19 Commits

Author	SHA1	Message	Date
julienChemillier	1bd92074ab	Back to multiple bias implementation	2023-03-18 13:25:58 +01:00
julienChemillier	2a88621c34	Change bias implementation to fix keras's one	2023-03-12 11:13:26 +01:00
julienChemillier	89402b9ee6	Replace numbers by defines	2023-03-08 20:48:34 +01:00
augustin64	7f88acf17f	Add float clip(float) to update.c	2023-03-02 10:35:25 +01:00
augustin64	c45b21e322	Rename MAX_RESEAU to CLIP_VALUE	2023-03-01 19:12:57 +01:00
julienChemillier	1d462576a9	Change 'input_size' to 'size_input'	2023-02-19 13:43:09 +01:00
julienChemillier	c13772c291	Change 'w' and 'd_w' to 'weights' and 'd_weights'	2023-02-19 13:38:33 +01:00
augustin64	220d0a71be	Update backpropagation (It works now)	2023-01-25 11:18:47 +01:00
augustin64	5f47b93672	Add loss computation	2023-01-20 13:41:38 +01:00
augustin64	cea4132e2d	Remove white spaces	2023-01-17 15:34:29 +01:00
augustin64	c78c8a0ade	Update linearisation detection	2023-01-17 12:49:35 +01:00
augustin64	963a4afcff	Add cnn knuth shuffle	2022-12-07 10:44:28 +01:00
augustin64	5a0f807a00	Update update.c	2022-11-18 14:09:49 +01:00
julienChemillier	50af676027	Learning_rate is a (NON NULL) float	2022-11-15 18:15:18 +01:00
julienChemillier	f5f22c6b3e	Fix issues	2022-11-15 12:58:00 +01:00
julienChemillier	d94f61bb77	First results in backprop ?	2022-11-15 12:50:38 +01:00
julienChemillier	682715d5d7	Add learning_rate missing	2022-11-04 11:31:34 +01:00
augustin64	4637d62e73	Update backpropagation.c	2022-11-03 18:13:01 +01:00
julienChemillier	0e317549a5	Creation of update (.h and .c)	2022-11-03 16:28:03 +01:00