GESIS Training Courses
user_jsdisabled
Search

Scientific Coordination

Verena Kunz

Administrative Coordination

Noemi Hartung
Tel: +49 621 1246-211

Introduction to Deep Learning in R

About
Location:
Online via Zoom
General Topics:
Course Level:
Format:
Software used:
Duration:
Language:
Fees:
Students: 275 €
Academics: 413 €
Commercial: 825 €
 
Keywords
Additional links
Lecturer(s): Christian Arnold

About the lecturer - Christian Arnold

Course description

Neural networks-long believed dead-are back. Advances in training deep neural network architectures have had a tremendous impact on Computer Science and Machine Learning for more than a decade now. Today, they are the foundation of many modern data science applications in academia and industry.  Their capacity to handle unstructured information such as text, audio, or image data makes them particularly attractive for researchers who want to solve research problems that involve data beyond 'just' spreadsheets. This hands-on course is designed to demystify the complexities of deep learning, providing you with a solid foundation in its fundamental concepts and practical applications.
 
Deep learning, a subset of machine learning, involves training neural networks to learn and extract variables from complex data. Deep learning can be utilized in social science research in many ways and is the foundation of many modern tools, e.g. for analyzing text. For example, it is possible to employ deep learning for sentiment analysis, topic modelling, entity recognition, and language translation, all of which are valuable in understanding public opinion, political discourse, and social media behavior. Moreover, deep learning can also be the foundation of image and video analysis, social network analysis, time-series analysis, predictive modelling, or enhanced data pre-processing such as multiple imputation.
 
Deep learning is a little different from other, more classical machine learning models approaches. While classical machine learning models have fewer parameters and a shallower structure, deep neural networks often consist of many layers with a large number of parameters. Their makeup allows them to learn highly complex and hierarchical features from the data. Deep learning can thus automatically retrieve features from the raw data through the network's layers, reducing the need for extensive manual feature engineering.
 
This workshop will provide an introduction to deep neural networks. Starting from flat architectures, we will understand how neural networks use backward propagation of prediction errors to optimize their performance. Adding more layers to the initial set-up, we will then go on and build increasingly “deep” architectures. We implement fully connected deep learning architectures and learn about classical pitfalls and how to tackle them.
 
The workshop will also give up the full connectedness between nodes and take a first look at models that aggregate information to more abstract data representations and recurrent data. We will guide you through the fundamental principles of deep learning and its application in various domains, focusing specifically natural language processing (NLP) with a brief excursion to computer vision at the end of the workshop. The course is structured into an introduction to the basics of deep learning and two main sections:
 
1. Basics of Deep Learning:
  • Understanding the architecture of neural networks: perceptrons, layers, activations, and more.
  • Exploring forward and backward propagation: how neural networks make predictions and learn from data.
  • Introduction to optimization techniques: gradient descent, learning rates, and loss functions.
2. Natural Language Processing with Sequential Architectures:
  • Introduction to sequential data and its challenges in NLP.
  • Exploring recurrent neural networks (RNNs) and long short-term memory (LSTM) for tasks like sentiment analysis.
3. Exploring Convolutional Architectures:
  • Introduction to convolutional architectures for Natural Language Processing
  • Outlook: Using convolutional architectures for the analysis of images
 
Organizational Structure of the Course
For teaching, the class will alternate between lecture-style blocks and more hands-on workshop phases where you implement code yourselves. There is time for working alone, but we will also have dedicated sections where you will work in groups. All sessions will have the support from the lecturer.


Target group

  • Social Scientists writ large, including Psychology, Business Administration, Economics, Sociology, Political Science, or Communication Science
  • Researchers who have research problems that require predictions
  • Researchers working with classic spreadsheet data, but also unstructured data like text or images


Learning objectives

By the end of the course participants will:
  • have a comprehensive understanding of deep learning principles, architectures, and their applications in NLP.
  • be equipped with the skills to start experimenting with deep learning tools, integrating them into your social science research, and uncovering valuable insights from complex data.
  •  


    Prerequisites

  • A good understanding of R (or Python, which should allow you to follow along with the R examples and potentially transfer them to Python)
  • A good understanding of non-linear models, including an understanding of their mathematical foundations, e.g. of logit models.
  •  
    Software requirements
    This class relies on R and KERAS, a user-friendly API that offers an intuitive entry point for social scientists to define and train many different types of deep-learning models. You do not have to prepare your local machines, since we will deploy all code in the Cloud.


    Schedule

    Recommended readings