# Multi-Model Least Squares-Based Recomputation Framework for Large Data Analysis

arXiv: https://arxiv.org/abs/2101.01271 · HTML: https://mlsanity.com/paper/2101.01271/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Stochastic Configuration Networks: Fundamentals and Algorithms](https://mlsanity.com/paper/1702.03180/) (2017)
- [Random Vector Functional Link Neural Network based Ensemble Deep Learning](https://mlsanity.com/paper/1907.00350/) (2019)
- [A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines](https://mlsanity.com/paper/1801.01586/) (2018)
- [Stacked Autoencoder Based Deep Random Vector Functional Link Neural Network for Classification](https://mlsanity.com/paper/1910.01858/) (2019)
- [Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM](https://mlsanity.com/paper/1812.01967/) (2018)
- [Sparse Regularization: Convergence Of Iterative Jumping Thresholding Algorithm](https://mlsanity.com/paper/1402.5744/) (2014)

## Abstract (arXiv)

Most multilayer least squares (LS)-based neural networks are structured with two separate stages: unsupervised feature encoding and supervised pattern classification. Once the unsupervised learning is finished, the latent encoding would be fixed without supervised fine-tuning. However, in complex tasks such as handling the ImageNet dataset, there are often many more clues that can be directly encoded, while the unsupervised learning, by definition cannot know exactly what is useful for a certain task. This serves as the motivation to retrain the latent space representations to learn some clues that unsupervised learning has not yet learned. In particular, the error matrix from the output layer is pulled back to each hidden layer, and the parameters of the hidden layer are recalculated with Moore-Penrose (MP) inverse for more generalized representations. In this paper, a recomputation-based multilayer network using MP inverse (RML-MP) is developed. A sparse RML-MP (SRML-MP) model to boost the performance of RML-MP is then proposed. The experimental results with varying training samples (from 3 K to 1.8 M) show that the proposed models provide better generalization performance than most representation learning algorithms.