# Data Classification with Dynamically Growing and Shrinking Neural Networks

arXiv: https://arxiv.org/abs/2507.01043 · HTML: https://mlsanity.com/paper/2507.01043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Breaking the Curse of Dimensionality with Convex Neural Networks](https://mlsanity.com/paper/1412.8690/) (2014)
- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [GradMax: Growing Neural Networks using Gradient Information](https://mlsanity.com/paper/2201.05125/) (2022)
- [Simplifying approach to Node Classification in Graph Neural Networks](https://mlsanity.com/paper/2111.06748/) (2021)
- [The Canonical Interval Forest (CIF) Classifier for Time Series Classification](https://mlsanity.com/paper/2008.09172/) (2020)
- [Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search](https://mlsanity.com/paper/1805.07440/) (2018)
- [Multilevel Optimization for Policy Design with Agent-Based Epidemic Models](https://mlsanity.com/paper/2304.02281/) (2023)

## Abstract (arXiv)

The issue of data-driven neural network model construction is one of the core problems in the domain of Artificial Intelligence. A standard approach assumes a fixed architecture with trainable weights. A conceptually more advanced assumption is that we not only train the weights, but also find out the optimal model architecture. We present a new method that realizes just that. This article is an extended version of our conference paper titled "Dynamic Growing and Shrinking of Neural Networks with Monte Carlo Tree Search [26]". In the paper, we show in detail how to create a neural network with a procedure that allows dynamic shrinking and growing of the model while it is being trained. The decision-making mechanism for the architectural design is governed by a Monte Carlo tree search procedure which simulates network behavior and allows to compare several candidate architecture changes to choose the best one. The proposed method was validated using both visual and time series datasets, demonstrating its particular effectiveness in multivariate time series classification. This is attributed to the architecture's ability to adapt dynamically, allowing independent modifications for each time series. The approach is supplemented by Python source code for reproducibility. Experimental evaluations in visual pattern and multivariate time series classification tasks revealed highly promising performance, underscoring the method's robustness and adaptability.