Module Directory

Artificial Intelligence is the science of making computers and machines to produce results and behave in a way that resembles human intelligence. This multidisciplinary activity involves the knowledge of different disciplines such as Computer Science, Mathematics and Statistics, but also includes important elements from Philosophy, Logic and even Psychology.

This module will provide you with a broad overview of Artificial Intelligence, as well as more detailed understanding of core concepts and models. We will follow an approach both theoretical and practical, describing the theory and fundamentals of machine learning models, as well as showing how to implement them and their applications.

The aim of this module is:

• To provide a general introduction to Artificial Intelligence and Machine Learning for students without a strong background in Mathematics or Computer Science.

By the end of this module, students will be expected to have:

1. A systematic understanding of Artificial Intelligence, its scope and its limitations.


2. A comprehensive understanding of techniques applicable to formulate abstract problems in a way that AI techniques such as Searching Algorithms and Genetic Algorithms can solve them efficiently.


3. A conceptual understanding that enables the student to use supervised and unsupervised machine algorithms, such as Decision Trees and K-Means Clustering, for analysing datasets.


4. A systematic understanding of knowledge, and a critical awareness of the functioning of Artificial Neural Networks and Convolutional Neural Networks, as well as use them in the context of computational linguistics.


5. The ability to apply a range of AI algorithms for studying real world cases. This includes:
   
   
   
   1. Determining which types of models are best suited considering the characteristics of the dataset studied.
   
   
   2. Implementing in the code in Python/Jupyter.
   
   
   3. Using appropriate testing procedures and benchmarks.
   
   
   4. Correctly interpreting the outputs and limitations.
   
   
   5. The ability to communicate effectively AI and Machine Learning concepts and ideas.
   
   
   
   

Nowadays, AI is well embedded in our society from self-driving cars to spam filters, and from finance trading to video games. All predictions state that more and more our society will depend on this technology with the consequent transformation of our society and our economy. The impact of AI affects any discipline and therefore it is important for everyone to understand its principles, applications and limitations. This course is suitable for any student regardless of their background.

We will start with the history of the AI and its general principles as well as current examples and challenges that AI is nowadays facing. Then we will review specific models and algorithms in order to provide a wide range of tools and the logic behind them. Finally, we will also put a strong accent on the actual application of those machine learning models by going through practicals and seminars that will teach how to use them in a Python environment.

Syllabus

• Artificial Intelligence
  
  
  
  • History, definitions and Principles of AI.
  
  
  • Ethics of AI. Biases and its consequences.
  
  
  • Applications of AI.
  
  
  
  


• Problem Solving
  
  
  
  • Searching Algorithms.
  
  
  • Genetic Algorithms.
  
  
  
  


• Machine Learning
  
  
  
  • Supervised Learning, including LASSO and Random Forests.
  
  
  • Unsupervised Learning, including k-means Clustering.
  
  
  • Reinforced Learning.
  
  
  
  


• Deep Learning
  
  
  
  • Artificial Neural Networks.
  
  
  • Training Artificial Neural Networks and backpropagation.
  
  
  • Convolutional Neural Networks and Image recognition.
  
  
  
  

Teaching in the School will be delivered using a range of face to face lectures, classes and lab sessions as appropriate for each module. Modules may also include online only sessions where it is advantageous, for example for pedagogical reasons, to do so.