# Deep Learning of Part-based Representation of Data Using Sparse Autoencoders with Nonnegativity Constraints

arXiv: https://arxiv.org/abs/1601.02733 · HTML: https://mlsanity.com/paper/1601.02733/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2016.

## Built on by (most cited first, 8 of 8)

- [Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning](https://mlsanity.com/paper/2405.05714/) (2024)
- [Fixed points of nonnegative neural networks](https://mlsanity.com/paper/2106.16239/) (2021)
- [Differentiable Genetic Programming for High-dimensional Symbolic Regression](https://mlsanity.com/paper/2304.08915/) (2023)
- [Bayesian Entropy Neural Networks for Physics-Aware Prediction](https://mlsanity.com/paper/2407.01015/) (2024)
- [Multiplicative update rules for accelerating deep learning training and increasing robustness](https://mlsanity.com/paper/2307.07189/) (2023)
- [A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning](https://mlsanity.com/paper/2301.07272/) (2023)
- [On the Relation Between Autoencoders and Non-negative Matrix Factorization, and Their Application for Mutational Signature Extraction](https://mlsanity.com/paper/2405.07879/) (2024)
- [Using Part-based Representations for Explainable Deep Reinforcement Learning](https://mlsanity.com/paper/2408.11455/) (2024)

## Abstract (arXiv)

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested on three standard image data sets and one text dataset. The results indicate that the nonnegativity constraint forces the autoencoder to learn features that amount to a part-based representation of data, while improving sparsity and reconstruction quality in comparison with the traditional sparse autoencoder and Nonnegative Matrix Factorization. It is also shown that this newly acquired representation improves the prediction performance of a deep neural network.