Deep learning

Physics

Aerospace engineering

Meteorology

Operating system

Machine learning

Engineering

Artificial intelligence

Range (aeronautics)

Training (meteorology)

Contrast (vision)

Scale (ratio)

Computer science

Quantum mechanics

Process (computing)

Deep neural networks

Artificial neural network

Training set

Decision tree

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 neural networks which require large-scale training data, gcForest can work well even when there are only small-scale training data.

Deep Forest: Towards An Alternative to Deep Neural Networks