gavindiaz/QuanTAlib
1
0
Fork 0
mirror of https://github.com/mihakralj/QuanTAlib.git synced 2026-08-23 04:58:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

v0.8.6: update indicator docs, ndepend tooling, ALMA refactor, gitignore cleanup

Browse Source
This commit is contained in:
Miha Kralj
2026-03-13 13:46:52 -07:00
parent e3e9555fc1
commit c75135ab14
402 changed files with 2222 additions and 1779 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/numerics/relu/Relu.md
+1 -3
View File
@@ -14,8 +14,6 @@
- The Rectified Linear Unit (ReLU) activation function applies `max(0, x)` to each value, passing positive inputs unchanged while zeroing negative ones.
- No configurable parameters; computation is stateless per bar.
- Output range: Varies (see docs).
- Requires `0` bars of warmup before first valid output (IsHot = true).
- Validated against TA-Lib, Skender, and Tulip reference implementations where available.
The Rectified Linear Unit (ReLU) activation function applies `max(0, x)` to each value, passing positive inputs unchanged while zeroing negative ones. Its simplicity belies its importance: ReLU enabled the training of deep neural networks by mitigating vanishing gradients, and its computational efficiency makes it the default activation for most architectures.
@@ -183,4 +181,4 @@ Relu.Calculate(source.AsSpan(), output.AsSpan());
- Nair, V. & Hinton, G. (2010). "Rectified Linear Units Improve Restricted Boltzmann Machines." *ICML*.
- Glorot, X., Bordes, A., & Bengio, Y. (2011). "Deep Sparse Rectifier Neural Networks." *AISTATS*.
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). *Deep Learning*. MIT Press.
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). *Deep Learning*. MIT Press.