Proactive Minimization of Convolutional Networks
|Title||Proactive Minimization of Convolutional Networks|
|Publication Type||Conference Paper|
|Year of Publication||2019|
|Authors||Jenei B, Berend G, Varga L|
|Conference Name||2019 International Joint Conference on Neural Networks (IJCNN)|
|Keywords||automatic minimization, Automatic Scaling, Biological neural networks, convolutional kernels, Convolutional Networks, convolutional neural nets, convolutional neural networks, Deep Learning, Image edge detection, Kernel, minimisation, Minimization, Neurons, proactive minimization, Task analysis, Training|
Optimizing the performance of convolutional neural networks (CNNs) in real applications (i.e., production programs) is crucial. The desired network can perform a task while having minimal evaluation time and resource requirement. The evaluation time of a network strongly depends on the number of layers and the number of convolutional kernels in each layers. Therefore, by minimizing the network while keeping its accuracy high is a frequent task. In this paper, we present variations of a method for the automatic minimization of convolutional networks. Our method minimizes the neural network by omitting convolutional kernels during the training process, while also keeping the quality of the results high.