Modeling of Pruning Techniques for Deep Neural Networks Simplification
This work addresses the problem of computational complexity and parameter reduction in CNNs for researchers and practitioners, but it appears incremental as it models existing methods rather than introducing new ones.
The paper tackles the lack of a unifying framework for pruning techniques in deep neural networks by proposing a general model that encompasses most methods, aiming to identify their advantages and disadvantages for simplification.
Convolutional Neural Networks (CNNs) suffer from different issues, such as computational complexity and the number of parameters. In recent years pruning techniques are employed to reduce the number of operations and model size in CNNs. Different pruning methods are proposed, which are based on pruning the connections, channels, and filters. Various techniques and tricks accompany pruning methods, and there is not a unifying framework to model all the pruning methods. In this paper pruning methods are investigated, and a general model which is contained the majority of pruning techniques is proposed. The advantages and disadvantages of the pruning methods can be identified, and all of them can be summarized under this model. The final goal of this model is to provide a general approach for all of the pruning methods with different structures and applications.