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.

我们发现身体感受的对数和刺激之间的关系 - 韦伯 - 费希纳定律对人类概念的学习算法有利，特别是通过神经网络的对数幂级数的作用，可以在少数训练迭代和有限的计算资源内加速机器对人类概念的学习。

通过韦伯 - 费克纳定律加速机器学习

Accelerating Machine Learning via the Weber-Fechner Law

We analyze different aspects of our quantum modeling approach of human
concepts, and more specifically focus on the quantum effects of contextuality,
interference, entanglement and emergence, illustrating how each of them makes
its appearance in specific situations of the dynamics of human concepts and
their combinations. We point out the relation of our approach, which is based
on an ontology of a concept as an entity in a state changing under influence of
a context, with the main traditional concept theories, i.e. prototype theory,
exemplar theory and theory theory. We ponder about the question why quantum
theory performs so well in its modeling of human concepts, and shed light on
this question by analyzing the role of complex amplitudes, showing how they
allow to describe interference in the statistics of measurement outcomes, while
in the traditional theories statistics of outcomes originates in classical
probability weights, without the possibility of interference. The relevance of
complex numbers, the appearance of entanglement, and the role of Fock space in
explaining contextual emergence, all as unique features of the quantum
modeling, are explicitly revealed in this paper by analyzing human concepts and
their dynamics.

本文分析了量子建模途径中与人类概念相关的不同方面，重点关注了上下文相关性、干涉、纠缠和新兴量子效应，并举例说明它们在人类概念及其组合的特定情况下的出现。