Deep learning modelling techniques: current progress, applications, advantages, and challenges
Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela Rozbu, Taoseef Ishtiak, Nazifa Rafa, M. Mofijur, A. B. M. Shawkat Ali, Amir H. Gandomi · 2023
Read Deep learning modelling techniques: current progress, applications, advantages, and challenges by Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela Rozbu, Taoseef Ishtiak, Nazifa Rafa, M. Mofijur, A. B. M. Shawkat Ali, Amir H. Gandomi (2023) 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/openalex-w4366091323.txt.
Description
Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, and colleagues review deep learning modelling in Artificial Intelligence Review in 2023. Deep learning teaches computers to find patterns by passing data through many layers of transformation. It has produced striking results in health care, education, security, and industry. Yet surveys covering the whole field's designs remain surprisingly few, the authors note.
Their review compares the main model families, how each is trained, and where each works best. Many models excel only in narrow domains, they find. Training can be slow and costly and demands huge datasets for accuracy. Models can also be fooled, misclassify, or settle into poor solutions. The authors map these strengths and weaknesses to guide builders toward sturdier designs.
Catalog record
| CREATOR | Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela Rozbu, Taoseef Ishtiak, Nazifa Rafa, M. Mofijur, A. B. M. Shawkat Ali, Amir H. Gandomi |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 302 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | OpenAlex / Artificial Intelligence Review |