Learning Notes
1st Semester of MSc. in AI and ML
University of Birmingham, Sept 2023- Sept 2024
Machine Learning, Deep Learning and Maths for AI/ML
- Oscar Guarnizo University of Birmingham
Description
This page contains all the notes taken during my first semester of MSc in Artificial Intelligence and Machine Learning at the University of Birmingham, United Kingdom
Skills:
Python, PyTorch, Machine Learning, Deep Learning, Fundamentals of Mathematics for AI/ML.
Module 1: Machine Learning
Machine learning studies how computers can autonomously learn from available data, without being
explicitly programmed. The module will provide a solid foundation to machine learning by giving
an overview of the core concepts, theories, methods, and algorithms for learning from data.
The emphasis will be on the underlying theoretical foundations, illustrated through a set of
methods used in practice. This will provide the student with a good understanding of how, why
and when various machine learning methods work.
Official Link: Machine Learning (Extended) - 2023
- Week 07: Is Learning Feasible?: Hoeffding Inequality
- Week 07: Is Learning Feasible?: Generalization Bound
- Week 08: Dichotomy
Module 2: Neural Computation (Deep Learning)
This course focuses on artificial neural networks and their use in machine learning.
It covers the fundamental underlying theory, as well as methodologies for constructing
modern deep neural networks, which nowadays have practical applications in a variety of
industrial and research domains. The course also provides practical experience of designing
and implementing a neural network for a real-world application.
Official Link: Neural Computation (Extended) - 2023
Module 3: Mathematical Foundations of Artificial Intelligence and Machine Learning
Mathematics is an integral part of modern approaches to machine intelligence. From the role
of linear algebra and calculus in neural network learning models for image classification
and speech recognition, to Bayesian approaches to automated disease diagnosis, , to control
and reasoning in robotocs, mathematical methods are essential to understand, apply, and
advance state-of-the art machine intelligence techniques. This module will introduce a range
of mathematical tools and demonstrate how they can be used to understand and solve core machine
intelligence tasks, and to analyse the limits of their performance.
Official Link: Mathematical Foundations of Artificial Intelligence and Machine Learning - 2023
Related links
TBD