# An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Non-stationary Data Streams

arXiv: https://arxiv.org/abs/1808.08517 · HTML: https://mlsanity.com/paper/1808.08517/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [Adaptive Online Incremental Learning for Evolving Data Streams](https://mlsanity.com/paper/2201.01633/) (2022)
- [Autonomous Cross Domain Adaptation under Extreme Label Scarcity](https://mlsanity.com/paper/2209.01548/) (2022)
- [Scalable Teacher Forcing Network for Semi-Supervised Large Scale Data Streams](https://mlsanity.com/paper/2107.02943/) (2021)
- [DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System](https://mlsanity.com/paper/2308.06378/) (2023)
- [Dynamic Long-Term Time-Series Forecasting via Meta Transformer Networks](https://mlsanity.com/paper/2401.13968/) (2024)
- [Self-Organizing Recurrent Stochastic Configuration Networks for Nonstationary Data Modelling](https://mlsanity.com/paper/2410.10072/) (2024)

## Abstract (arXiv)

Existing FNNs are mostly developed under a shallow network configuration having lower generalization power than those of deep structures. This paper proposes a novel self-organizing deep FNN, namely DEVFNN. Fuzzy rules can be automatically extracted from data streams or removed if they play limited role during their lifespan. The structure of the network can be deepened on demand by stacking additional layers using a drift detection method which not only detects the covariate drift, variations of input space, but also accurately identifies the real drift, dynamic changes of both feature space and target space. DEVFNN is developed under the stacked generalization principle via the feature augmentation concept where a recently developed algorithm, namely gClass, drives the hidden layer. It is equipped by an automatic feature selection method which controls activation and deactivation of input attributes to induce varying subsets of input features. A deep network simplification procedure is put forward using the concept of hidden layer merging to prevent uncontrollable growth of dimensionality of input space due to the nature of feature augmentation approach in building a deep network structure. DEVFNN works in the sample-wise fashion and is compatible for data stream applications. The efficacy of DEVFNN has been thoroughly evaluated using seven datasets with non-stationary properties under the prequential test-then-train protocol. It has been compared with four popular continual learning algorithms and its shallow counterpart where DEVFNN demonstrates improvement of classification accuracy. Moreover, it is also shown that the concept drift detection method is an effective tool to control the depth of network structure while the hidden layer merging scenario is capable of simplifying the network complexity of a deep network with negligible compromise of generalization performance.