Name
Abstract | ||
|---|---|---|
A comprehensive and comprehensible summary of existing deep neural networks (DNNs) helps practitioners understand the behaviour and evolution of DNNs, offers insights for architecture optimization, and sheds light on the working mechanisms of DNNs. However, this summary is hard to obtain because of the complexity and diversity of DNN architectures. To address this issue, we develop DNN Genealogy, an interactive visualization tool, to offer a visual summary of representative DNNs and their evolutionary relationships. DNN Genealogy enables users to learn DNNs from multiple aspects, including architecture, performance, and evolutionary relationships. Central to this tool is a systematic analysis and visualization of 66 representative DNNs based on our analysis of 140 papers. A directed acyclic graph is used to illustrate the evolutionary relationships among these DNNs and highlight the representative DNNs. A focus + context visualization is developed to orient users during their exploration. A set of network glyphs is used in the graph to facilitate the understanding and comparing of DNNs in the context of the evolution. Case studies demonstrate that DNN Genealogy provides helpful guidance in understanding, applying, and optimizing DNNs. DNN Genealogy is extensible and will continue to be updated to reflect future advances in DNNs. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/TVCG.2019.2921323 | IEEE Transactions on Visualization and Computer Graphics |
Keywords | DocType | Volume |
Visualization,Computer architecture,Tools,Neural networks,Interviews,Task analysis,Deep learning | Journal | 26 |
Issue | ISSN | Citations |
11 | 1077-2626 | 5 |
PageRank | References | Authors |
0.38 | 52 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qianwen Wang | 1 | 39 | 6.47 |
| Jun Yuan | 2 | 244 | 23.10 |
| Shuxin Chen | 3 | 10 | 5.02 |
| Hang Su | 4 | 448 | 47.57 |
| Huamin Qu | 5 | 2033 | 115.33 |
| Shixia Liu | 6 | 2095 | 82.41 |