Annoucements

November 22nd, 2019: Paper Review Reports

Students will select two from amongst the following papers and write a review for each (two separate reports):

  1. Guillaume Escamocher, Barry O'Sullivan: Solving Logic Grid Puzzles with an Algorithm that Imitates Human Behavior. CoRR abs/1910.06636 (2019)
  2. Hadrien Cambazard, Barry O'Sullivan, Helmut Simonis: A Constraint-Based Dental School Timetabling System. AI Magazine 35(1): 53-63 (2014)
  3. Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan: Semantics derived automatically from language corpora contain human-like biases. Science, Vol. 356, Issue 6334, pp. 183-186, 14 Apr 2017.
  4. Yann LeCun, Yoshua Bengio & Geoffrey Hinton: Deep learning. Nature volume 521, pages 436–444 (2015).
  5. Helmut Simonis, Barry O'Sullivan: Search Strategies for Rectangle Packing. CP 2008: 52-66
  6. Eoin O'Mahony, Emmanuel Hebrard, Alan Holland, Conor Nugent and Barry O'Sullivan Using Case-based Reasoning in an Algorithm Portfolio for Constraint Solving. Proceedings of AICS 2018.
  7. Dónal Doyle, Padraig Cunningham, Derek G. Bridge, Yusof Rahman: Explanation Oriented Retrieval. ECCBR 2004: 157-168
  8. Rakesh Agrawal and Ramakrishnan Srikant: Fast algorithms for mining association rules. Proceedings of the 20th International Conference on Very Large Data Bases, VLDB, pages 487-499, Santiago, Chile, September 1994.
  9. Robert C. Holte: Very Simple Classification Rules Perform Well on Most Commonly Used Datasets. Machine Learning 11: 63-91 (1993)
  10. Jadzia Cendrowska: PRISM: An Algorithm for Inducing Modular Rules. International Journal of Man-Machine Studies 27(4): 349-370 (1987)
The format of each review report is as follows:
  • Each report should be no more than 3 pages using 12pt font with a margin of 2cm.
  • The following headings should be used:
    1. Summary: Summary of the topic and contribution of the paper;
    2. State-of-the-Art: Explain how the paper compares to the state-of-the-art;
    3. Evaluation: Comment on the methodology for evaluating the results or the proofs of theoretical/algorithmic results;
    4. Opportunities: Comment on the opportunities for applying the work presented in this paper and also how the work could be extended.

October 28th, 2019: In-term Examination

The in-term examination for this module will take place during the Friday November 15th.

October 21st, 2019: Web-site is fully up-to-date

All teaching materials and code are available on this web-site and it will be updated weekly.

About this Module

Credit Weighting: 5

Pre-requisite(s): None

Co-requisite(s): None

Teaching Method(s): 24 x 1hr(s) Lectures; 9 x 1hr(s) Practicals.

Module Objective: Review and critically analyse the motivating factors, challenges and technical concepts behind artificial intelligence.

Module Content: Topics that may be covered in this module include: the principles, technologies and applications of model-driven versus data-driven AI; the ethics of AI; fair, accountable and transparent AI.

Learning Outcomes: On successful completion of this module, students should be able to:

  • Critically discuss the challenges and opportunities in realising the future of AI.
  • Describe in detail the main principles, technologies and applications of AI.
  • Evaluate AI technologies from a performance but also an ethical viewpoint.

Assessment: Total Marks 100: Continuous Assessment 100 marks (1x Mid-Semester Examination 40 marks, 1 x End of Semester Examination 40 marks, 2 x Laboratory Reports, 10 marks each).

Compulsory Elements: Continuous Assessment.

Penalties (for late submission of Course/Project Work etc.): Work which is submitted late shall be assigned a mark of zero (or a Fail Judgement in the case of Pass/Fail modules).

Pass Standard and any Special Requirements for Passing Module: 40\%.

Requirements for Supplemental Examination: 1 x 1.5 hr(s) paper(s) (corresponding to Mid-Semester Examination and End of Semester Examination) to be taken in Autumn 2020. The mark for Continuous Assessment is carried forward.