.png){kind=icon}
返回
Training generalizable quantized deep neural nets
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2022.118736.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
While a number of practical methods for training quantized DL models have been presented in the literature, there exists a critical gap in the theoretical generalizability results for such approaches. Although empirical evidence often suggests a high tolerance of DL architectures to variations of training procedures, existing theoretical generalization analyses are often contingent on the specific designs of training algorithms, e.g., in stochastic gradient descent (SGD). This specialization makes such generalizability results inapplicable to the case of quantized DL models. In view of this critical vacuum, this paper provides several almost -algorithm-independent results to ensure the generalizability of a quantized neural network at different levels of optimality. These results include the characterizations of a computable, quantized local solution that ensures the generalization performance and an algorithm that is provably convergent to such a local solution.
Keyword:
Deep learning
Deep learning Quantized neural networks
Generalizability
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
分享收藏分享收藏Graphene/Ionic Liquid Binary Electrode Material for High Performance Supercapacitor用于高性能超级电容器的石墨烯/离子液体二元电极材料
PREAI
分享收藏Optimal approximation of piecewise smooth functions using deep ReLU neural networks.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏The integrated methodology of rough set theory and artificial neural network for business failure prediction粗糙集理论与人工神经网络相结合的企业失败预测方法
PREAI
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
查看更多内容