articleJul 28, 2017GOLD OA

Deep Forest: Towards An Alternative to Deep Neural Networks

Novelis (Canada) · Nanjing University

Indexed incrossref

Abstract

In this paper, we propose gcForest, a decision tree ensemble approach with performance highly competitive to deep neural networks in a broad range of tasks. In contrast to deep neural networks which require great effort in hyper-parameter tuning, gcForest is much easier to train; even when it is applied to different data across different domains in our experiments, excellent performance can be achieved by almost same settings of hyper-parameters. The training process of gcForest is efficient, and users can control training cost according to computational resource available. The efficiency may be further enhanced because gcForest is naturally apt to parallel implementation. Furthermore, in contrast to deep…

Citation impact

896
total citations
FWCI
86.15
Percentile
100%
References
34
Citations per year

Authors

2

Topics & keywords

Keywords
  • Computer science
  • Artificial intelligence
  • Deep neural networks
  • Deep learning
  • Artificial neural network
  • Machine learning
  • Process (computing)
  • Contrast (vision)
No related works found for this paper.

Funding