This portal has been archived. Explore the next generation of this technology.
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.
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
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)