Data Selection in Neural Networks

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Data Selection in Neural Networks

Jonathas O. Ferreira; Marcele O. K. Mendonça; Paulo S. R. Diniz

In the era of big data, profitable opportunities are becoming available for many applications. As the amount of data keeps increasing, machine learning becomes an attractive tool to analyze the information acquired. However, harnessing meaningful data remains a challenge. The machine learning tools employed in many applications apply all training data without taking into consideration how relevant are some of them. In this paper, we propose a data selection strategy for the training step of Neural Networks to obtain the most significant data information and improve algorithm performance during training. The approach proposes a data-selection strategy applied to classification and regression problems leading to computational savings and classification error reduction. Based on open datasets, including a deep neural network case, the examples corroborate the effectiveness of the proposed approach.


Over the last few years, machine learning methods have witnessed growing popularity. The quantity of information generated in the world is soaring, raising the basic question if all data stored is useful. The current trend of creating data at an increasing rate is overwhelming the capacity to store, analyze, and make proper use of learning algorithms. In part, this phenomenon originates from the proliferation of sensors, human-computer interactions, internet of things, medical data, and machine-to-machine and mobile communications, to name a few data generators.

SPS on Twitter

  • The DEGAS Webinar Series continues on Thursday, 2 December when Dr. Michael Schaub presents "Signal processing on g…
  • Save 50% on IEEE Student Membership to the ultimate network for electrical engineering and computer science student…
  • SPS needs your support! is approaching. If our program receives 30 unique donations of US$10 or…
  • On 9 December, the IEEE SPS Sensor Array and Multichannel Technical Committee Webinar Series will feature a talk by…
  • The SPS Webinar Series continues on Friday, 10 December when Dr. Yu Liu presents "Image Fusion with Convolutional S…

SPS Videos

Signal Processing in Home Assistants


Multimedia Forensics

Careers in Signal Processing             


Under the Radar