CS351 – Artificial Intelligence & Deep Learning
Bachelor of Science in Computing and Business Technologies
Core Course
CS351 – Artificial Intelligence & Deep Learning
Course Unit Code: CS351
Type Of Unit: Core
Level of Course Unit: Second cycle
Year of Study: Third
Semester: B’ Semester (Spring)
Number of ECTS Credits: 7.5
Class Contact Hours: 36
Mode of Delivery
Face to Face
Prerequisites
Course Objectives
The objective of this course is to teach the students about the fundamentals of deep learning. The students will revise some basic machine learning algorithms taught in other courses, and understand their relationship to current deep learning approaches. The students will learn about different types of neural networks such as feedforward, recurrent and convolutional neural networks and they have the opportunity to apply these to real world problems. The course will also teach the students how to implement deep neural networks in Python using Keras.
Learning Outcomes
- Revise basic machine learning algorithms relating to neural networks: support vector machines, logistic regression, linear regression, perceptron.
- Understand the different types of neural networks: feedforward, recurrent, convolutional. Understand how these types can be used for different types of problems: supervised, unsupervised, reinforcement, multi-task learning.
- Understand how deep neural networks are designed and optimised: gradient descent, neural architecture search, regularization, dropout.
- Understand how neural networks can be applied in natural language data.
- Know how to use neural networks for computer vision problems.
- Learn how to implement and use deep neural network to solve real world problems in supervised learning using structured data.
Course Content
Course Features
Planned learning activities and teaching methods
Lectures; in-class discussion and debates; in-class exercises; problem sets; team work; video case studies, team presentations, interactive online learning via Moodle (quizzes, assignments, forums)
Assessment methods and criteria
10% class participation
60% exam
30% group project
Language of Instruction
English
Readings
Textbooks:
1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach, Deep Learning (Adaptive Computation and Machine Learning Series), MIT Press, 2017
Online sources:
https://keras.io/getting_started/intro_to_keras_for_engineers/
https://www.deeplearningbook.org/
English (UK) 
Ελληνικά