commit 9c515aba8eea511f49cead100af4f857375f395c
Author: Sabic <sabic@seiwert.local>
Date:   Mon Jun 24 15:52:44 2024 +0200

    first commit

diff --git a/generate_dataset.py b/generate_dataset.py
new file mode 100644
index 0000000..daa108f
--- /dev/null
+++ b/generate_dataset.py
@@ -0,0 +1,29 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Parameters
+num_points = 1000  # Number of data points
+radius = 5  # Radius to separate the classes
+
+# Generate random (x, y) coordinates
+x = np.random.uniform(-10, 10, num_points)
+y = np.random.uniform(-10, 10, num_points)
+
+# Calculate distance from the origin
+distance = np.sqrt(x**2 + y**2)
+
+# Class labels: 0 for inside the radius, 1 for outside the radius
+labels = (distance > radius).astype(int)
+
+# Plot the dataset
+plt.figure(figsize=(8, 8))
+plt.scatter(x[labels == 0], y[labels == 0], color='blue', label='Class 0 (Inside radius)')
+plt.scatter(x[labels == 1], y[labels == 1], color='red', label='Class 1 (Outside radius)')
+plt.axhline(0, color='black',linewidth=0.5)
+plt.axvline(0, color='black',linewidth=0.5)
+plt.grid(color = 'gray', linestyle = '--', linewidth = 0.5)
+plt.xlabel('X')
+plt.ylabel('Y')
+plt.title('Generated Dataset for Classification Task')
+plt.legend()
+plt.show()
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..401f416
--- /dev/null
+++ b/main.py
@@ -0,0 +1,29 @@
+import numpy as np
+from random import random
+
+neurons_per_layer = 4
+layers = 2
+inputs = 2
+outputs = 1
+
+grid_min = -10
+grid_max = 10
+
+biases = [[] for _ in range(layers)]
+
+for i in range(0, neurons_per_layer)
+
+weights = [[] for _ in range(layers+2)]
+
+# Input layer to first hidden layer weights
+weights[0] = [random() for _ in range(inputs*neurons_per_layer)]
+
+for i in range(1, layers+1):
+    # Weights between hidden layers
+    weights[i] = [random() for _ in range(neurons_per_layer ** 2)]
+
+# Weights from last hidden layer to output layer
+weights[-1] = [random() for _ in range(outputs*neurons_per_layer)]
+
+def sigmoid(x):  
+    return np.exp(-np.logaddexp(0, -x))