DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture
Alok K. Sharma, Edwin Vans, Daichi Shigemizu, Keith A. Boroevich, Tatsuhiko Tsunoda · 2019
Read DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture by Alok K. Sharma, Edwin Vans, Daichi Shigemizu, Keith A. Boroevich, Tatsuhiko Tsunoda (2019) 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-w2964962196.txt.
Description
Alok Sharma, Edwin Vans, Daichi Shigemizu, and colleagues published this methods paper in Scientific Reports in 2019. It presents DeepInsight, a way to turn data that are not images into images. The converted images can then be fed to convolutional neural networks, the models that excel at picture analysis.
The method matters because small, telling differences in genomic and other data are hard to spot directly. Image-based networks pull out features on their own, with no extra extraction step. They can also catch complex patterns and hidden correlations in data. By reshaping raw values into pictures, DeepInsight lets deep networks work on data far beyond photos. The authors offer it as a general tool for data science.
Catalog record
| CREATOR | Alok K. Sharma, Edwin Vans, Daichi Shigemizu, Keith A. Boroevich, Tatsuhiko Tsunoda |
|---|---|
| YEAR | 2019 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | OpenAlex / Scientific Reports |