PAPERUnderstanding Probabilistic Classifiers

Covers: theory of Probabilistic Classifier
Estimated time needed: 7 minutes
Questions this item adddesses:
  • Why do probabilistic classifiers with simplifying assumptions still work?
How to use this item?

Read the abstract, introduction, and conclusion.

Author(s) / creator(s) / reference(s)
Ashutosh Garg, Dan Roth

Introduction to Probabilistic Classifiers

Yan NusinovichTotal time needed: ~44 minutes
Learning Objectives
Provide background to newcomers to NLP about probabilistic classifiers.
Potential Use Cases
The user of this shortlist is someone new to NLP who needs to build a classifier and wants to compare the usefulness of different types of classifiers.
Target Audience
BEGINNERNewcomers to machine learning and natural language processing.
Go through the following annotated items in order:
ARTICLE 1. Probabilistic Classification
  • What is probabilistic classification?
2 minutes
ARTICLE 2. Probability and Machine Learning? — Part 1- Probabilistic vs Non-Probabilistic Machine Learning Models
  • What is the difference between probabilistic and non-probabilistic machine learning?
5 minutes
PAPER 3. Understanding Probabilistic Classifiers
  • Why do probabilistic classifiers with simplifying assumptions still work?
7 minutes
VIDEO 4. Build a Probabilistic Classification using Scikit-learn | Machine Learning Tutorials | Codegnan
  • How do you build a probabilistic classifier step-by-step?
30 minutes

Concepts Convered