Abstract
Researchers and educators have long wrestled with the question of how best to teach their clients be they humans, non-human animals or machines. Here, we examine the role of a single variable, the difficulty of training, on the rate of learning. In many situations we find that there is a sweet spot in which training is neither too easy nor too hard, and where learning progresses most quickly. We derive conditions for this sweet spot for a broad class of learning algorithms in the context of binary classification tasks. For all of these stochastic gradient-descent based learning algorithms, we find that the optimal error rate for training is around 15.87% or, conversely, that the optimal training accuracy is about 85%. We demonstrate the efficacy of this ‘Eighty Five Percent Rule’ for artificial neural networks used in AI and biologically plausible neural networks thought to describe animal learning.
Highlights
Researchers and educators have long wrestled with the question of how best to teach their clients be they humans, non-human animals or machines
In this paper we address this issue of optimal training difficulty for a broad class of learning algorithms in the context of binary classification tasks, in which ambiguous stimuli must be classified into one of two classes
A major factor in determining the difficulty of this perceptual decision is the fraction of coherently moving dots, which can be manipulated by the experimenter to achieve a fixed error rate during training using a procedure known as ‘staircasing’[17]
Summary
Researchers and educators have long wrestled with the question of how best to teach their clients be they humans, non-human animals or machines. These algorithms descend the gradient of error rate as a function of model parameters Such gradient-descent learning forms the basis of many algorithms in AI, from single-layer perceptrons to deep neural networks[10], and provides a quantitative description of human and animal learning in a variety of situations, from perception[11], to motor control[12] to reinforcement learning[13]. For these algorithms, we provide a general result for the optimal difficulty in terms of a target error rate for training. We demonstrate the applicability of the Eighty Five Percent Rule to artificial one- and two-layer neural networks[9,14], and a model from computational neuroscience that is thought to describe human and animal perceptual learning[11]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.