Infomax, or the principle of maximum information preservation, is an optimization principle for artificial neural networks and other information processing systems. It prescribes that a function that maps a set of input values to a set of output values should be chosen or learned so as to maximize the average Shannon mutual information between and , subject to a set of specified constraints and/or noise processes. Infomax algorithms are learning algorithms that perform this optimization process. The principle was described by Linsker in 1988.[1] The objective function is called the InfoMax objective.
As the InfoMax objective is difficult to compute exactly, a related notion uses two models giving two outputs , and maximizes the mutual information between these. This contrastive InfoMax objective is a lower bound to the InfoMax objective.[2]
Infomax, in its zero-noise limit, is related to the principle of redundancy reduction proposed for biological sensory processing by Horace Barlow in 1961,[3] and applied quantitatively to retinal processing by Atick and Redlich.[4]