Machine Learning

In this lecture, we will take a look at the widely used Perceptron algorithm and its associated mistake bound theorem.

Lecture slides

• The Perceptron algorithm and its variants
• The Perceptron mistake bound
• Videos:
  • Lecture 1, introducing the algorithm

  • Lecture 2, describing practical variants and the mistake bound theorem

  • Older videos:
    • spring 2024: part 1, part 2
    • spring 2023: part 1, part 2, part 3
    • fall 2018 part 1, part 2
    • fall 2017 part 1, part 2

Links and Resources

• Chapters 3 and 6 of Hal Daumé III, A Course in Machine Learning

• Dan Roth, On-Line Learning of Linear Functions (course notes)

Further reading

• Freund, Yoav, and Robert E. Schapire. Large margin classification using the perceptron algorithm. Machine learning 37, no. 3 (1999): 277-296.

• Roni Khardon and Gabriel Wachman, Noise Tolerant Variants of the Perceptron Algorithm, Journal of Machine Learning Research , Vol 8, pp 227–248, 2007