What question did this study set out to answer?

The central aim is to create more efficient convolutional neural networks by reducing parameters and computation while maintaining accuracy.

July 1, 2017Open Access

Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved CNN efficiency in model architectures, suggesting better performance for computational tasks.

The central aim is to create more efficient convolutional neural networks by reducing parameters and computation while maintaining accuracy.
Developed a novel sparse connection structure resembling a tree root.
Trained efficient variants of state-of-the-art CNN models.
Evaluated performance on CIFAR10 and ILSVRC datasets.
For ResNet 50, achieved 40% fewer parameters, 45% fewer floating point operations, and was 31% faster on CPU.
For ResNet 200, achieved 48% fewer parameters, 27% fewer floating point operations, maintaining accuracy.
For GoogLeNet, achieved 7% fewer parameters and was 21% faster on CPU.

Ioannou et al. (2017) studied this question.

View Full Paper

Ask AI

Bookmark