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

Neural Networks and Deep Learning

Area of studies: Business Informatics
When: 2 year, 1, 2 module
Mode of studies: distance learning
Online hours: 20
Open to: students of all HSE University campuses
Instructors: Seungmin Jin
Master’s programme: Business Analytics and Big Data Systems
Language: English
ECTS credits: 6

Course Syllabus

Abstract

In today's data-driven world, neural networks and deep learning are revolutionizing how we solve complex problems. This course empowers students to utilize visual programming tools that integrate with the latest deep learning frameworks, allowing them to intuitively and efficiently tackle real-world challenges. By focusing on practical problem-solving, students will learn to apply neural network models to derive actionable insights, enhancing their analytical capabilities in a user-friendly environment. The course will specifically utilize KNIME, showcasing its strengths in visual programming to facilitate the development and deployment of deep learning models. The course will also explore Explainable AI (XAI), helping students understand how to make AI models more transparent and understandable.
Learning Objectives

Learning Objectives

  • Learn to effectively apply deep learning techniques to real-world business problems in computer vision, natural language processing, and tabular data
  • Acknowledge ethical implications of applying machine learning in practice
Expected Learning Outcomes

Expected Learning Outcomes

  • Able to use embedding for tabular data and recommenders
  • Able to use momentum and advanced optimizers for stochastic gradient descent
  • Able to use residual blocks with neural networks
  • Can construct a digit classifier using a deep learning model
  • Can construct a neural network from scratch
  • Can construct recurrent neural network from scratch
  • Can solve multi-class and multi-label problems with deep learning
  • Knows advanced neural networks such as U-Net and Siamese
  • Knows and uses state-of-the-art approaches to train neural networks
  • Knows the definitions of deep learning
  • Understands approaches to put machine learning system into production
  • Understands approaches to solve natural language processing problems
  • Understands data ethics and able to detect ethical problems
  • Understands the role of convolutions in image processing
Course Contents

Course Contents

  • Introduction
  • Machine learning in production
  • Data ethics
  • Introduction to deep learning
  • Neural Networks Basics
  • Shallow neural networks
  • The training process of neural networks
  • A neural net from scratch
  • Training a digit classifier
  • Deep Neural Networks
  • Convolutional neural networks
  • Image classification
  • Neural architectures
  • Reaching state-of-the-art
  • Class Activation Maps
  • Tabular data
  • Natural language processing
  • A language model from scratch
  • Residual neural networks
Assessment Elements

Assessment Elements

  • non-blocking Exam
    The exam will be conducted remotely on the MS Teams platform. Students are required to submit their written responses in a text document format. Each student must complete the assignment independently, without consulting or re-using solutions from fellow students. The submission link will be provided in MS Teams, and all responses must be submitted one hour before the end of the exam. Students are allowed to use any resources to complete the assignment, but collaboration is not permitted. Example of Question: Neural Networks in Business Applications Case Study: A retail company wants to improve its customer experience by providing personalized product recommendations on its online platform. The company has a large dataset of customer purchase histories, product details, and customer reviews. Question: Based on the case study provided, describe how you would develop a neural network model to address the company's goal of enhancing customer experience through personalized recommendations. In your response, consider the following: Model Selection: Explain which type of neural network architecture you would choose (e.g., feedforward neural network, recurrent neural network, convolutional neural network) and why it is suitable for this case. Data Processing: Describe how you would preprocess the data to make it suitable for training the neural network. Consider aspects such as feature selection, data normalization, and handling missing values. Implementation Strategy: Outline the steps you would take to implement the model, including training, validation, and deployment. Discuss any tools or frameworks you might use. Evaluation Metrics: Identify the metrics you would use to evaluate the model's performance and justify your choices. Business Impact: Discuss how the implementation of this model could potentially impact the business, considering both benefits and challenges. Instructions: Provide a detailed response in essay format, ensuring that your explanation is clear and concise. Use examples where appropriate to illustrate your points. This format encourages students to think critically about the application of neural networks in a real-world business scenario, focusing on model development, data handling, and business implications.
  • non-blocking Homework №2
    A student should provide a KNIME workflow
  • non-blocking Homework №1
    A student should provide a KNIME workflow
Interim Assessment

Interim Assessment

  • 2024/2025 2nd module
    0.2 * Exam + 0.3 * Homework №1 + 0.5 * Homework №2
Bibliography

Bibliography

Recommended Core Bibliography

  • Hastie, T., Tibshirani, R., & Friedman, J. H. (2009). The Elements of Statistical Learning : Data Mining, Inference, and Prediction (Vol. Second edition, corrected 7th printing). New York: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=277008
  • Ian Goodfellow, Yoshua Bengio, & Aaron Courville. (2016). Deep Learning. The MIT Press.
  • Jeremy Howard, & Sylvain Gugger. (2020). Deep Learning for Coders with Fastai and PyTorch. O’Reilly Media.

Recommended Additional Bibliography

  • M Narasimha Murty, & V Susheela Devi. (2015). Introduction To Pattern Recognition And Machine Learning. World Scientific.

Authors

  • KALMYKOVA NADEZHDA SERGEEVNA
  • Beklarian Armen Levonovich
  • Dzhin Seungmin