Neural networks are a priori biased towards Boolean functions with low entropy

lib:d0f62d4d5d81c968 (v1.0.0)

Authors: Chris Mingard,Joar Skalse,Guillermo Valle-Pérez,David Martínez-Rubio,Vladimir Mikulik,Ard A. Louis
Where published: ICLR 2020 1
ArXiv: 1909.11522
Document:  PDF  DOI 
Abstract URL: https://arxiv.org/abs/1909.11522v3


Understanding the inductive bias of neural networks is critical to explaining their ability to generalise. Here, for one of the simplest neural networks -- a single-layer perceptron with n input neurons, one output neuron, and no threshold bias term -- we prove that upon random initialisation of weights, the a priori probability P(t) that it represents a Boolean function that classifies t points in {0,1}^n as 1 has a remarkably simple form: P(t) = 2^{-n} for 0\leq t < 2^n. Since a perceptron can express far fewer Boolean functions with small or large values of t (low entropy) than with intermediate values of t (high entropy) there is, on average, a strong intrinsic a-priori bias towards individual functions with low entropy. Furthermore, within a class of functions with fixed t, we often observe a further intrinsic bias towards functions of lower complexity. Finally, we prove that, regardless of the distribution of inputs, the bias towards low entropy becomes monotonically stronger upon adding ReLU layers, and empirically show that increasing the variance of the bias term has a similar effect.

Relevant initiatives  

Related knowledge about this paper Reproduced results (crowd-benchmarking and competitions) Artifact and reproducibility checklists Common formats for research projects and shared artifacts Reproducibility initiatives

Comments  

Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!