Percptron-rohandhanraj 0.0.2

Its an Implementation of Percptron

Perceptron

Single Layer Perceptron(one Neuron)
A Perceptron is a simple model of a biological neuron that classifies the label of the input data based on various activation functions:

1. Binary Step Function: \begin{equation} f(x)=\begin{cases} 0, & \text{if $x<0$}.\ 1, & \text{otherwise}. \end{cases} \end{equation}

2. Signum Function: \begin{equation} f(x)=\begin{cases} -1, & \text{if $x<0$}.\ 0, & \text{if $x=0$>}\ 1, & \text{if $x>0$}. \end{cases} \end{equation}

3. Linear Activation Function: $$f(x) = x$$

4. Sigmoid / Logistic Activation Function: $$f(x) = \frac{1}{1+e^{-x}}$$

5. Tanh Function (Hyperbolic Tangent): $$f(x) = \frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}$$

6. ReLU Function: $$f(x) = max(0, x)$$

7. Exponential Linear Units (ELUs) Function: \begin{equation} f(x)=\begin{cases} x, & \text{if $x\geqslant0$}.\ \alpha(e^{x} - 1), & \text{otherwise}. \end{cases} \end{equation}

8. Swish: $$f(x) = \frac{x}{1 + e^{-x}}$$

9. Gaussian Error Linear Unit (GELU): $$f(x) = 0.5x(1 + tanh[\sqrt{2/\pi}(x + 0.044715x^3)])$$

fn_list = ['step', 'signum', 'linear', 'relu', 'sigmoid', 'tanh', 'elu', 'gelu', 'swish']

How to use this

from Perceptron.perceptron import Perceptron
from Perceptron.utils import prepare_data, save_plot, save_model

# get the data, convert it into a DataFrame and then use below commands
X, y = prepare_data(df)

model = Perceptron(eta = eta, epochs = epochs)
model.fit(X, y, fn, alpha=None) # alpha ranges between 0 to 1 if and only if ELU activation function is applied else alpha value remains None for other activation functions

Total_Error = model.total_loss()

save_model(model, filename = filename)

save_plot(df, plotFilename, model)

Reference

Python Package Publishing Docs

GitHub Actions CICD Docs