# An Adaptive Learning Method of Restricted Boltzmann Machine by Neuron Generation and Annihilation Algorithm

arXiv: https://arxiv.org/abs/1807.03478 · HTML: https://mlsanity.com/paper/1807.03478/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2018.

## Built on by (most cited first, 5 of 5)

- [Automatic Extraction of Road Networks from Satellite Images by using Adaptive Structural Deep Belief Network](https://mlsanity.com/paper/2110.12684/) (2021)
- [An Adaptive Structural Learning of Deep Belief Network for Image-based Crack Detection in Concrete Structures Using SDNET2018](https://mlsanity.com/paper/2110.12700/) (2021)
- [An Embedded System for Image-based Crack Detection by using Fine-Tuning model of Adaptive Structural Learning of Deep Belief Network](https://mlsanity.com/paper/2110.13145/) (2021)
- [A Distillation Learning Model of Adaptive Structural Deep Belief Network for AffectNet: Facial Expression Image Database](https://mlsanity.com/paper/2110.12717/) (2021)
- [Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster](https://mlsanity.com/paper/2511.05567/) (2025)

## Abstract (arXiv)

Restricted Boltzmann Machine (RBM) is a generative stochastic energy-based model of artificial neural network for unsupervised learning. Recently, RBM is well known to be a pre-training method of Deep Learning. In addition to visible and hidden neurons, the structure of RBM has a number of parameters such as the weights between neurons and the coefficients for them. Therefore, we may meet some difficulties to determine an optimal network structure to analyze big data. In order to evade the problem, we investigated the variance of parameters to find an optimal structure during learning. For the reason, we should check the variance of parameters to cause the fluctuation for energy function in RBM model. In this paper, we propose the adaptive learning method of RBM that can discover an optimal number of hidden neurons according to the training situation by applying the neuron generation and annihilation algorithm. In this method, a new hidden neuron is generated if the energy function is not still converged and the variance of the parameters is large. Moreover, the inactivated hidden neuron will be annihilated if the neuron does not affect the learning situation. The experimental results for some benchmark data sets were discussed in this paper.