Parsimonious Inference On Convolutional Neural Networks Learning And Applying Online Kernel Activation Rules
ASecurity**arXiv ID:** 1701.05221 **Authors:** I. Theodorakopoulos, V. Pothos, D. Kastaniotis, N. Fragoulis **Published:** 2017-01-18T20:03:12Z **Abstract:** A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic intervention on both the CNN architecture and the training procedure, which targets to the parsimonious inference by learning to exploit or remove the redundant capacity of a...
- 3 stars
- 0 votes
- 0 copies
- 2 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill parsimonious-inference-on-convolutional-neural-networks-learning-and-applying-online-kernel-activation-rules --agent claude-codeAre you the author of Parsimonious Inference On Convolutional Neural Networks Learning And Applying Online Kernel Activation Rules?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-parsimonious-inference-on-convolutional-neural-net)# Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules
**arXiv ID:** 1701.05221
**Authors:** I. Theodorakopoulos, V. Pothos, D. Kastaniotis, N. Fragoulis
**Published:** 2017-01-18T20:03:12Z
**Abstract:**
A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic intervention on both the CNN architecture and the training procedure, which targets to the parsimonious inference by learning to exploit or remove the redundant capacity of a CNN architecture. This is accomplished, by the introduction of a new structural element that can be inserted as an add-on to any contemporary CNN architecture, whilst preserving or even improving its recognition accuracy. Our approach formulates a systematic and data-driven method for developing CNNs that are trained to eventually change size and form in real-time during inference, targeting to the smaller possible computational footprint. Results are provided for the optimal implementation on a few modern, high-end mobile computing platforms indicating a significant speed-up of up to x3 times.
## Skill Description
This skill is generated from the arXiv paper: Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules (1701.05221).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1701.05221](http://arxiv.org/abs/1701.05221v5)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.