Artificial Intelligence & Data Science

Taught: 2024

EPF, Paris-Cachan, France

EPF, Paris-Cachan, France

Description

This course provides an introduction to the fundamental concepts and techniques in Artificial Intelligence (AI) and Data Science, equipping students with the knowledge and skills to solve real-world problems. The course covers the foundational principles of AI, including search strategies, knowledge representation, and deep machine learning, as well as key topics in Data Science, such as data preprocessing, exploratory data analysis, and basic statistical methods.

Students will gain hands-on experience with AI and Data Science tools and frameworks to implement models, analyze datasets, and extract meaningful insights. By the end of the course, students will have a solid understanding of how AI and Data Science intersect and how they can be applied in various domains, including healthcare, finance, and social sciences.

Key Learning Outcomes:

  • Understand the core principles and techniques of Artificial Intelligence and Data Science.
  • Develop proficiency in data preprocessing, visualization, and statistical analysis.
  • Apply machine learning techniques such as supervised and unsupervised learning.
  • Explore problem-solving methods in AI, including search algorithms and optimization.
  • Gain practical experience with Python and libraries like NumPy, pandas, scikit-learn, and matplotlib.
  • Design and evaluate AI and Data Science models for real-world datasets.

Course Topics:

  • Introduction to AI and Data Science

Definition and scope

Applications in the real world

Data Science Fundamentals

  • Data preprocessing and cleaning

Exploratory Data Analysis (EDA) and visualization techniques

Basic probability and statistics

  • Introduction to Machine Learning

Supervised learning (classification and regression)

Unsupervised learning (clustering, dimensionality reduction)

Model evaluation (accuracy, precision, recall, etc.)

Deep Learning and Large Language Models

  • AI Foundations

Search strategies (e.g., BFS, DFS, A*)

Knowledge representation and reasoning

Introduction to reinforcement learning

  • Tools and Libraries

Python for AI and Data Science

Libraries: pandas, NumPy, matplotlib, scikit-learn

  • Case Studies and Applications

AI and Data Science in healthcare, business, and social sciences

  • Ethical Considerations

Bias in data and algorithms

Ethical use of AI and Data Science

  • Course Format

Lectures: Introduction to theoretical concepts.

Practical Labs: Hands-on coding exercises and projects.

Assignments: Implementing AI and Data Science techniques.

Final Project: Analyze a dataset and present findings using learned techniques.

Prerequisites:

Basic programming knowledge (preferably Python).

Familiarity with linear algebra, calculus, and probability.