DS212BKK
Intro to Deep Learning
Faculty
Mikhail Romanov
Senior Machine Learning Engineer, Yandex, Expert
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
Neural Networks (sometimes called AI) is the most attractive area of Machine Learning since 2012. Due to significant progress, machines can solve visual problems, perform accurate translations, and play Chess better than humans. Although the area has grown tremendously in recent years, still many of the areas require significant work. Meanwhile, the companies’ need for specialists in this area grows with years.
This area is not only interesting and filled with science, programming and mathematical riddles but also is one of the best-paid areas of contemporary Computer Science. Moreover, it has numerous applications in other areas such as engineering, commerce, astrophysics, biology and many others.
Learning highlights
- In this course, there are two main objectives. The first objective is to learn how to build and train neural networks from a practical point of view. The second objective is to deeply understand the processes that take place in an artificial neural network. In addition, it’s crucial for debugging neural networks and training scripts, designing novel neural networks, and reusing the already pre-trained networks for other tasks (so-called transfer learning).
Course outline
15 classes
Session 1
Neuron and Neural Network.
Session 2
Training a Neural Network
Session 3
Designing interfaces and loss functions for Neural Network
Session 4
Optimisers for Neural Networks
Session 5
Maximum Likelihood and Regularization
Session 6
Gradient Vanishing and Batch Normalization
Session 7
Convolutional Neural Networks
Session 8
Convolutional Neural Networks Architectures
Session 9
Efficient Architectures of Convolutional Neural Networks
Session 10
Segmentation
Session 11
Detection
Session 12
Optical Flow and Depth Estimation
Session 13
Final Project
Session 14
Final Project
Session 15
Final Project
Prerequisites
Calculus
Linear Algebra
Statistics and Probability
Python programming
Methodology
Grading
Mikhail Romanov, PhD, is a deep learning researcher and engineer. His experience includes deep learning for production, scientific computing and research, accompanied by teaching mathematics and machine learning in general.
His academic experience includes teaching courses at MIPT, HSE, Harbour Space Universities and online platforms. As a researcher, he has conducted research at the Technical University of Denmark, Mail.ru, Samsung Research, Quantori, and Yandex. In his research, his main areas of interest are depth estimation, optical flow, optimisation of neural networks, multi-task learning, self-supervised learning, LLMs and diffusion models. He has published papers on tomography, deep learning, scientific computing, computer vision, generative AI, and diffusion models.
See full profileApply for this course
Intro to Deep Learning
by Mikhail Romanov
Total hours
45 Hours
Dates
May 08 - May 26, 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.