Knowledge Extracted from Recurrent Deep Belief Network for Real Time Deterministic Control
This addresses the problem of reducing computational costs for real-time deterministic control in industries using IoT data, but it is incremental as it builds on existing knowledge extraction methods.
The authors tackled the trade-off between high precision in deep learning and the high cost of GPU implementation by extracting IF-THEN rules from a trained recurrent deep belief network to enable faster inference. Their experiments on benchmark time series datasets demonstrated effectiveness in improving computational speed.
Recently, the market on deep learning including not only software but also hardware is developing rapidly. Big data is collected through IoT devices and the industry world will analyze them to improve their manufacturing process. Deep Learning has the hierarchical network architecture to represent the complicated features of input patterns. Although deep learning can show the high capability of classification, prediction, and so on, the implementation on GPU devices are required. We may meet the trade-off between the higher precision by deep learning and the higher cost with GPU devices. We can success the knowledge extraction from the trained deep learning with high classification capability. The knowledge that can realize faster inference of pre-trained deep network is extracted as IF-THEN rules from the network signal flow given input data. Some experiment results with benchmark tests for time series data sets showed the effectiveness of our proposed method related to the computational speed.