Machine Learning Algorithms Summary, Exercises of Artificial Intelligence

Download Machine Learning Algorithms Summary and more Exercises Artificial Intelligence in PDF only on Docsity!

ML Notes

Algorithm Input Output Learns by Complexity Control Notes

Naive Bayes boolean feature vector discrete estimating conditional probabilities (counting)

Assumes independent features

LaPlace Correction, XOR

basic Decision Tree boolean feature vector discrete minimizing average entropy at the branches

parametric: leaf size, minimum entropy Continuous-Valued Decision Tree

real feature vector discrete minimizing average entropy at the branches K-Nearest Neighbor real feature vector discrete memorizing all points parametric: K Scaling Perceptron real feature vector discrete maximizing margin (weight space search)

limited to linear separator guarantees separator if it exists SVM real feature vector discrete maximizing margin (quadratic programming)

maximizes margin in error function

Neural Net real feature vector discrete gradient descent (weight space search)

architecture Architecture, Scaling

Neural Net Regression real feature vector real gradient descent (weight space search)

architecture Architecture, Scaling

Regression Trees real feature vector real minimizing variance at the branches

Kernel functions (not SVM kernels) Nearest Neighbor Regression real feature vector real memorizing all points Kernel functions (not SVM kernels)

docsity.com