Research Communication | Open Access
Volume 2021 | Communication ID 262
Volume 2021 | Communication ID 262
| Neural networks hyperparameters extrapolation |
Hassane Allouche, Khalid Tigma
Received |
Accepted |
Published |
January 31, 2021 |
February 15, 2021 |
March 15, 2021 |
Abstract: Machine learning requires large volumes of both data and the outcome associated with this data. Preparing these inputs can be expensive and becomes an entry ticket allowing only the largest organizations with access to large volumes of data and with large budgets to take advantage of machine learning. In this work, we try to build a more efficient method aimed at obtaining the maximum results from the limited data available, and we aim, using smaller input data volumes, to achieve an accuracy comparable to existing methods requiring larger volumes. The idea is to use the available data to ...