v0.4.1-alpha

Overhauled activation functions for efficiency and fixed certain bugs, removed tests since they needed to be reworked

v0.4.0-alpha

Release Notes - v0.4.0-alpha

The following activation functions are now supported:

1. ReLU (Rectified Linear Unit)

   • Parameters: negative_slope, max_value, threshold

2. Sigmoid

   • No additional parameters

3. Softmax

   • No additional parameters

4. Softplus

   • No additional parameters

5. Softsign

   • No additional parameters

6. Tanh (Hyperbolic Tangent)

   • No additional parameters

7. SELU (Scaled Exponential Linear Unit)

   • No additional parameters

8. ELU (Exponential Linear Unit)

   • Parameters: alpha

9. Exponential

   • No additional parameters

10. Leaky ReLU

    • Parameters: alpha

11. ReLU6

    • No additional parameters

12. SiLU (Sigmoid Linear Unit)

    • No additional parameters

13. Swish

    • No additional parameters

14. GELU (Gaussian Error Linear Unit)

    • Parameters: approximate

15. Hard Sigmoid

    • No additional parameters

16. Linear

    • No additional parameters

17. Mish

    • No additional parameters

18. Log Softmax

    • No additional parameters

Loss Functions

The release also includes various loss functions to cater to different optimization objectives:

1. Mean Squared Error (MSE)
2. Mean Absolute Error (MAE)
3. Mean Absolute Percentage Error (MAPE)
4. Mean Squared Logarithmic Error (MSLE)

v0.3.1-alpha

Fully completed activation layers, more information can be found here

v0.3.0-alpha

Rewrote activations and arithmetic functions to use generics, speedups on uses of alias, changes to Graph

v0.2.6-alpha

Tensor struct Rewritten for memory and speed efficiency, other small tweaks and bugfixes

v0.2.5-alpha

Finalized API for Dense and Conv layers, optimized training and sample data

v0.2.1-alpha

Fully added CNN example designed for MNIST dataset

v0.2.0-alpha

Very WIP versions of the following layers have been added

• Dense (Linear)
• Max Pool
• Dropout
• LeakyRelu
• Conv2D
• Flatten

v0.1.0-alpha

conv2 added