Artificial Intelligence II (2235.YR.000565.1)
General information
Type: |
OBL |
Curs: |
1 |
Period: |
S semester |
ECTS Credits: |
3 ECTS |
Teaching Staff:
| Group |
Teacher |
Department |
Language |
| Year 1 |
Jordi Nin Guerrero |
Operaciones, Innovación y Data Sciences |
ENG |
Prerequisites
Cloud Computing
Artificial Intelligence I
Previous Knowledge
- Basic programming skills (Python)
- Basic knowledge on Machine Learning
Workload distribution
- 27 hours of face-to-face lessons (Lessons)
- 15 hours of group work (Assignments)
- 6 hours of practical lessons (Hackathons)
- 24 hours of independent study (Exam preparation + understanding theory concepts)
COURSE CONTRIBUTION TO PROGRAM
- Deep understanding of supervised Machine Learning methods
- Basic knowledge of Deep Learning as a supervised and unsupervised learning method
- Business evaluation of the different ML techniques
Course Learning Objectives
The main goal of the course is to get a better understanding of how to create Machine Learning models and apply them to specific business problems. The student will practice applying ML with Python to create valid evaluation metrics in particular business contexts.
CONTENT
1. Introduction to sklearn This introductory session provides the basic concepts of how to use the Python sklearn library. |
2. From train/test split to pipelines with cross validation A deep dive into the internals of the sklearn library |
3. Model evaluation and grid search This session will assume some knowledge about model evaluation and it will introduce how to fine tune model hyperparamenters |
4. Hackathon 1 This session is devoted to practice with a dataset |
5. Understanding decision trees This session will assume some knowledge about decision trees. Based on this knowledge, this session will introduce concepts such as pruning, balancing and hyperparameters tuning. |
6. Deep learning basics We will introduce the basic concepts to use neural networks for supervised machine learning, such as softmax layers or dropout. |
7. Deep learning embeddings This session will introduce autoencoders: a technique used for data compression. |
8. Hackathon 2 This session is devoted to practice with a dataset |
Methodology
The course combines theoretical lectures with practical sessions. During the sessions, students will solve real problems with their computers using Python and state-of-the-art ML libraries.
ASSESSMENT
ASSESSMENT BREAKDOWN
| Description |
% |
| Assignment 1: Sklearn |
10 |
| Assignment 2: Grid search |
10 |
| Assignment 3: Deep learning |
10 |
| Hackathon 1 |
15 |
| Hackathon 2 |
15 |
| Exam |
30 |
| Class attendance and participation |
10 |
Assessment criteria
The evaluation of the course is composed of:
- 10 % Class attendance and participation
- 30% Jupyter notebooks with assignments
- 30 % hackathons
- 30 % Final exam
Bibliography
1. Pattern Recognition and Machine Learning. Christopher M. Bishop
2. An Introduction to Statistical Learning: with Applications in R. Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani.
3. Deep Learning. Aaron C. Courville, Ian Goodfellow, and Yoshua Bengio
Timetable and sections
| Group |
Teacher |
Department |
| Year 1 |
Jordi Nin Guerrero |
Operaciones, Innovación y Data Sciences |
Timetable Year 1
From 2024/2/8 to 2024/2/15:
Each Thursday from 15:30 to 17:00. (Except: 2024/2/8)
Each Thursday from 17:15 to 18:45. (Except: 2024/2/8)
Each Thursday from 10:30 to 12:00. (Except: 2024/2/15)
Each Thursday from 8:45 to 10:15. (Except: 2024/2/15)
From 2024/2/29 to 2024/4/11:
Each Thursday from 15:30 to 17:00. (Except: 2024/3/28)
Each Thursday from 17:15 to 18:45. (Except: 2024/3/28)
Thursday 2024/4/18 from 9:00 to 10:30.
