Tech Heart
Harbour.Space University

All rights reserved. 2018

Chief Research Officer, Neuromation
Head of AI Lab, PDMI RAS
Head of AI, Synthesis AI
Head of Multimodal Data Analysis Lab, Samsung AI Center Moscow
Assistant Professor, St. Petersburg State University
Assistant Professor, Higher School of Economics St. Petersburg


Deep learning, i.e., training multilayered neural architectures, was one of the oldest tools in machine learning but has revolutionized the industry over the last decade. In this course, we begin with the fundamentals of deep learning and then proceed to modern architectures related to basic computer vision problems: image classification, object detection, segmentation, and others.

Modern computer vision is almost entirely based on deep convolutional neural networks, so this is a natural fit that lets us explore interesting architectures, while at the same time staying focused and not going into too wide a survey of the entire field of deep learning. Computer vision is also a key element in robotics: vision systems are necessary for navigation, localization and mapping, and scene understanding, which are all key problems for creating industrial and home robots.

The course is supported by Neuromation and features practical assignments done over the Neuromation platform.


As a result of the course, the students will:
- Learn to apply Deep Learning techniques in practice

- Understand the theory behind the Deep Learning from basics to state-of-the-art approaches

- Learn how to train various deep neural architectures

- Understand a wide variety of neural architectures suited for real-life computer vision problems

- Gain essential experience with main Deep Learning frameworks

DATE: 18 May - 5 Jun, 2020


LECTURES: 3 Hours per day


LOCATION: Barcelona, Harbour.Space Campus



Session 1

Neural networks: history and basic idea. Relationship between biology and mathematics. The perceptron: basic construction, training, activation functions. 
Practice: intro to Deep Learning frameworks

Neural network basics.

Session 2

Feedforward neural networks

Feedforward neural networks. Gradient descent basics. Computation graph and computing gradients on the computation graph (backpropagation).
Practice: a feedforward neural network on classic datasets

Session 3

Gradient descent: motivation, problems. Modifications, ideas: momentum, Nesterov’s momentum, Adagrad, RMSProp, adam. Second order methods
Practice: comparing gradient descent variations

Optimization in neural networks

Session 5

Weight initialisation and batchnorm

Weight initialisation: supervised pre training idea, why straightforward random init fails, Xavier initialisation. Covariate shift and batch normalisation.
Practice: putting everything together

Session 4

Regularization: L1, L2, early stopping. Dropout. Data augmentation.
Practice: Applying different regularisation approaches

Regularisation in neural networks

Session 6

Convolutional architectures: idea and structure. Examples. Deconvolution and visualisation in CNNs.
Practice: CNNs for MNIST

Convolutional neural networks I

Sergey Nikolenko is a computer scientist with vast experience in machine learning and data analysis, algorithms design and analysis, theoretical computer science, and algebra. He graduated from St. Petersburg State University in 2005, majoring in algebra (Chevalley groups), and earned his Ph.D at the Steklov Mathematical Institute at St. Petersburg in 2009 in theoretical computer science (circuit complexity and theoretical cryptography). Since then, Sergey  has been interested in machine learning and probabilistic modeling, producing theoretical results and working on practical projects for the industry.

Sergey Nikolenko is currently serving as the Chief Research Officer at Neuromation, leading the Artificial Intelligence Lab at the Steklov Mathematical Institute at St. Petersburg, and teaching at the St. Petersburg State University and Higher School of Economics. Dr. Nikolenko has published more than 170 research papers on machine learning (ICML, CVPR, ACL, SIGIR, WSDM...), analysis of algorithms (SIGCOMM, INFOCOM, ICNP…), and other fields, several books, including a bestselling "Deep Learning" book (in Russian), lecture courses in ML, DL, other fields of computer science (St. Petersburg State University, NRU Higher School of Economics...) and much more. He has extensive experience in managing research and industrial AI/ML projects.

Research/Academic Interests:
Machine learning: probabilistic graphical models, recommender systems, topic modeling
Algorithms for networking: competitive analysis, FIB optimization
Bioinformatics: processing mass-spectrometry data, genome assembly
Proof theory, automated reasoning, computational complexity, circuit complexity
Algebra (Chevalley groups), algebraic geometry (motives)


-Machine Learning

-Deep Learning

-Reinforcement Learning



-System & Virtualization

-Public Speaking




DATE: 18 May – 5 Jun, 2020

DURATION:  3 Weeks

LECTURES: 3 Hours per day


LOCATION: Barcelona, Harbour.Space Campus



Researcher at Steklov Math Institute
Researcher at Synthesis AI

Alexey Davydov is a computer scientist experienced with algorithm design and machine learning. He received his bachelor degree in physics at Moscow Institute of Physics and Technology and his master degree at St. Petersburg Academic University. His main research interests are developing competitive scheduling algorithms and usage of synthetic data in deep learning.

He has been teaching at St. Petersburg Academic University, Computer Science Center and St. Petersburg State University since 2012. Alex Davydov currently is a researcher at Steklov Math Institute where he works on theoretical research and at Synthesis AI where he can apply it to practice.


Harbour.Space is a university created by entrepreneurs for entrepreneurs. We focus on meeting the demands of the future, while traditional education providers are too often stuck in the past.

We’re one of the only European institutions completely dedicated to technology, design and entrepreneurship, and our interdisciplinary courses are taught by some of today’s leading professionals. Our aim is not only to equip students with the knowledge to take on the real world, but to nurture, create and shape tomorrow’s tech superstars.

 Learn more about Harbour.Space.



-Machine Learning

-Computer Vision

-Time Series Analysis