Forward propagation is the process by which input data passes through a neural network to generate predictions. It is the first step in training and using neural networks, allowing the model to compute outputs based on current weights and biases. Understanding forward propagation is essential for grasping how neural networks learn.<\/p>\n\n\n\n
How Forward Propagation Works<\/strong><\/p>\n\n\n\n Mathematical Representation<\/strong> Example: Forward Propagation in Python<\/strong><\/p>\n\n\n\n Key Points About Forward Propagation<\/strong><\/p>\n\n\n\n Applications<\/strong><\/p>\n\n\n\n Lesson Summary<\/strong>\n
z = (w1 \u00d7 x1) + (w2 \u00d7 x2) + … + (wn \u00d7 xn) + b<\/li>\n\n\n\n
a = f(z)<\/li>\n\n\n\n
For a single neuron:<\/p>\n\n\n\n\n
For multiple layers, this process is repeated for each neuron in every layer.<\/li>\n<\/ul>\n\n\n\nimport numpy as np# Inputs
X = np.array([1, 2])# Weights and bias
weights = np.array([0.5, 0.3])
bias = 0.1# Activation function (ReLU)
def relu(x):
return np.maximum(0, x)# Forward propagation
z = np.dot(X, weights) + bias
output = relu(z)print(\"Weighted sum (z):\", z)
print(\"Output after activation (a):\", output)<\/pre>\n\n\n\n\n
\n
Forward propagation is the process of passing input data through a neural network to generate predictions. It involves calculating weighted sums, applying activation functions, and propagating outputs layer by layer. This process is fundamental to understanding how neural networks operate before applying backpropagation for learning.<\/p>\n\n\n