Decoupling Learning Rules from Representations
This work tackles a foundational issue in AI design, particularly for neural networks, by enabling more flexible and consistent learning processes, though it is incremental in nature.
The paper addresses the undesirable coupling between learning rules and representations in AI systems, where using the same learning rule with different representations can lead to different outcomes, and presents a method to partially decouple these decisions across unsupervised, reinforcement, and supervised learning.
In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating an artificial intelligence system, we must make two decisions: what representation should be used (i.e., what parameterized function should be used) and what learning rule should be used to search through the resulting set of representable functions. Using most learning rules, these two decisions are coupled in a subtle (and often unintentional) way. That is, using the same learning rule with two different representations that can represent the same sets of functions can result in two different outcomes. After arguing that this coupling is undesirable, particularly when using artificial neural networks, we present a method for partially decoupling these two decisions for a broad class of learning rules that span unsupervised learning, reinforcement learning, and supervised learning.