| Module Code: |
H7IAIML |
|
Long Title
|
Introduction to Artificial Intelligence and Machine Learning
|
|
Title
|
Introduction to Artificial Intelligence and Machine Learning
|
| Module Level: |
LEVEL 7 |
| EQF Level: |
6 |
| EHEA Level: |
First Cycle |
| Module Author: |
Alex Courtney |
| Departments: |
School of Computing
|
| Specifications of the qualifications and experience required of staff |
MSc and/or PhD degree in computer science or cognate discipline. May have industry experience also.
|
| Learning Outcomes |
| On successful completion of this module the learner will be able to: |
| # |
Learning Outcome Description |
| LO1 |
Describe the theory and concepts underpinning Artificial Intelligence (AI), as well as discuss the seminal, current applications of AI and their implications |
| LO2 |
Apply fundamental techniques in both descriptive and inferential statistics for real world problems |
| LO3 |
Contrast fundamental data mining and machine learning concepts and techniques, and discuss their applicability to different problems |
| LO4 |
Build and evaluate simple machine learning models on various datasets and problem domains |
| Dependencies |
Module Recommendations
This is prior learning (or a practical skill) that is required before enrolment on this module. While the prior learning is expressed as named NCI module(s) it also allows for learning (in another module or modules) which is equivalent to the learning specified in the named module(s).
|
| No recommendations listed |
Co-requisite Modules
|
| No Co-requisite modules listed |
| Entry requirements |
Learners should have attained the knowledge, skills and competence gained from stage 2 of the BSc (Hons) in Computer Science
|
Module Content & Assessment
| Indicative Content |
|
Introduction to Artificial Intelligence
Foundations of AI: philosophy, maths, psychology, computing, linguistics, logic, probability theory. Historical evolution of the field. Weak vs Strong AI. Ethical implications of AI
|
|
Agents
Percepts, actions, goals, environment. Simple reflex agents. Reflex agents with state. Goal based agents. Utility based agents
|
|
Search Strategies in AI
Uninformed Search strategies: Uniform Cost, Breadth-First, Depth-First. Informed Search strategies: Greedy Best First Search, A* Search, Heuristic functions
|
|
Selected Topics in AI
High-level overview and Applications of AI Techniques such as Mathematical Optimization, Machine Learning, Natural Language Processing, Recommender Systems, Deep Learning, Computer Vision and Knowledge Representation
|
|
Descriptive Statistics
Arrangement, pre-processing and representation of data. Measures of central tendency (mode, median, mean). Measures of dispersion (range, variance, standard deviation). Statistical graphics & visuals (e.g., box-plot, histograms). Ethics in statistics. Ethics case studies
|
|
Hypothesis Testing
Null/Alternative Hypothesis. Single sample z test. One-tail tests. Two-tail tests
|
|
Test for Normality
Normal distributions. Q-Q/P-P Plots. Shapiro-Wilk Test. Kolmogorov-Smirnov Test
|
|
Dependent and Independent Sample Tests
Test for Equality of Variance. Student’s t-Test
|
|
Introduction to Machine Learning
Data mining methodologies: KDD, CRISP-DM. Data security and ethical implications of machine learning. Introduction to data mining tools such as Python SciKit-Learn, R/RStudio, Weka, RapidMiner. Supervised vs Unsupervised Learning. Regression vs Classification Problems
|
|
Introduction to Regression
Simple Linear Regression. Estimating Regression Coefficients. Evaluating Regression Models (R-Squared, Mean Absolute Error, etc.)
|
|
Introduction to Classification
What is classification?. Evaluating classification models (confusion matrix). Logistic Regression. K-Nearest Neighbours
|
|
Evaluating Predictive Models
Data Splitting and Sampling Methods (Holdout, Cross-fold Validation, Stratification, etc.). Model Tuning and Overfitting
|
| Assessment Breakdown | % |
|---|
| Coursework | 50.00% |
| End of Module Assessment | 50.00% |
AssessmentsFull Time
| Coursework |
| Assessment Type: |
Formative Assessment |
% of total: |
Non-Marked |
| Assessment Date: |
n/a |
Outcome addressed: |
1,2,3,4 |
| Non-Marked: |
Yes |
Assessment Description:
Formative assessment will be provided on the in-class individual or group activities. |
|
| Assessment Type: |
Project |
% of total: |
50 |
| Assessment Date: |
n/a |
Outcome addressed: |
2,4 |
| Non-Marked: |
No |
Assessment Description:
Learners will apply descriptive statistics as well as a number of statistical tests to data sets of their choosing. Learners will also apply regression and classification models to data sets of their choosing, evaluate the performance of these models, and report on their findings. |
|
| End of Module Assessment |
| Assessment Type: |
Terminal Exam |
% of total: |
50 |
| Assessment Date: |
End-of-Semester |
Outcome addressed: |
1,3 |
| Non-Marked: |
No |
Assessment Description:
The end of semester examination will contain questions, with students required to answer. Questions may be essay-style (e.g. AI search strategies), or may require some calculation (e.g. computing test statistics). Marks will be awarded based on clarity, structure, relevant examples, depth of topic knowledge and an understanding of the potential and limits of solutions. |
|
| 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.
|
Reassessment Description
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.
|
NCIRL reserves the right to alter the nature and timings of assessment
Module Workload
| Module Target Workload Hours 0 Hours |
| Workload: Full Time |
| Workload Type |
Workload Description |
Hours |
Frequency |
Average Weekly Learner Workload |
| Lecture |
Classroom & Demonstrations (hours) |
24 |
Every Week |
24.00 |
| Tutorial |
Other hours (Practical/Tutorial) |
12 |
Every Week |
12.00 |
| Independent Learning |
Independent learning (hours) |
89 |
Every Week |
89.00 |
| Total Weekly Contact Hours |
36.00 |
Module Resources
| Recommended Book Resources |
|---|
-
James T. McClave,Terry T. Sincich. Statistics, Global Edition, [ISBN: 1292161558].
-
Gareth James,Daniela Witten,Trevor Hastie,Robert Tibshirani. (2014), An Introduction to Statistical Learning, Springer, p.426, [ISBN: 1461471370].
-
Stuart Russell,Peter Norvig. (2016), Artificial Intelligence: A Modern Approach, Global Edition, Pearson Higher Ed, p.1152, [ISBN: 1292153970].
-
Kartik Hosanagar. (2019), A Human's Guide to Machine Intelligence, Penguin, p.272, [ISBN: 9780525560890].
| | Supplementary Book Resources |
|---|
-
Paul R. Daugherty,H. James Wilson. Human + Machine, [ISBN: 978-1633693869].
-
Rajendra Akerkar. (2018), Artificial Intelligence for Business, Springer, p.81, [ISBN: 978-3319974354].
-
Article/Paper List.
-
Type.
-
Item.
-
Fernandez Elian, Farkhad Ihsan Hariadi, Muhammad Iqbal Arsyad, Implementation of Computer Vision Algorithms for Position Correction of Chip-Mounter Machine,. (2017), International Symposium on Electronics and Smart Devices (ISESD),.
-
Gilles Simonin, Christian Artigues, Emmanuel Hebrard, Pierre Lopez.. (2014), , Scheduling Scientific Experiments for Comet Exploration, Constraints, 20, https://hal, fr/hal-, archives-ouvertes.
| | This module does not have any article/paper resources |
|---|
| This module does not have any other resources |
|---|
|
