Machine Learning for Digital Humanities

Explore fundamental concepts of artificial intelligence, machine learning, and deep learning through this comprehensive video tutorial series specifically designed for humanities scholars and learners without mathematical backgrounds. Master the basics of neural networks, understanding key concepts like models, layers, training processes, validation, testing, and prediction methods. Learn to work with TensorFlow and Keras frameworks to build and implement neural networks for solving humanities-specific problems. Practice hands-on skills through a detailed binary text classification project that demonstrates how to distinguish between different authors' writing styles, covering the complete workflow from data preparation and labeling to model creation, training, saving, loading, and testing. Gain practical experience with shallow neural networks and discover various types of neural network architectures applicable to digital humanities research and analysis.

Syllabus

An Easy Introduction to Machine Learning
Intro to Deep Learning (Neural Networks for DH 02)
What are Models and Layers (Neural Networks for DH 03)
How Training Works (Neural Networks for DH 04)
Validation, Testing, and Loss (Neural Networks for DH 05)
What is Prediction (Neural Networks for DH 06)
Types of Neural Networks (Neural Networks for DH 07)
What is TensorFlow (Neural Networks for DH 08)
What is Keras (Neural Networks for DH 09)
Shallow Neural Networks SNNs (Neural Networks for DH 10)
Binary Text Classification | The Problem | Dan Brown v Oscar Wilde (Neural Nets for DH 11a)
Preparing and Labeling Data for Binary Text Classification (Neural Networks for DH 11b)
Creating and Training a Binary Text Classification Model in Keras (Neural Networks for DH 11c)
How to Save, Load, and Test Models in Keras and TensorFlow (Neural Networks for DH 11d)