Machine Learning - AbhiAgarwal/notes GitHub Wiki

Algorithms

  • Supervised learning
    • Statistical classification
  • Semi-supervised learning
  • Unsupervised learning
    • Artificial neural network
    • Association rule learning
    • Hierarchical clustering
    • Cluster analysis
    • Outlier Detection
  • Reinforcement learning
  • Deep learning

Supervised learning

Support Vector Machines

Why called Support Vector Machines

Kernel Method

  • http://en.wikipedia.org/wiki/Kernel_method
    • Kernel methods are a class of algorithms for pattern analysis, whose best known member is the support vector machine (SVM). The general task of pattern analysis is to find and study general types of relations in datasets.
    • For many of these tasks, data have to be represented as feature vectors, but kernel methods replace this representation by similarities to other data points.
    • Kernel methods owe their name to the use of kernel functions, which enable them to operate in a high-dimensional, implicit feature space without ever computing the coordinates of the data in that space, but rather by simply computing the inner products between the images of all pairs of data in the feature space. This operation is often computationally cheaper than the explicit computation of the coordinates. This approach is called the kernel trick.
    • Any linear model can be turned into a non-linear model by applying the "kernel trick" to the model: replacing its features (predictors) by a kernel function.

Semi-supervised learning

  • You have to classify something say if an image is either a motorcycle or a car, and the images you have are not classified (it isn't labeled on the image if it is a motorcycle or a car). This is a problem where you could use semi-supervised as you know that you have to classify them as either motorcycle or a car, but the data itself is not labeled, and therefore it can't check to see what it is itself.

Q and A

Sources