Papers › TensorFlow based deep learning layer for Local Derivative Patterns
TensorFlow based deep learning layer for Local Derivative Patterns
Devrim Akgun
Deep learning architectures can extract features automatically via particular layers such as convolutions, recurrent networks, and pooling operations. In addition to the predefined layers in TensorFlow, developers can implement their custom layers based on the existing operators. This study presents a new library for using the Local Derivative Pattern (LDP) algorithm as a deep learning layer. The LDP layer has no trainable parameters and extracts the local patterns in four directions. The layer’s output provides the features to the following layers separately or combined. The developed library enables integrating LDP into any desired model that works with two-dimensional input data.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections