Psychophysical Machine Learning
arXiv:2208.11236v4h-index: 1
Originality Synthesis-oriented
AI Analysis
This work addresses performance enhancement in deep learning for applications where human-like perception is relevant, but it appears incremental as it adapts an existing psychophysical principle to machine learning.
The authors tackled the problem of improving deep learning performance by incorporating the Weber-Fechner Law, which describes human perception as logarithmic, into loss functions, resulting in enhanced network performance.
The Weber Fechner Law of psychophysics observes that human perception is logarithmic in the stimulus. We present an algorithm for incorporating the Weber Fechner law into loss functions for machine learning, and use the algorithm to enhance the performance of deep learning networks.