Module Details
Module Code: |
ELEC C4602 |
Module Title:
|
Artificial Intelligence and Machine Learning
|
Title:
|
Artificial Intelligence and Machine Learning
|
Module Level:: |
8 |
Module Coordinator: |
Frances Hardiman
|
Module Author:: |
James Garland
|
Module Description: |
AI and ML techniques are not new, however, due to the internet's ubiquitous availability of data and compute to train ML networks, their performance has, for example, surpassed that of human visual recognition. This module investigates methods of design, training, and validation of classification neural network models to provide the student with a demonstratable understanding of machine learning's underlying scientific principles.
|
Learning Outcomes |
On successful completion of this module the learner will be able to: |
# |
Learning Outcome Description |
LO1 |
Demonstrate the differences between artificial intelligence, machine learning and deep learning systems. |
LO2 |
Compose, assemble, clean, and pre-process training data. |
LO3 |
Train image recognition deep learning models. |
LO4 |
Develop and solve computer vision problems with appropriate models. |
LO5 |
Design the components of an image acquisition system. |
Dependencies |
Module Recommendations
This is prior learning (or a practical skill) that is recommended before enrolment in this module.
|
No recommendations listed |
Co-requisite Modules
|
No Co-requisite modules listed |
Additional Requisite Information
|
No Co Requisites listed
|
Indicative Content |
Artificial Intelligence
Define AI from narrow to broad to general to super-general artificial intelligence. Give examples of different types and fields of AI, such as text and speech recognition, natural language processing, search and recommendation algorithms, vision detection and recognition.
|
Neural Networks
Fully connected networks, representation learning models, and convolution neural networks. Different machine learning (ML) models such as LeNet, AlexNet, VGG, Inception, ResNet, Xception, U-net, Fully Convolutional, Attention.
|
Machine Learning
Supervised, unsupervised, semi-supervised learning, reinforcement learning, and their applications. Linear regression, logistic regression, Support Vector Machines, natural language processing.
|
Data cleaning and pre-processing
Training data analysis and modelling.
|
Training
Different training techniques for models, e.g. optimisation, regularisation, batch normalisation, and dropout
|
Metrics
Confusion matrices, area under the curve (AUC), receiver operator characteristics (ROC), classification accuracy.
|
Ethics
Data privacy, algorithm and data bias, model misuse.
|
Module Content & Assessment
|
Assessment Breakdown | % |
Continuous Assessment | 20.00% |
Practical | 20.00% |
End of Module Formal Examination | 60.00% |
AssessmentsFull Time
End of Module Formal Examination |
|
Reassessment Requirement |
Repeat examination
Reassessment of this module will consist of a repeat examination. It is possible that there will also be a requirement to be reassessed in a coursework element.
|
SETU Carlow Campus reserves the right to alter the nature and timings of assessment
Module Workload
Workload: Full Time |
Workload Type |
Workload Category |
Contact Type |
Workload Description |
Frequency |
Average Weekly Learner Workload |
Hours |
Lecture |
|
Contact |
No Description |
Every Week |
3.00 |
3 |
Laboratory |
|
Contact |
No Description |
Every Week |
2.00 |
2 |
Independent Learning |
|
Non Contact |
No Description |
Every Week |
6.00 |
6 |
Total Weekly Contact Hours |
5.00 |
Module Resources
|
Recommended Book Resources |
---|
-
GĂ©ron, A.. (2019), Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems., O'Reilly Media.
-
Goodfellow, I., Bengio, Y., Courville, A.. (2016), Deep learning, 2. Cambridge: MIT press.
-
Bishop, C. (2006), Pattern Recognition and Machine Learning., Springer.
| This module does not have any article/paper resources |
---|
This module does not have any other resources |
---|
|