Skip to content

Releases: GiorgosXou/NeuralNetworks

🕸️ NeuralNetworks

15 Mar 03:55
Compare
Choose a tag to compare

Note

I want to really thanks @ripred for his kind and honest words, especially for "... You did a great job on this and should be proud.". But also, I want to thanks Ivo Ljubičić for using my library in his ✨ master thesis named "Artificial skin concept for human-robot physical interaction". And last but not least @pjurczen for giving me the spark I needed when he said "... I'd love to see this feature added!".

(Additionally: Note that all feature are compatible with almost all optimization use cases)

Donate

🕸️ NeuralNetworks

21 Nov 23:31
Compare
Choose a tag to compare
  • Added support for:
    • Internal EEPROM, SD
    • 8-byte double precision
    • Custom activation functions
    • Basic ESP32-S3 SIMD instructions
  • Fixed:
    • Multiple #define - compiler warnings
    • Many issues related to ESP32 compilation

Note

Special thanks to the "National Institute of Telecommunications Research and Training- National University of Engineering, Perú" for using and referencing my library into their beautiful article


Donate

Simple MLP - NeuralNetwork Library

13 Aug 08:51
Compare
Choose a tag to compare

Simple MLP - NeuralNetwork Library

25 Feb 21:58
4d95303
Compare
Choose a tag to compare
  • Crucial fix for back-propagation with "multiple activation functions".
  • Support for "multiple activation function" use without defining Functions.
  • Fixed const pointer ISSUE .
  • Minor fixes.

Simple MLP - NeuralNetwork Library

30 Jan 12:50
Compare
Choose a tag to compare

Support for:

  • More Activation Functions.
  • Activation Functions Per Layer.
  • Optimizations based on user's Preference.

Simple MLP - NeuralNetwork Library

15 Dec 21:28
0821ed8
Compare
Choose a tag to compare

Simple MLP - NeuralNetwork Library

19 May 20:48
7c068b7
Compare
Choose a tag to compare
  • Optimazed Algorithm For Less SRAM Usage.
  • Only Sigmoid Activation Function.
  • Use of PROGMEM.