• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
Master 2024/2025

Introduction to Deep Learning in NLP

Area of studies: Applied Mathematics and Informatics
Delivered by: School of Linguistics
When: 2 year, 1, 2 module
Mode of studies: offline
Open to: students of all HSE University campuses
Instructors: Ksenia Klokova
Master’s programme: Applied Artificial Intelligence Models
Language: English
ECTS credits: 6

Course Syllabus

Abstract

Introduction to Deep Learning https://www.coursera.org/learn/intro-to-deep-learning?specialization=aml The course starts with a recap of linear models and discussion of stochastic optimization methods that are crucial for training deep neural networks. Learners will study all popular building blocks of neural networks including fully connected layers, convolutional and recurrent layers. Learners will use these building blocks to define complex modern architectures in TensorFlow and Keras frameworks. In the course project learner will implement deep neural network for the task of image captioning which solves the problem of giving a text description for an input image. The prerequisites for this course are: 1) Basic knowledge of Python. 2) Basic linear algebra and probability. Please note that this is an advanced course and we assume basic knowledge of machine learning. You should understand: 1) Linear regression: mean squared error, analytical solution. 2) Logistic regression: model, cross-entropy loss, class probability estimation. 3) Gradient descent for linear models. Derivatives of MSE and cross-entropy loss functions. 4) The problem of overfitting. 5) Regularization for linear models.
Learning Objectives

Learning Objectives

  • The goal of this course is to give learners basic understanding of modern neural networks and their applications in computer vision and natural language understanding.
Expected Learning Outcomes

Expected Learning Outcomes

  • Module 1: Introduction to optimization
  • Module 2: Introduction to neural networks
  • Module 3: Deep Learning for images
  • Module 4: Unsupervised representation learning
  • Module 5: Deep learning for sequences
Course Contents

Course Contents

  • Module 1: Introduction to optimization
  • Module 2: Introduction to neural networks
  • Module 3: Deep Learning for images
  • Module 4: Unsupervised representation learning
  • Module 5: Deep learning for sequences
Assessment Elements

Assessment Elements

  • non-blocking домашние задания
  • non-blocking экзамен
    Экзамен состоит из теоретических вопросов, которые были на лекциях
Interim Assessment

Interim Assessment

  • 2024/2025 2nd module
    Итоговая оценка вычисляется как среднее арифметическое оценок за домашние задания. Если студента не устраивает полученная оценка, то можно добрать до двух баллов на экзамене
Bibliography

Bibliography

Recommended Core Bibliography

  • Bhavsar, K., Kumar, N., & Dangeti, P. (2017). Natural Language Processing with Python Cookbook : Over 60 Recipes to Implement Text Analytics Solutions Using Deep Learning Principles. Packt Publishing.

Recommended Additional Bibliography

  • Ning, C., & You, F. (2019). Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming. https://doi.org/10.1016/j.compchemeng.2019.03.034

Authors

  • DYACHKOVA ANNA EVGENEVNA
  • KLYSHINSKIY EDUARD STANISLAVOVICH