This repository contains a Jupyter notebook that demonstrates a simple regression task using Tensorflow. Two different models are compared: a standard Fully Connected Neural Network (FCN) and an FCN with a custom activation function called "Adaptive Activation." The models are trained and evaluated using TensorFlow.
To use the Adaptive Activation Layer in your own projects, you can simply copy and paste the code provided above into your TensorFlow codebase. You can then create instances of the AdaptiveActivation layer within your neural network architectures.
The following Python libraries are used in this project:
- tensorFlow
- keras
- scikit-learn
- jupyter Notebook
- matplotlib
- pandas
You can install these dependencies using pip:
pip install tensorflow keras scikit-learn matplotlib pandas jupyter
This project is licensed under the MIT License. See the LICENSE file for details.
Feel free to explore the notebook and the Adaptive Activation Layer code to gain insights into how these models perform on a regression task.