Understanding Geometry of Encoder-Decoder CNNs
Authors: Jong Chul Ye, Woon Kyoung Sung
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Inspired by recent theoretical understanding on generalizability, expressivity and optimization landscape of neural networks, as well as the theory of deep convolutional framelets, here we provide a uniļ¬ed theoretical framework that leads to a better understanding of geometry of encoder-decoder CNNs. |
| Researcher Affiliation | Academia | Jong Chul Ye 1 2 Woon Kyoung Sung 2 1Dept. of Bio/Brain Engineering, KAIST Daejeon 34141, Republic of Korea. 2Dept. of Mathematical Sciences, KAIST, Daejeon 34141, Republic of Korea. |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found. The paper contains mathematical definitions and descriptions of network components but no formal pseudocode or algorithm listings. |
| Open Source Code | No | No statement providing concrete access to source code for the methodology was found. The paper is purely theoretical and does not present a new implemented methodology requiring code release. |
| Open Datasets | No | No concrete access information for a publicly available or open dataset was provided. The paper is theoretical and discusses properties related to training data in abstract terms, but does not use or provide access to any specific dataset. |
| Dataset Splits | No | No specific dataset split information for training, validation, or test sets was found. The paper is theoretical and does not conduct experiments involving data partitioning. |
| Hardware Specification | No | No specific hardware details used for running experiments were found. The paper is theoretical and does not describe any computational experiments that would require hardware specifications. |
| Software Dependencies | No | No specific ancillary software details with version numbers were found. The paper is theoretical and does not describe any software implementation details for reproducibility. |
| Experiment Setup | No | No specific experimental setup details, hyperparameters, or training configurations were found. The paper is purely theoretical and does not include an experimental setup section. |