The Cerebellar Model Articulation Controller (CMAC) is a type of neural network based on a model of the mammalian cerebellum. It is also known as the Cerebellar Model Arithmetic Computer. It is a type of associative memory.^{[2]}
Contents 
The CMAC was first proposed as a function modeler for robotic controllers by James Albus in 1975^{[1]} (hence the name), but has been extensively used in reinforcement learning and also as for automated classification in the machine learning community. CMAC computes a function f(x_{1}...x_{ n}), where n is the number of input dimensions. The input space is divided up into hyperrectangles, each of which is associated with a memory cell. The contents of the memory cells are the weights, which are adjusted during training. Usually, more than one quantisation of input space is used, so that any point in input space is associated with a number of hyperrectangles, and therefore with a number of memory cells. The output of a CMAC is the algebraic sum of the weights in all the memory cells activated by the input point.
A change of value of the input point results in a change in the set of activated hyperrectangles, and therefore a change in the set of memory cells participating in the CMAC output. The CMAC output is therefore stored in a distributed fashion, such that the output corresponding to any point in input space is derived from the value stored in a number of memory cells. This provides generalisation.
In the image on the right, there are two inputs to the CMAC, represented as a twodimensional space. Two quantising functions have been used to divide this space with two overlapping grids (one shown in heavier lines). A single input is shown near the middle, and this has activated two memory cells, corresponding to the shaded area. If another point occurs close to the one shown, it will share some of the same memory cells, providing generalisation.
The CMAC is trained by presenting pairs of input points and output values, and adjusting the weights in the activated cells by a proportion of the error observed at the output. This simple training algorithm has a proof of convergence.^{[3]}
It is normal to add a kernel function to the hyperrectangle, so that points falling towards the edge of a hyperrectangle have a smaller activation than those falling near the centre.^{[4]}
One of the major problems cited in practical use of CMAC is the memory size required, which is directly related to the number of cells used. This is usually ameriolated by using a hash function, and only providing memory storage for the actual cells that are activated by inputs.
