Path9.Mod1.c - Selecting Binary Classification Algorithms for Azure ML Flashcards
Augmented learning https://learn.microsoft.com/en-us/azure/machine-learning/algorithm-cheat-sheet?WT.mc_id=docs-article-lazzeri&view=azureml-api-1 https://learn.microsoft.com/en-us/azure/machine-learning/media/algorithm-cheat-sheet/machine-learning-algorithm-cheat-sheet.png?view=azureml-api-1#lightbox
When you want to Predict between two categories where the there are under 100 features, resulting in a linear model
Two-Class SVM (Support Vector Machine)
When you want to Predict between two categories where training time is a priority, resulting in a linear model where the data is linearly separable or very close to it
Two-Class Averaged Perceptron
When you want to Predict between two categories where training time must be fast, resulting in a linear model, despite data not being linearly separable
Two-Class Logistic Regression
When you want to Predict between two categories where accuracy and fast training are your priorities, and memory utilization can be controlled
What this algorithm allows you to do, that makes it the ideal choice.
Two-Class Decision Forest. You can control the depth and number of trees.
When you want to Predict between two categories where accuracy and fast training are your priorities, despite high memory utilization
Two-Class Boosted Decision Forest. Produces a large memory footprint.
It takes months to train ChatGPT…
When you want to Predict between two categories where Accuracy is your highest priority and training time isn’t a consideration
Two-Class Neural Network
