论文标题
通过Weber-Fechner Law加速机器学习
Accelerating Machine Learning via the Weber-Fechner Law
论文作者
论文摘要
Weber-Fechner定律观察到人类的感知尺度是刺激的对数。我们认为，学习人类概念的算法可以从Weber-Fechner法律中受益。具体而言，我们通过其分类输出的对数功率系列将Weber-Fechner强加于简单的神经网络，无论有无卷积。我们的实验在一些训练迭代和有限的计算资源中显示了MNIST数据集令人惊讶的性能和准确性，这表明Weber-Fechner可以加速对人类概念的机器学习。
The Weber-Fechner Law observes that human perception scales as the logarithm of the stimulus. We argue that learning algorithms for human concepts could benefit from the Weber-Fechner Law. Specifically, we impose Weber-Fechner on simple neural networks, with or without convolution, via the logarithmic power series of their sorted output. Our experiments show surprising performance and accuracy on the MNIST data set within a few training iterations and limited computational resources, suggesting that Weber-Fechner can accelerate machine learning of human concepts.
