Effective Network Compression Using Simulation-Guided Iterative Pruning
This work addresses the challenge of deploying deep learning in constrained environments, but it appears incremental as it builds on existing iterative pruning techniques.
The paper tackles the problem of embedding deep learning models into resource-limited systems by proposing a simulation-guided iterative pruning method for network compression, achieving higher performance than existing methods at the same pruning level.
Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network compression as a method to solve this limitation. The principle of this idea is to make iterative pruning more effective and sophisticated by simulating the reduced network. A simple experiment was conducted to evaluate the method; the results showed that the proposed method achieved higher performance than existing methods at the same pruning level.