# Backward-Forward Algorithm: An Improvement towards Extreme Learning Machine

## TL;DR

This paper introduces a backward-forward algorithm that improves extreme learning machines by reducing the number of hidden nodes needed and decreasing training iterations through a Moore-Penrose approximation-based supervised learning method.

## Contribution

It presents a novel supervised learning approach using Moore-Penrose approximation to optimize input and output weights in fewer epochs, outperforming traditional extreme learning machines.

## Key findings

- Requires fewer hidden nodes for generalization.
- Reduces training iterations compared to back-propagation.
- Outperforms existing extreme learning machine methods.

## Abstract

The extreme learning machine needs a large number of hidden nodes to generalize a single hidden layer neural network for a given training data-set. The need for more number of hidden nodes suggests that the neural-network is memorizing rather than generalizing the model. Hence, a supervised learning method is described here that uses Moore-Penrose approximation to determine both input-weight and output-weight in two epochs, namely, backward-pass and forward-pass. The proposed technique has an advantage over the back-propagation method in terms of iterations required and is superior to the extreme learning machine in terms of the number of hidden units necessary for generalization.