first commit

Author: Atefeh97hmt

HyperbolicTangentFunction.py

@@ -0,0 +1,22 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the Tanh Activation Function
+def tanh(x):
+    return np.tanh(x)
+
+# Generate input values
+x = np.linspace(-10, 10, 1000)
+y = tanh(x)
+
+# Plot the Tanh Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='f(x) = tanh(x)', color='purple')
+plt.title('Tanh Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Output (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()

Leaky ReLU.png

@@ -0,0 +1,22 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the Leaky ReLU Activation Function
+def leaky_relu(x, alpha=0.01):
+    return np.where(x > 0, x, alpha * x)
+
+# Generate input values
+x = np.linspace(-10, 10, 1000)
+y = leaky_relu(x, alpha=0.01)
+
+# Plot the Leaky ReLU Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='f(x) = Leaky ReLU (α=0.01)', color='red')
+plt.title('Leaky ReLU Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Output (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()

Leaky ReLU.py

@@ -0,0 +1,22 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the ReLU Activation Function
+def relu(x):
+    return np.maximum(0, x)
+
+# Generate input values
+x = np.linspace(-10, 10, 1000)
+y = relu(x)
+
+# Plot the ReLU Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='f(x) = max(0, x)', color='orange')
+plt.title('ReLU Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Output (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()

Linear.png

@@ -0,0 +1,22 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the Sigmoid Activation Function
+def sigmoid(x):
+    return 1 / (1 + np.exp(-x))
+
+# Generate input values
+x = np.linspace(-10, 10, 1000)
+y = sigmoid(x)
+
+# Plot the Sigmoid Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='f(x) = 1 / (1 + e^(-x))', color='g')
+plt.title('Sigmoid Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Output (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()

ReLU Function Chart.png

@@ -0,0 +1,23 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the Softmax Activation Function
+def softmax(x):
+    exp_x = np.exp(x - np.max(x))  # For numerical stability
+    return exp_x / np.sum(exp_x)
+
+# Generate input values (example logits)
+x = np.linspace(-5, 5, 100)
+y = softmax(x)
+
+# Plot the Softmax Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='Softmax Function', color='gray')
+plt.title('Softmax Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Probability (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()

RectifiedLinearUnit.py

@@ -0,0 +1,22 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Define the Linear Activation Function
+def linear_activation(x):
+    return x
+
+# Generate input values
+x = np.linspace(-10, 10, 100)
+y = linear_activation(x)
+
+# Plot the Linear Activation Function
+plt.figure(figsize=(8, 6))
+plt.plot(x, y, label='f(x) = x', color='b')
+plt.title('Linear Activation Function')
+plt.xlabel('Input (x)')
+plt.ylabel('Output (f(x))')
+plt.axhline(0, color='grey', lw=0.5)
+plt.axvline(0, color='grey', lw=0.5)
+plt.grid(True, linestyle='--', alpha=0.5)
+plt.legend()
+plt.show()