	7.5

Description

Deep learning algorithms represent a family of machine learning approaches that have proven instrumental in many applications that use unstructured data such as natural language and images. Developments in deep learning have therefore led to significant advancements in a wide range of tasks from language generation and machine translation, to image classification and speech recognition. This module will delve into the foundations of modern deep learning approaches and help students understand how they can be applied to a number of modalities including text, images and sound, for a range of different tasks.

Learning Outcomes

1. Explain the fundamental concepts underlying neural network architectures including the backpropagation algorithm.
2. Train deep learning models using appropriate optimisation algorithms and regularisation techniques.
3. Explain how neural networks can be used for both language-related and computer vision tasks, including machine translation, speech recognition and image classification.
4. Describe the structure of common modern neural network architectures such as the Transformer architecture and Convolutional Neural Networks.
5. Use transfer learning to fine-tune neural networks in low-resource settings.
6. Explain the effects of datasets on deep learning models and the ethical issues associated with these techniques, both social and environmental.

*Type*	*Hours*	*Description*
Workload	Full time hours per semester
Lecture	24	Two lectures a week
Laboratory	24	One two-hour lab session a week
Independent Study	90	Preparation and revision for lab quizzes
Independent Study	49.5	Studying material presented in lecture, reading research papers
Total Workload: 187.5

Section Breakdown
CRN	21474	Part of Term	Semester 2
Coursework	30%	Examination Weight	70%
Grade Scale	40PASS	Pass Both Elements	N
Resit Category	RC1	Best Mark	N
Module Co-ordinator	Ellen Rushe	Module Teacher	Andrew Way (Emeritus Prof), Brian Davis, John McKenna, Kolawole John Adebayo, Maja Popovic

Type	Description	% of total	Assessment Date
Assessment Breakdown
Loop Quiz	Lab assessment on the fundamentals of neural networks (all material from week 1-5 inclusive).	10%	Week 6
Loop Quiz	Lab assessment on the specific neural network architectures used to learn from different modalities (all material from week 6-8 inclusive).	10%	Week 9
Loop Quiz	Lab assessment on transfer learning, learning with limited data and the effects of datasets on deep learning models (all material from week 9-11 inclusive).	10%	Week 12
Formal Examination	End-of-Semester Final Examination	70%	End-of-Semester

Reassessment Requirement Type
Resit arrangements are explained by the following categories; RC1: A resit is available for both^* components of the module. RC2: No resit is available for a 100% coursework module. RC3: No resit is available for the coursework component where there is a coursework and summative examination element. ^* ‘Both’ is used in the context of the module having a coursework/summative examination split; where the module is 100% coursework, there will also be a resit of the assessment

Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Introduction to neural networks
The fundamentals of artificial neural networks.

Training neural networks
Neural network training and regularisation.

Deep learning architectures
What are the common deep learning architectures? How do they work and what are they used for?

Deep learning for different modalities
How deep learning models learn from text, visual data and sound.

Transfer learning and low resource learning
How neural networks can learn with limited data using transfer learning.

Effect of deep learning on society and the environment
The effects of dataset bias on deep learning algorithms and the ethical issues associated with these techniques.

Indicative Reading List

Books:

Daniel Jurafsky and James H. Martin: 2026, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models. 3rd Edition., URL: https://web.stanford.edu/~jurafsky/slp3,
Ian Goodfellow, Yoshua Bengio and Aaron Courville: 2016, Deep learning, MIT Press, URL: http://www.deeplearningbook.org,

Articles:
None

Other Resources

None