Math203BKK
Math Basics for ML
Faculty
Valery Marchenkov
Data Scientist at S7 Airlines. Visiting Lecturer at MISIS.
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
This course aims to introduce or refresh the main mathematical concepts that are commonly used in the Machine Learning field. It makes the connection between mathematical abstractions and real-world technical applications and describes the math fundamentals, techniques and assumptions that Machine Learning algorithms and models rely on.
Learning highlights
- Learn the main theoretical foundations of Machine and Deep Learning.
- Understand the main mechanics that are used in all Machine and Deep Learning algorithms and models.
- Feel comfortable dealing with the application of Machine Learning in practice.
- Be prepared to fully immerse into advanced Artificial Intelligence topics.
- At the end of this course, students will obtain the prerequisite mathematical knowledge to understand the basic mechanics that are used to create modern AI-applications.
Course outline
15 classes
Session 1
How does the computer read? How to measure the distance between two sentences?
Intro. Course motivation. Vector Algebra.
Session 2
Neural Networks are just matrix multiplications.
Matrix Algebra.
Session 3
Is there something special in matrices?
Eigenvectors and Eigenvalues. Matrix decompositions.
Session 4
How to see in 10D space? How to compress the data without losing information?
Principal Component Analysis (PCA). Singular Value Decomposition (SVD).
Session 5
How does the computer see? Real world applications of Linear Algebra.
Computer Vision.
Linear Algebra exam.
Session 6
How to measure rate of change?
Single Variable Calculus. Limits. Differentiation. Integration
Session 7
Matrix in - scalar out?
Multivariable Calculus. Chain rule and total derivative. Gradient. Jacobian matrix. Hessian.
Session 8
How to find a low in all of these hills?
Optimization. (Stochastic) Gradient descent, convergence improving techniques
Session 9
Matrix in - matrix out? Go deeper.
Matrix Calculus. Matrix - Vector differentiation.
Session 10
How do Neural Networks actually learn?
Backpropagation Algorithm.
Calculus exam.
Session 11
What is the probability of meeting a dinosaur in the street?
Basic combinatorics. Basic probability. Bayes’s Theorem.
Session 12
It’s not random, not a variable. Why does it seem so normal?
Discrete and continuous random variables. Probability distributions. Mean, variance, covariance and correlation.
Session 13
What do we learn from data?
Maximum Likelihood Estimation and Loss Functions.
Session 14
How many questions do we need to find the answer? How different are the distributions?
Introduction to Information Theory. Shannon Entropy. KL-divergence.
Session 15
Probability and Statistics exam. Review.
Bonus: What is the next move for an autonomous car?
Markov Chains and Decision Processes.
Prerequisites
There are no specific theoretical high-level prerequisites for this course, all concepts are introduced from scratch and will be clearly explained. For a more comfortable participation, it would good to have the prior knowledge of:
Mathematical notations
Basic calculus (functions, graphs)
Basic probability (classical definition)
Python basic syntax
Methodology
The course is made up of 15 three-hour sessions, half of which are made up of lecture materials and the other half are practical workshops.
It covers three modules with an exam at the end of each of them:
Linear Algebra
Calculus
Probability and Statistics
Daily homework assignments are designed for students to do them at approximately the same time as in-class sessions of completion and consist of theoretical and practical assignments.
Grading
Valery is a Data Scientist at S7 Airlines. He works on aircraft engines and the fleet's recorded data in terms of fuel efficiency and maintenance planning algorithms development, travelers purchase, flight data and recommender systems. He also works as a Practice Instructor for Machine Learning courses at the Moscow Institute of Physics and Technology (MIPT) and as a Deep Learning lecturer at the NUST MISIS.
Before that he worked as a Structural Analysis Engineer at Boeing, where he worked on airframe design, static strength and fatigue analysis of metal parts for prospective aircrafts.
See full profileApply for this course
Math Basics for ML
by Valery Marchenkov
Total hours
45 Hours
Dates
Oct 02 - Oct 20, 2023
Fee for single course
€1500
Fee for degree students
€750
How to secure your spot
Complete the form below to kickstart your application
Schedule your Harbour.Space interview
If successful, get ready to join us on campus
FAQ
Will I receive a certificate after completion?
Yes. Upon completion of the course, you will receive a certificate signed by the director of the program your course belonged to.
Do I need a visa?
This depends on your case. Please check with the Spanish or Thai consulate in your country of residence about visa requirements. We will do our part to provide you with the necessary documents, such as the Certificate of Enrollment.
Can I get a discount?
Yes. The easiest way to enroll in a course at a discounted price is to register for multiple courses. Registering for multiple courses will reduce the cost per individual course. Please ask the Admissions Office for more information about the other kinds of discounts we offer and what you can do to receive one.