Bausager
be2c193341
Next steps
...
Next up is dropout layers. remember that it can be used to see uncerstaty in multiply output, which is not in the book
2026-05-16 21:36:19 +02:00
Bausager
eb2374eaf5
Backpass on reg
...
Made backpass on regulariaztion and made it easy to see in main.cpp
2026-05-16 21:34:34 +02:00
Bausager
d2fe8aa65c
Fittet new functions to everying in neural networks. Still need to optimise for uint64_t vs int64_t and vec vs mat in some places.
2026-05-16 20:37:05 +02:00
Bausager
412a854c65
Update .gitea/workflows/sync-public.ymldisable
...
Disable automatic sunc
2026-04-26 13:29:16 +02:00
Bausager
20859844a0
Update .gitea/workflows/openbuild-keep.txtdisabled
...
Sync public mirror / sync (push) Has been cancelled
Disable automaticly update
2026-04-26 13:28:25 +02:00
Bausager
6b8a7ab582
refactor
...
Sync public mirror / sync (push) Failing after 29s
almost complete. Need to doublecheck names for functions in *_serial.h
2026-01-18 17:51:05 +01:00
Bausager
9709949a5b
Refactor progress
...
Sync public mirror / sync (push) Failing after 27s
Next step is ramdom and equal. I also need to have a look at add and the serial naming of the functions.
2026-01-13 20:07:27 +01:00
Bausager
48f329feef
Regulaization
...
Sync public mirror / sync (push) Failing after 27s
Started on regulaization in Loss.h. I need to refactor the matsum.h since I need a total sum over the matrix. Also matmul needs a elementwise matmul function, which is the next this in the ragulaization
2026-01-03 22:10:50 +01:00
Bausager
32ba0518fa
run.sh
...
Sync public mirror / sync (push) Failing after 27s
CMake stores the absolute folder path, this now get deleted in run.sh, so it can be called on deffrent computers without problems
2026-01-02 19:34:37 +01:00
Bausager
e5f8c91be4
Optimizers - Part 1
...
Sync public mirror / sync (push) Failing after 24s
Done with SGD and Adagrad, still need to optimize them but they work.
2026-01-01 19:23:48 +01:00
Bausager
bd2edea8ef
p.238 in NNFS
Sync public mirror / sync (push) Failing after 24s
2025-12-23 14:47:40 +01:00
Bausager
22d6ea5fad
Backwards Pass
...
Sync public mirror / sync (push) Successful in 26s
Activation Softmax with CategoricalCrossentrophy is almost done from page. 234
2025-10-20 14:23:36 +02:00
Bausager
7fe6be9ba7
Backwards - ReLU & Dense Lasyer
...
Sync public mirror / sync (push) Successful in 27s
Made the backwards for dense layers and ReLU, but I think I soon need to refactor some code to make it all steamlined.
2025-10-09 10:43:45 +02:00
Bausager
c164d790db
NNFS p.135
...
Sync public mirror / sync (push) Successful in 37s
Started on the iteration, not need to rewrite matadd.h and need to make matrandom.h.
2025-10-07 19:06:33 +02:00
Bausager
66b3a4ee6b
CatagoricalCrossentrophy
...
Sync public mirror / sync (push) Successful in 27s
Fixed the loss functions for categories and is ready for accuracy calculation on page 129
2025-10-07 13:09:25 +02:00
Bausager
8e70310760
Testing openbuild-keep.txt file with include folder
Sync public mirror / sync (push) Successful in 40s
2025-10-06 22:21:09 +02:00
Bausager
1c6080d32c
Testing openbuild-keep.txt file with include folder
Sync public mirror / sync (push) Successful in 38s
2025-10-06 22:13:43 +02:00
Bausager
9ae603bfc9
Testing openbuild-keep.txt file with include folder
2025-10-06 22:12:42 +02:00
Bausager
f341d80dec
Testing openbuild-keep.txt file with include folder
Sync public mirror / sync (push) Successful in 35s
2025-10-06 22:01:49 +02:00
Bausager
b528403ec8
Fixed Flux openbuild name
Sync public mirror / sync (push) Successful in 33s
2025-10-06 21:59:42 +02:00
Bausager
9c70ab0966
Update .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Successful in 1m15s
2025-10-06 21:44:43 +02:00
Bausager
25b8024bf5
Update .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Successful in 1m1s
2025-10-06 21:35:14 +02:00
Bausager
83e30d2c3d
Update .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Failing after 1m0s
2025-10-06 21:31:38 +02:00
Bausager
c063188bc4
Update .gitea/workflows/sync-public.yml
2025-10-06 21:30:04 +02:00
Bausager
ae8799c7db
Add .gitea/workflows/oss-keep.txt
Sync public mirror / sync (push) Has been cancelled
2025-10-06 21:29:10 +02:00
Bausager
6a01b0afe5
Update .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Successful in 1m1s
2025-10-06 21:15:34 +02:00
Bausager
ab76cbbe0f
Update .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Failing after 42s
2025-10-06 21:12:46 +02:00
Bausager
bbd72e63d1
Update .gitea/workflows/sync-public.yml
Diagnose SSH to Flux-oss / diag (push) Successful in 27s
2025-10-06 21:06:02 +02:00
Bausager
134f8cb363
Test on private repo
Sync public mirror / sync (push) Successful in 1m7s
2025-10-06 20:52:19 +02:00
Bausager
a99fa268ea
Add .gitea/workflows/sync-public.yml
Sync public mirror / sync (push) Has been cancelled
2025-10-06 20:48:07 +02:00
Bausager
6cdc6b996f
Update README.md
2025-10-05 21:29:17 +02:00
Bausager
76978619a2
Upload files to "assets/logo"
2025-10-05 21:28:51 +02:00
Bausager
2f5b27b573
Update README.md
2025-10-05 21:21:01 +02:00
Bausager
02d5ac670d
Update README.md
2025-10-05 21:14:43 +02:00
Bausager
d1e94a193f
Update README.md
2025-10-05 21:13:23 +02:00
Bausager
3ef78fc733
Update README.md
2025-10-05 21:12:49 +02:00
Bausager
15918c0bb7
Update README.md
2025-10-05 21:11:13 +02:00
Bausager
8bef524d81
Update README.md
2025-10-05 21:10:12 +02:00
Bausager
47001acff2
Update README.md
2025-10-05 20:48:46 +02:00
Bausager
2f2962519c
Logo fix
2025-10-05 20:48:15 +02:00
Bausager
6ae8fa306f
Logo
2025-10-05 20:46:51 +02:00
Bausager
ea359f3b09
Started Loss, done softmax, up to p.125
...
I've implemented alot of support functions that needs to be refactored, optimised and tested; mean.h, exponential.h, matdiv.h matsum.h matsubtract.h. Maybe we need to have a look at if matdiv/matmul should be in the same. Same with matadd/matsubtract and if some of it should be in matvec.h.
2025-10-05 19:47:56 +02:00
Bausager
1b59713565
Test from laptop/atlas
2025-10-03 22:20:16 +02:00
Bausager
88227a38fc
Neural Network
...
Started on implementing neural network from NNFS. I've done ReLU and stopped at p.104. Softmax is not ready.
2025-10-03 20:54:37 +02:00
Bausager
a86410fda7
diffusion.h
...
I'm done with the backbone of it, I haven't had feedback on it.
2025-09-29 20:54:06 +02:00
Bausager
99e0f3fda4
Frist push from Desktop Newton
...
Created diffusion1d.h in fluids
2025-09-29 15:03:49 +02:00
Bausager
513f071748
Ready for fvm steady case
2025-09-21 20:57:02 +02:00
Bausager
3a53b6ebf7
interpolation1d
...
done single-threded 1d interpolations; linear, rational, cubic spline, polynomial and barycentric. Still not done test functions yet. Still missing multi-core options.
2025-09-18 20:18:27 +02:00
Bausager
92437e5ef1
LU and LU inverse is done
2025-09-14 18:35:37 +02:00
Bausager
88087ea6a6
Finishing up and starting lu decomp
2025-09-13 21:44:20 +02:00
Bausager