Algorithms generate input-output mappings through operations on representations. In cognitive science, we use algorithms to explain cognition. For example, we use tree-search algorithms to explain planning, reinforcement learning algorithms to explain exploration, and Bayesian algorithms to explain categorization. There are often many cognitive science algorithms consistent with a subject's performance on a task. How are we supposed to choose? It is natural to think of algorithms as causal models of brain processes. Thus, a natural method for choosing an algorithm is to look for parts in the brain corresponding to the steps of the algorithm. However, we haven't found many cognitive science algorithms using this method. This has led some to view cognitive science algorithms as merely normative, indicating the ideal input-output mapping without attributing any particular operation to the brain. It has led others to view cognitive science algorithms as merely useful fictions; useful insofar as they allow us to predict behavior, but fictional insofar as they inaccurately describe the causes of that behavior. They recommend explaining cognitive processes using other frameworks, such as dynamical systems theory. As an alternative, we suggest identifying a neural system's algorithm by assessing how quickly it learns alternative input-output mappings, that is, its transfer learning profile. The basic idea is that, depending on which algorithm is being used, different input-output mappings will be easier to learn, allowing us to recover its original algorithm from its transfer learning profile. We use artificial neural networks to demonstrate that this proposal productively applies to multiple networks and tasks. We conclude that transfer learning is a promising approach for integrating algorithms with neural networks and thus for integrating cognitive science with systems neuroscience and machine learning.