Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Approaching Metaheuristic Deep Learning Combos for Automated Data Mining

Gustavo Assunção, Paulo Menezes

TL;DR

This work proposes a means of combining meta-heuristic methods with conventional classifiers and neural networks in order to perform automated data mining and empirically observed that using a ground truth labeled dataset's validation accuracy is inadequate for correcting labels of other previously unseen data instances.

Abstract

Lack of data on which to perform experimentation is a recurring issue in many areas of research, particularly in machine learning. The inability of most automated data mining techniques to be generalized to all types of data is inherently related with their dependency on those types which deems them ineffective against anything slightly different. Meta-heuristics are algorithms which attempt to optimize some solution independently of the type of data used, whilst classifiers or neural networks focus on feature extrapolation and dimensionality reduction to fit some model onto data arranged in a particular way. These two algorithmic fields encompass a group of characteristics which when combined are seemingly capable of achieving data mining regardless of how it is arranged. To this end, this work proposes a means of combining meta-heuristic methods with conventional classifiers and neural networks in order to perform automated data mining. Experiments on the MNIST dataset for handwritten digit recognition were performed and it was empirically observed that using a ground truth labeled dataset's validation accuracy is inadequate for correcting labels of other previously unseen data instances.

Approaching Metaheuristic Deep Learning Combos for Automated Data Mining

TL;DR

This work proposes a means of combining meta-heuristic methods with conventional classifiers and neural networks in order to perform automated data mining and empirically observed that using a ground truth labeled dataset's validation accuracy is inadequate for correcting labels of other previously unseen data instances.

Abstract

Lack of data on which to perform experimentation is a recurring issue in many areas of research, particularly in machine learning. The inability of most automated data mining techniques to be generalized to all types of data is inherently related with their dependency on those types which deems them ineffective against anything slightly different. Meta-heuristics are algorithms which attempt to optimize some solution independently of the type of data used, whilst classifiers or neural networks focus on feature extrapolation and dimensionality reduction to fit some model onto data arranged in a particular way. These two algorithmic fields encompass a group of characteristics which when combined are seemingly capable of achieving data mining regardless of how it is arranged. To this end, this work proposes a means of combining meta-heuristic methods with conventional classifiers and neural networks in order to perform automated data mining. Experiments on the MNIST dataset for handwritten digit recognition were performed and it was empirically observed that using a ground truth labeled dataset's validation accuracy is inadequate for correcting labels of other previously unseen data instances.

Paper Structure

This paper contains 14 sections, 1 equation, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. Automated Data Mining
  4. Heuristic ANN Coupling
  5. Methodology
  6. Artificial Neural Networks
  7. Genetic Algorithms
  8. Simulated Annealing
  9. Proposed Coupling
  10. Experiments
  11. GA Method
  12. SA Method
  13. Discussion
  14. Conclusions

Figures (3)

  • Figure 1: Flow diagram of standard genetic algorithmics (right), in parallel with the explanation of each step's specific functioning in our GA-ANN framework.
  • Figure 2: Flow diagram of the proposed Simulated Annealing technique.
  • Figure 3: Examples for the labeling code vector format (left), used for testing with the MNIST dataset, as well as for the recombination and mutation methods (right), respectively performed as half-way merging and gene order inversion applied to the labelling codes.