Short Title:Applied Artificial Intelligence and Deep Learning
Full Title:Applied Artificial Intelligence and Deep Learning
Language of Instruction:English
Module Code:AADL H4002
 
Credits: 5
Field of Study:Computer Science
Module Delivered in 8 programme(s)
Reviewed By:FINBARR FEENEY
Module Author:Keith Quille
Module Description:The aims of this module are: To instill an understanding of the foundations, the applied design, and architectures of artificial neural networks. To be able to apply these techniques to deep learning networks. To be able to apply and to defend the design choices of the model, based on best practices.
Learning Outcomes
On successful completion of this module the learner will be able to:
LO1 Discuss and explain the general principles of artificial neural networks and deep learning networks
LO2 Distinguish between and select appropriate hyper-parameters for training artificial neural networks
LO3 Demonstrate an understanding in determining performance of artificial neural networks
LO4 Apply artificial neural networks and deep learning techniques to several contexts
 

Module Content & Assessment

Course Work
Assessment Type Assessment Description Outcome addressed % of total Assessment Date
Laboratory Sample CA1: Design, develop an artificial neural network for a specific context, with an emphasis on hyper-parameter tuning, and performance assessment techniques. 1,2,3 25.00 n/a
Continuous Assessment Sample CA2: Given a particular data set or problem, develop an appropriate artificial neural network. Interpret the results and produce findings. 2,3,4 25.00 n/a
End of Module Formal Examination
Assessment Type Assessment Description Outcome addressed % of total Assessment Date
Formal Exam End-Of-Semester Final Examination   50.00 End-of-Semester

TU Dublin – Tallaght Campus reserves the right to alter the nature and timings of assessment

 

Module Workload

Workload: Full Time
Workload Type Workload Description Hours Frequency Average Weekly Learner Workload
Lecture Class Based Instruction 2.00 Every Week 2.00
Laboratories Practical/Workshops 2.00 Every Week 2.00
Independent Learning Time Reading/Studying 4.00 Every Week 4.00
Total Weekly Learner Workload 8.00
Total Weekly Contact Hours 4.00
Workload: Part Time
Workload Type Workload Description Hours Frequency Average Weekly Learner Workload
Lecture Class/Lab Based Instruction 4.00 Every Second Week 2.00
Independent Learning Reading/Studying 4.00 Every Week 4.00
Total Weekly Learner Workload 6.00
Total Weekly Contact Hours 2.00
 

Module Resources

Required Book Resources
  • Jason Brownlee 2017, Deep Learning with Python. Develop Deep Learning Models on Theano and TensorFlow using Keras., v10, Machine Learning Mastery Ed.
  • Antonio Gulli 2017, Deep Learning with Keras: Implementing deep learning models and neural networks with the power of Python, Packt [ISBN: 9781787128422]
Recommended Book Resources
  • Ian H.Witten et al 2017, Data Mining: Practical Machine Learning Tools and Tecniques, 4th Ed., MK [ISBN: 978-012804291]
This module does not have any article/paper resources
This module does not have any other resources
 

Module Delivered in

Programme Code Programme Semester Delivery
TA_KACTM_B Bachelor of Science (Honours) in Computing with Information Technology Management 8 Elective
TA_KCITM_B Bachelor of Science (Honours) in Computing with Information Technology Management - Year 4 ( Add on) 8 Elective
TA_KACOS_B Bachelor of Science (Honours) in Computing with Software Development 8 Elective
TA_KCOSD_B Bachelor of Science (Honours) in Computing with Software Development - Year 4 ( Add on) 2 Elective
TA_KITMG_B Bachelor of Science (Honours) IT Management (add On) 8 Elective
TA_KACOD_B Bachelor of Science (Hons) in Computing with Data Analytics 8 Mandatory
TA_KCODA_B Bachelor of Science (Hons) in Computing with Data Analytics (Add-On) 2 Mandatory
TA_KMLAI_B Certificate in Machine Learning & Artificial Intelligence 2 Mandatory