DS405
Master's Machine Learning
Faculty
Radoslav Neychev
Harbour.Space AI Track Director, Girafe-ai founder
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 students to the contemporary state of Machine Learning and Artificial Intelligence. It combines theoretical foundations of Machine Learning algorithms with comprehensive practical assignments. The course covers materials from classical algorithms to Deep Learning approaches and recent achievements in the field of Artificial Intelligence. This course is accompanied by Deep Learning in Applications course (Module 12), which brings the most recent achievements in the field and their applications.
Programming assignments will be implemented in Python 3. PyTorch framework will be used for Deep Learning practice.
Special acknowledgements to Nikolay Karpachev and Ivan Provilkov for contributions into the course materials and structure.
Learning highlights
- Learn the main theoretical foundations of Machine Learning and Deep Learning
- Get familiar with various approaches to supervised and unsupervised problems
- Gain essential experience in data preprocessing, model development, fitting and validation
- Develop skills required in product development and applied research
Course outline
15 classes
Class 1
Introduction, overview and metric algorithms
Machine Learning general overview. Supervised and Unsupervised learning problem statements. Metrics. kNN. Maximum Likelihood estimation. Naive Bayesian Classification.
Class 2
Linear regression
Gauss-Markov theorem. L1 and L2 regularization. Matrix differentiation.
Class 3
Linear classification
Margin. Logistic regression. Multiclass classification strategies.
Class 4
Linear classification & dimensionality reduction
SVM, kernel trick. Linear algebra recap: eigendecomposition of a matrix, SVD. PCA
Class 5
Model construction and validation
Bias-Variance decomposition. Train-Validation-Test framework. Hyperparameters tuning.
Class 6
Decision trees & ensembling methods
Construction procedure. Bootstrap recap. Bagging. Random Subspace Method. Random Forest. Out of Bag error.
Class 7
Ensembling methods
Stacking. Blending. Gradient boosting.
Class 8
Midterm
Feature engineering and missing values. Feature importance estimation.
Class 9
Intro to Deep Learning
Motivation & timeline. Intuition, forward pass. NN specific terminologyBackpropagation mechanism. Activation functions.
Class 10
Optimization & regularization in Deep Learning
SGD refinements. Weights initialization. NN overfitting and regularization methods.
Class 11
Deep learning for structured data
Recurrent neural networks, sequence modeling. Vanishing gradient problem.
Class 12
Deep Learning for structured data
Convolutional layers. Upconvolutions. Pooling. Most influential architectures overview.
Class 13
Embeddings
Text vectorization. Autoencoders. Embeddings.
Class 14
Unsupervised learning
Manifold learning. Dimensionality reduction. Clustering algorithms.
Class 15
Final test General recap. Extra themes.
Prerequisites
Basic knowledge of Python. You do not need to be a developer, but you need to be able to write without googling every line. A good example of what you should be able to do: https://gitlab.erc.monash.edu.au/andrease/Python4Maths/tree/master
Basic knowledge of linear algebra / probability theory / statistics. You can use the chapters of the Deep Learning book as a cool minimal tutorial: * Linear algebra: http://www.deeplearningbook.org/contents/linear_algebra.html * Probability and Information Theory: http://www.deeplearningbook.org/contents/prob.html * Numerical Computation: http://www.deeplearningbook.org/contents/numerical.html
Methodology
The course will be organised in three-hour sessions and self-study practical assignments. Sessions will contain both theoretical and practical parts with different ratios depending on the materials.
Grading
Radoslav Neychev is a data scientist with focus on Deep Learning and Reinforcement Learning techniques. He has worked on variety of research (CERN LHCb, MIPT Machine Intelligence Lab, CC RAS) and industrial projects (Yandex, RaiffeisenBank) in different domains vary from particle identification problem to fraudulent transactions detection.
Radoslav graduated from Moscow Institute of Physics and Technology, majoring in Applied Mathematics and Machine Learning. Radoslav is reading lectures and organising practical classes at Russian top-tier universities, tech companies and summer schools.
See full profileApply for this course
Master's Machine Learning
by Radoslav Neychev
Total hours
45 Hours
Dates
Jan 09 - Jan 27, 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.