paper-with-me

Papers

Accelerating Machine Learning via the Weber-Fechner Law

2022-04-21 · B. N. Kausik

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.

📄 PDF Abstract BibTeX arXiv:2204.11834

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Psychophysical Machine Learning

2022-08-23 · B. N. Kausik

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 …

Deep Learning

Psychophysical laws as reflection of mental space properties

2018-06-27

The paper is devoted to the relationship between psychophysics and physics of mind. The basic trends in psychophysics development are briefly discussed with special attention focused on Teghtsoonian's hypotheses. These h…

Spatial Stimuli Gradient Sketch Model

2015-02-15 · Joshin John Mathew, Alex Pappachen James

The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perceptio…

Edge DetectionFace RecognitionmodelObject

Weber-Fechner Law in Temporal Difference learning derived from Control as Inference

2024-12-30 · Keiichiro Takahashi, Taisuke Kobayashi, Tomoya Yamanokuchi, Takamitsu Matsubara

This paper investigates a novel nonlinear update rule based on temporal difference (TD) errors in reinforcement learning (RL). The update rule in the standard RL states that the TD error is linearly proportional to the d…

Reinforcement Learning (RL)

Number detectors spontaneously emerge in a deep neural network designed for visual object recognition

2019-05-08 · journal 2019 5 · Khaled Nasr, Pooja Viswanathan, Andreas Nieder

Humans and animals have a “number sense,” an innate capability to intuitively assess the number of visual items in a set, its numerosity. This capability implies that mechanisms to extract numerosity indwell the brain’…

ObjectObject Recognition