# Deep Randomized Neural Networks

arXiv: https://arxiv.org/abs/2002.12287 · HTML: https://mlsanity.com/paper/2002.12287/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 30 of 33)

- [Random vector functional link network: recent developments, applications, and future directions](https://mlsanity.com/paper/2203.11316/) (2022)
- [Sampling weights of deep neural networks](https://mlsanity.com/paper/2306.16830/) (2023)
- [Deep learning for dynamic graphs: models and benchmarks](https://mlsanity.com/paper/2307.06104/) (2023)
- [Learning Augmentation Distributions using Transformed Risk Minimization](https://mlsanity.com/paper/2111.08190/) (2021)
- [Randomly Initialized Convolutional Neural Network for the Recognition of COVID-19 using X-ray Images](https://mlsanity.com/paper/2105.08199/) (2021)
- [Koopman-informed recurrent neural networks](https://mlsanity.com/paper/2410.23467/) (2024)
- [Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks](https://mlsanity.com/paper/2106.00881/) (2021)
- [Asymptotic Stability in Reservoir Computing](https://mlsanity.com/paper/2206.03854/) (2022)
- [Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience](https://mlsanity.com/paper/2408.12664/) (2024)
- [ResCP: Reservoir Conformal Prediction for Time Series Forecasting](https://mlsanity.com/paper/2510.05060/) (2025)
- [Cluster-based Input Weight Initialization for Echo State Networks](https://mlsanity.com/paper/2103.04710/) (2021)
- [Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Case](https://mlsanity.com/paper/2201.04543/) (2022)
- [On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification](https://mlsanity.com/paper/2102.08634/) (2021)
- [Coin Flipping Neural Networks](https://mlsanity.com/paper/2206.09182/) (2022)
- [Neural Graph Revealers](https://mlsanity.com/paper/2302.13582/) (2023)
- [Randomly Initialized Subnetworks with Iterative Weight Recycling](https://mlsanity.com/paper/2303.15953/) (2023)
- [Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices](https://mlsanity.com/paper/2103.17142/) (2021)
- [The Hyperdimensional Transform for Distributional Modelling, Regression and Classification](https://mlsanity.com/paper/2311.08150/) (2023)
- [Euler State Networks: Non-dissipative Reservoir Computing](https://mlsanity.com/paper/2203.09382/) (2022)
- [PRANC: Pseudo RAndom Networks for Compacting deep models](https://mlsanity.com/paper/2206.08464/) (2022)
- [Random weights of DNNs and emergence of fixed points](https://mlsanity.com/paper/2501.04182/) (2025)
- [Half-Layered Neural Networks](https://mlsanity.com/paper/2506.04352/) (2025)
- [An Enhanced Randomly Initialized Convolutional Neural Network for Columnar Cactus Recognition in Unmanned Aerial Vehicle Imagery](https://mlsanity.com/paper/2105.04430/) (2021)
- [Physical Deep Learning with Biologically Plausible Training Method](https://mlsanity.com/paper/2204.13991/) (2022)
- [On gradient descent training under data augmentation with on-line noisy copies](https://mlsanity.com/paper/2206.03734/) (2022)
- [Emergence of Structure in Ensembles of Random Neural Networks](https://mlsanity.com/paper/2505.10331/) (2025)
- [RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning](https://mlsanity.com/paper/2505.19054/) (2025)
- [Random Feature Spiking Neural Networks](https://mlsanity.com/paper/2510.01012/) (2025)
- [Fast PINN Eigensolvers via Biconvex Reformulation](https://mlsanity.com/paper/2511.00792/) (2025)
- [Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains](https://mlsanity.com/paper/2604.09361/) (2026)

## Abstract (arXiv)

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network architectures where the connections to the hidden layer(s) are left untrained after initialization. Limiting the training algorithms to operate on a reduced set of weights inherently characterizes the class of Randomized Neural Networks with a number of intriguing features. Among them, the extreme efficiency of the resulting learning processes is undoubtedly a striking advantage with respect to fully trained architectures. Besides, despite the involved simplifications, randomized neural systems possess remarkable properties both in practice, achieving state-of-the-art results in multiple domains, and theoretically, allowing to analyze intrinsic properties of neural architectures (e.g. before training of the hidden layers' connections). In recent years, the study of Randomized Neural Networks has been extended towards deep architectures, opening new research directions to the design of effective yet extremely efficient deep learning models in vectorial as well as in more complex data domains. This chapter surveys all the major aspects regarding the design and analysis of Randomized Neural Networks, and some of the key results with respect to their approximation capabilities. In particular, we first introduce the fundamentals of randomized neural models in the context of feed-forward networks (i.e., Random Vector Functional Link and equivalent models) and convolutional filters, before moving to the case of recurrent systems (i.e., Reservoir Computing networks). For both, we focus specifically on recent results in the domain of deep randomized systems, and (for recurrent models) their application to structured domains.