Squeezed Very Deep Convolutional Neural Networks for Text Classification [article]

Andréa B. Duque, Luã Lázaro J. Santos, David Macêdo, Cleber Zanchettin
2019 arXiv   pre-print
Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance. In this paper, we evaluate the impact of Temporal Depthwise Separable Convolutions and Global
more » ... age Pooling in the network parameters, storage size, and latency. The squeezed model (SVDCNN) is between 10x and 20x smaller, depending on the network depth, maintaining a maximum size of 6MB. Regarding accuracy, the network experiences a loss between 0.4% and 1.3% and obtains lower latencies compared to the baseline model.
arXiv:1901.09821v1 fatcat:lxjx73xcfrfrhddesybv7i4dgm