DS407BKK
Neural Networks and Computer Vision
Faculty Profiles
Sergey Nikolenko
Chief Research Officer, Neuromation Head of AI Lab, PDMI RAS
Aleksei Shabanov
Applied Data Scientist / Machine Learning Engineer
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
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 of 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.
Learning highlights
- Learn to apply Deep Learning techniques in practice
- Understand the theory behind 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
Course outline
15 classes
Neural network basics.
Neural networks: history and basic idea. The perceptron: basic construction, training, activation functions.
Practice: Tensors in PyTorch, computational graph, functions, auto-grad.
Feedforward neural networks
Feedforward neural networks. Gradient descent basics. Computation graph and computing gradients on the computation graph (backpropagation).
Practice: PyTorch Modules, their parameters, eval/train modes, built-in optimizers.
Optimization in neural networks
Gradient descent: motivation, problems. Modifications, ideas: momentum, Nesterov’s momentum, Adagrad, RMSProp, Adam. Second-order methods.
Practice: PyTorch: losses, datasets, first training loop, collate fn.
Regularization in neural networks
Regularization: L1, L2, early stopping. Dropout. Data augmentation.
Practice: Implementing different optimizers.
Weight initialization and batch norm
Weight initialization: supervised pre-training idea, why straightforward random init fails, Xavier initialization. Covariate shift and batch normalization.
Practice: Components of training neural networks: lr and its’ scheduling, optimizers, early stopping, batch size, troubleshooting.
Convolutional neural networks
Convolutional architectures: idea and structure. Modern convolutional architectures: AlexNet, VGG, network-in-network, GoogLeNet, ResNet, EfficientNet.
Practice: Finetuning image classifier (ResNet), augmentations, working with GPU.
Object detection and segmentation
Object detection: the R-CNN family, the YOLO family. Image segmentation: FCNs, U-Net, Mask R-CNN.
Practice: Working with pre-trained object detectors, Precision-Recall curves, MAP.
Generative models in deep learning
Generative models and neural networks. Types of generative models. Autoregressive deep learning models, WaveNet.
Practice: Training semantic segmentation model.
Mid-term test
Mid-term test
Generative adversarial networks
Generative adversarial networks: idea, DCGAN, AAE, conditional GANs. Wasserstein GANs. Various loss functions in GANs. GANs for image generation.
Practice: DCGAN on CIFAR10: evaluation and analysis, inception score, dataset memorization problem.
Variational autoencoders
Variational autoencoders: ideas, construction, derivation.
Practice: DCGAN: training on Fashion MNIST.
Transformers
Another machine learning revolution: the Transformer architecture. Idea, formal description, applications. BERT and GPT families.
Practice: Transformers in practice: attention, multi-head attention, ViT. Self-supervised learning.
Transformers for images and video
Vision Transformers. ViT. Transformers for video processing: problems and solutions.
Practice: Image retrieval: task setup, benchmarks, metrics, representation power of ViT vs ResNet.
Case study: video retrieval
Multimodal Transformers: CLIP and BLIP. Transformers for video retrieval.
Practice: Training image retrieval models. Angular losses, contrastive losses. Sampling and mining for contrastive losses.
Final exam
Final exam
Prerequisites
Master’s Machine Learning
Python programming experience
At least basic knowledge of Linear Algebra, Probability Theory and Optimisation
Methodology
The course will be organized into three-hour sessions and self-study practical assignments. Sessions will contain both theoretical and practical parts with different ratios depending on the materials.
Grading
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.
See full profileAleksei Shabanov is an Applied Data Scientist / Machine Learning Engineer with 7+ years of industrial experience. His main interest is Deep Computer Vision. Alexei has hands-on experience in Image Search, Person tracking and re-identification, Object Detection, Segmentation, and many others. He is also the main author of an open-source project named Open Metric Learning and a former active contributor to the Catalyst library. As a teacher, Alexei usually focuses on practical Deep Learning, linking theory to industry applications.
See full profileApply for this course
Neural Networks and Computer Vision
by Sergey Nikolenko, Aleksei Shabanov
Total hours
45 Hours
Dates
Jan 08 - Jan 26, 2024
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.