Machine Learning

generalisation

The ability of a machine learning model to perform well on unseen data, reflecting its capacity to apply learned patterns to new inputs

Association learning

A type of machine learning where the model discovers relationships between variables in large datasets.

Computational

Level of analysis that identifies what is the goal of model

Algorithmic

Level of analysis that looks at how the model’s goal can be acheived

Implementational

Level of analysis that focuses on the physical realization of the model, including hardware and software requirements.

Sum Rule

Product Rule

Product Rule

Bayes Rule

Chain Rule

Binomial

Entropy

Naive Bayes

Sample mean

Sample Standard Deviation

Accuracy

Error Rate

Error Rate Reduction

Precision

Recall

Sensitivity

Specificity

F1 Score

Macro Averaging

Micro Averaging

Weighted Averaging

Mean Information

Information Gain

Gain Ratio

Cosine Similarity

Inverse Linear Distance

Inverse Distance

Mean Squared Error

Gradient Descent

Root Mean Squared Error

Root Relative Squared Error

Sigmoid

Multinomial Log Regression for non-pivot

Multinomial Log Regression for pivot

Pointwise Mutual Information

Mutual Information

Expected value

Chi-Squared

Bias

Variance

Hyperbolic tan

ReLU

Cross-Entropy Loss

Soft max

Log-likelihood

Kernel Density Estimate

Cohesion

Separation

Sum of Squared Errors

Purity

Entropy (unsupervised)

Viterbi Algorithm inductive step

Forward Algorithm inductive step

Transition probability approximation

Observation probability approximation

Initial state approximation