.png){kind=icon}
返回
Conditional Information Gain Trellis
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2024.06.018.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Conditional computing processes an input using only part of the neural network's computational units. Learning to execute parts of a deep convolutional network by routing individual samples has several advantages: This can facilitate the interpretability of the model, reduce the model complexity, and reduce the computational burden during training and inference. Furthermore, if similar classes are routed to the same path, that part of the network learns to discriminate between finer differences and better classification accuracies can be attained with fewer parameters. Recently, several papers have exploited this idea to select a particular child of a node in a tree-shaped network or to skip parts of a network. In this work, we follow a Trellis-based approach for generating specific execution paths in a deep convolutional neural network. We have designed routing mechanisms that use differentiable information gain-based cost functions to determine which subset of features in a convolutional layer will be executed. We call our method Conditional Information Gain Trellis (CIGT). We show that our conditional execution mechanism achieves comparable or better model performance compared to unconditional baselines, using only a fraction of the computational resources. We provide our code and model checkpoints used in the paper at: https://github.com/ufukcbicici/cigt/tree/prl/prl_scripts.
Keyword:
Machine learning
Deep learning
Conditional deep learning
期刊
IF:
3.3
论文数:
7.9K
被引数:
1.6W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏Interpretable machine learning: Fundamental principles and 10 grand challenges可解释的机器学习: 基本原则和十大挑战.png)
STATISTICS SURVEYS
OAAI
STATISTICS SURVEYSIF15.4
OAAI分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容