Neural architecture search using network embedding and generative adversarial networks
Morteza Yousefi, Vahid Mehrdad, Mohammad Bagher Dowlatshahi · 2025
Read Neural architecture search using network embedding and generative adversarial networks by Morteza Yousefi, Vahid Mehrdad, Mohammad Bagher Dowlatshahi (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12775394.txt.
Description
Morteza Yousefi, Vahid Mehrdad, and Mohammad Bagher Dowlatshahi work on faster search for good neural network designs. Their 2025 paper uses helper models that guess how a design will score. Training each design from scratch is slow, but helper models need many labeled cases. Gathering those cases takes much time.
Their method first maps each design into a space where alike designs sit close together. A pair of rival networks then makes extra training cases to bolster the helper model. That cuts the need for real tests. On two standard search sets, the helper did as well or better with the mapping. The full method beat top search methods the authors compared.
Catalog record
| CREATOR | Morteza Yousefi, Vahid Mehrdad, Mohammad Bagher Dowlatshahi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 114 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |