.png){kind=icon}
返回
Optimizing dense feed-forward neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.12.015.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning models have been widely used during the last decade due to their outstanding learning and abstraction capacities. However, one of the main challenges any scientist has to face using deep learning models is to establish the network's architecture. Due to this difficulty, data scientists usually build over complex models and, as a result, most of them result computationally intensive and impose a large memory footprint, generating huge costs, contributing to climate change and hindering their use in computational-limited devices. In this paper, we propose a novel dense feed-forward neural network constructing method based on pruning and transfer learning. Its performance has been thoroughly assessed in classification and regression problems. Without any accuracy loss, our approach can compress the number of parameters by more than 70%. Even further, choosing the pruning parameter carefully, most of the refined models outperform original ones. Furthermore, we have verified that our method not only identifies a better network architecture but also facilitates knowledge transfer between the original and refined models. The results obtained show that our constructing method not only helps in the design of more efficient models but also more effective ones.
Keyword:
Neural network pruning
Dense feed-forward neural network
optimization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Searching for exotic particles in high-energy physics with deep learning用深度学习寻找高能物理中的奇异粒子.png)
NATURE COMMUNICATIONS
NATURE COMMUNICATIONSIF15.7
PREAI
分享收藏分享收藏Ecological and genomic attributes of novel bacterial taxa that thrive in subsurface soil horizons
OAAI
IF0
OAAI分享收藏Defect-driven synthesis of self-assembled single crystal titanium nanowires via electrochemistry
PREAI
分享收藏
查看更多内容