Portal:Machine learning/Selected picture
From Infogalactic: the planetary knowledge core
Selected pictures
Portal:Machine learning/Selected picture/1
Credit: User:Cyc
A support vector machine is a classifier that divides its input space into two regions, separated by a linear boundary. Here, it has learned to distinguish black and white circles.
Portal:Machine learning/Selected picture/2
Credit: User:Qwertyus
Diagram of a restricted Boltzmann machine (RBM) with three visible units and four hidden units (no bias units).
Portal:Machine learning/Selected picture/3
Credit: User:Alisneaky
The effect of the kernel trick in a classifier. On the left, a non-linear decision boundary has been learned by a "kernelized" classifier. This simulates the effect of a feature map φ, that transforms the problem space into one where the decision boundary is linear (right).
Portal:Machine learning/Selected picture/4
Credit: User:Fyedernoggersnodden
An Elman network, one of the simplest types of recurrent neural networks. The network has an input layer, a hidden layer and an output layer. The hidden layer is connected to a context layer (bottom) that remembers its activation at the previous observation, giving the network a memory and making it capable of processing sequences (e.g., sequences of words or of phonemes).