Parameters - Variables inside the model that help it makes predictions. They are usually formed from the data, and not set by humans.
Hyperparameters - Parameters that affect the way a model works. They are usually set outside the model.
Cost function - An important parameter that calculates the performance of a model. It is the difference between the predicted value and the expected value.
Support Vector Machines
Data Mining - Analyzing datasets for meaningful patterns that can improve the models.
Entity extraction - Adding structure to the data. Can be done by humans or models.
Overfitting - The condition where a model is only able to identify the examplesgiven in the training data.
Backward chaining - Where a model starts with the output and works backwards to find data that might support it.
Forward chaining - Where a model starts with the dataset and tries to find an output.
Transfer learning - Making a model do a similar task for sometime, and then returning it to doing the original task for improving accuracy.
Directed Acyclic Graph
Support Vector Machine (SVM)
k-Nearest Neighbour (k-NN)

Left-click: follow link, Right-click: select node, Scroll: zoom