On tuning deep learning models: a data mining perspective

by   M. M. Ozturk, et al.

Deep learning algorithms vary depending on the underlying connection mechanism of nodes of them. They have various hyperparameters that are either set via specific algorithms or randomly chosen. Meanwhile, hyperparameters of deep learning algorithms have the potential to help enhance the performance of the machine learning tasks. In this paper, a tuning guideline is provided for researchers who cope with issues originated from hyperparameters of deep learning models. To that end, four types of deep learning algorithms are investigated in terms of tuning and data mining perspective. Further, common search methods of hyperparameters are evaluated on four deep learning algorithms. Normalization helps increase the performance of classification, according to the results of this study. The number of features has not contributed to the decline in the accuracy of deep learning algorithms. Even though high sparsity results in low accuracy, a uniform distribution is much more crucial to reach reliable results in terms of data mining.


page 1

page 2

page 3

page 4


Experimental Investigation and Evaluation of Model-based Hyperparameter Optimization

Machine learning algorithms such as random forests or xgboost are gainin...

Learning Models for Query by Vocal Percussion: A Comparative Study

The imitation of percussive sounds via the human voice is a natural and ...

Reliable BOF endpoint prediction by novel data-driven modeling

In a cooperative effort between SMS Siemag AG (SMS), AG der Dillinger Hü...

Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences

We propose a deep supervised learning algorithm based on low-discrepancy...

Deep Learning with Apache SystemML

Enterprises operate large data lakes using Hadoop and Spark frameworks t...

AEFE: Automatic Embedded Feature Engineering for Categorical Features

The challenge of solving data mining problems in e-commerce applications...

Self-configuration from a Machine-Learning Perspective

The goal of machine learning is to provide solutions which are trained b...

Please sign up or login with your details

Forgot password? Click here to reset