Course Details

Course Code(s):
CE6002
Available:
Part-Time
Intake:
Spring
Course Start Date:
Spring
Duration:
7 Weeks
Award:
University Certificate of Study
Qualification:
NFQ Level 9 Minor Award
Faculty: Science and Engineering
Course Type: Professional/Flexible, Online
Fees: For Information on Fees, see section below.

Contact(s):

Name: SEFLC
Address: Science & Engineering Flexible Learning Centre Email: seflc@ul.ie
Express Interest

Register your interest here for more information or to be notified when applications are open.

Brief Description

Course commencement is subject to minimum numbers.

The module covers what is meant by learning from data and using patterns in data to learn from it as long as we have enough data from which to learn. The module will look at how to learn from data, using basic techniques and trialling them on data sets, and will look at algorithms to make machine learning better.

FUNDING

This course qualifies for 80% funding under the HCI Micro-Credential Course Learner Subsidy. Check fees section for details and eligibility. Please Note: Applicants may only apply for and receive, one subsidised course per semester.

APPLICATION INFORMATION

Please ensure you enter the Module Code above when applying for this Micro Cred.  Applications without this cannot be processed.You may apply for more than one Micro Cred under the same application.

PATHWAY

This micro-credential represents a single module within a larger further award (e.g., Certificate, Diploma, Masters). By taking this micro-credential you may be eligible to apply for a credit exemption should you progress to study for a further award.

The programme(s) associated with this MicroCred are: 

 

Artificial Intelligence is the broader concept of machines being able to carry out tasks in a way that we would consider "smart". Machine Learning is a current application of AI based around the idea that we should be able to give machines access to data and let them learn for themselves.

The module will cover the following areas

  • The learning problem: feasibility of learning, error, and noise
  • Theory of generalization: Effective number of hypotheses, VC bound, sample and model complexity, approximation-generalization trade-off, bias and variance
  • Linear classification and regression, logistic regression, gradient descent, and feature space transformations
  • Overfitting and regularisation
  • Validation and model selection, data snooping
  • Neural Networks: Perceptron’s, Multi-Layer Perceptron’s and the Back-Propagation training algorithm.
  • Optimal Margin Classifiers and Support Vector Machines.
  • Parametric vs. Non-Parametric classifiers.

On successful completion of this module students will be able to:

  • Demonstrate an understanding of the theory of generalisation and its practical implications for machine learning algorithms, the concept of model complexity, in particular the VC bound and its practical interpretation.
  • Be able to apply regularization in order to prevent overfitting.
  • Demonstrate an understanding of and be able to apply non-linear transformations to feature spaces.
  • Recognise and manage under- and overfitting.
  • Apply methods for selecting one final machine learning model from among a collection of candidate machine learning models for a training dataset.
  • Apply methods for model validation, the process where a trained model is evaluated with a testing data set.
  • Apply a number of linear and non-linear and parametric and non-parametric machine learner training models e.g., linear regression, logistic regression, feed forward neural networks and Support Vector Machines.
  • Differentiate and critique various techniques that could be used and be able to justify an appropriate classification technique for a given a classification problem.
  • Demonstrate an awareness of and be able to implement appropriate protocols and practices to manage bias and data snooping when training a machine learner, for a given data set.
  • Demonstrate an awareness of the impact of the availability of data, for a given data set used to train the machine learner, when assessing the machine learner's performance.

Applicants must have a minimum Level 8 honours degree, at minimum second class  honours (NFQ or other internationally recognised equivalent), in a relevant engineering, computing, mathematics, science or technology discipline, or a Level 8 Honours degree in other disciplines, which has a significant mathematics and computing element.

Python will be used throughout this module. Students should be comfortable with general programming in Python. Exposure to Python machine learning toolboxes is not a must, but is advantageous.

Entry requirements are established to ensure the learner can engage with the course material and assessments, at a level suitable to their needs, and the academic requirements of the module. By applying to this micro-credential, you are confirming that you have reviewed and understand any such requirements, and that you meet the eligibility criteria for admission.

Successful completion of this module does not automatically qualify you for entry into a further award. All programme applicants must meet the entry requirements listed if applying for a further award.

The fees for this programme are €1,000

HCI Micro-Credential Course Learner Subsidy - Candidates who satisfy the eligibility criteria can qualify for 80% funding subject to the availability of places. To clarify eligibility please go to Eligibility Criteria

Please click here for information on funding and scholarships.