Master
2023/2024![Learning Objectives](/f/src/global/i/edu/objectives.svg)
![Expected Learning Outcomes](/f/src/global/i/edu/results.svg)
![Course Contents](/f/src/global/i/edu/sections.svg)
![Interim Assessment](/f/src/global/i/edu/intermediate_certification.svg)
![Bibliography](/f/src/global/i/edu/library.svg)
Introduction to Deep Learning in NLP
Category 'Best Course for Career Development'
Category 'Best Course for Broadening Horizons and Diversity of Knowledge and Skills'
Type:
Compulsory course (Computational Linguistics)
Area of studies:
Fundamental and Applied Linguistics
Delivered by:
School of Linguistics
Where:
Faculty of Humanities
When:
2 year, 1, 2 module
Mode of studies:
offline
Open to:
students of all HSE University campuses
Instructors:
Сорокин Семен Александрович
Master’s programme:
Computational Linguistics
Language:
English
ECTS credits:
6
Contact hours:
32
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
- 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
- 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
- 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
Interim Assessment
- 2023/2024 2nd module0.2 * домашнее задание 1 + 0.2 * домашнее задание 2 + 0.2 * домашнее задание 3 + 0.4 * проект
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