Finding a single informative bit in a sea of noise

versión (3.75 KB) por Brett Shoelson
Detect a single informative bit in a sea of noise, using deep learning

50 descargas

Actualizada 10 Jan 2019

Ver licencia

Generate random matrices of a user-specified size, and in a single location set a pixel to true in half of them, and false in the other half. Quickly train a convolutional neural network to classify the matrices ('class' 1 vs 'class 2'). Then use a deep dream image to find the location of the single informative bit.
This is a very simple but powerful example. "Traditional" machine learning algorithms fail (a long, slow failure). The CNN converges quickly! The binary matrices can be rectangular, or they can be vectors. The data could represent almost anything...a single nucleotide variant in aligned genomes, a fraudulent transaction in a ledger, ....

Citar como

Brett Shoelson (2022). Finding a single informative bit in a sea of noise (, MATLAB Central File Exchange. Recuperado .

Compatibilidad con la versión de MATLAB
Se creó con R2018a
Compatible con cualquier versión
Compatibilidad con las plataformas
Windows macOS Linux
Etiquetas Añadir etiquetas

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!