Introduction to Machine Learning

Overview

In this lesson, we'll explore how researchers can integrate machine learning (ML) into their humanities research projects. We'll discuss examples, potential research questions, and foundational principles for successfully linking ML techniques to research interests.

Program Schedule, November 5

Time Activity Speaker
10:00 – 10:20 Introduction Simon Enni & Ida Marie S. Lassen
10:20 – 11:00 Exercise 1: Image classification with CNN
11:00-11:15 Break
11:15 – 11:45 Exercise 1 cont.
11:45 – 12:00 Reflection exercise
12:00 – 12:30 Lunch Break –
12:30 – 13:30 Exercise 2: Language modeling with ML
13:30 – 14:00 Reflection on exercises, discussion, perspectives

Program Schedule, December 3

Time Activity Speaker
10:00 – 10:40 Recap from last time, examples of ML-driven research in the humanities. Reflection exercise: Use of ML in your own field and potential ML tasks. Ida Marie S. Lassen
10:40 – 11:00 Introduction to unsupervised machine learning Simon Enni
11:00-11:15 Break
11:15 – 12:00 Exercise 3: Topic Discovery Simon Enni
12:00 – 12:30 Lunch break -
12:30 – 13:30 Exercise 3 cont.
13:30 – 14:00 Reflection on exercises, discussion, perspectives

Add to stop word list


    from sklearn.feature_extraction import text
    from sklearn.feature_extraction.text import TfidfVectorizer

    my_stop_words = list(text.ENGLISH_STOP_WORDS.union(["said", "mr"]))

    vectorizer_lda = CountVectorizer(
        lowercase=True,
        min_df=2,
        max_features=5000,
        stop_words=my_stop_words
    )

Materials

UCloud guide

PDF.

Instructor

Simon Enni & Ida Marie S. Lassen