Forward propagation in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the weighted sum in forward propagation.

ML Python

weighted_sum = sum(inputs[i] * weights[i] for i in range(len(inputs))) + [1]

Drag options to blanks, or click blank then click option'

Abias

Bactivation

Coutput

Dloss

Attempts:

3 left

💡 Hint

Common Mistakes

Using activation instead of bias in the weighted sum.

Forgetting to add bias at all.

The weighted sum includes the bias term added to the sum of inputs times weights.

2fill in blank

medium

Complete the code to apply the activation function in forward propagation.

ML Python

output = [1](weighted_sum)

Drag options to blanks, or click blank then click option'

Aactivation_function

Blen

Cprint

Dsum

Attempts:

3 left

💡 Hint

Common Mistakes

Using sum instead of activation_function.

Trying to print the weighted sum instead of applying activation.

The activation function is applied to the weighted sum to produce the output.

3fill in blank

hard

Fix the error in the code to correctly compute the output of a neuron.

ML Python

output = activation_function([1])

Drag options to blanks, or click blank then click option'

Ainputs

Bweighted_sum

Cweights

Dbias

Attempts:

3 left

💡 Hint

Common Mistakes

Applying activation function directly to inputs or weights.

Using bias alone as input to activation.

The activation function should be applied to the weighted sum, not directly to inputs or weights.

4fill in blank

hard

Fill both blanks to complete the forward propagation step for one neuron.

ML Python

weighted_sum = sum([1][i] * [2][i] for i in range(len(inputs))) + bias

Drag options to blanks, or click blank then click option'

Ainputs

Bweights

Cbias

Doutput

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping inputs and weights in multiplication.

Including bias inside the loop.

Inputs and weights are multiplied element-wise and summed to get the weighted sum.

5fill in blank

hard

Fill all three blanks to complete the forward propagation for a layer of neurons.

ML Python

outputs = [activation_function(sum([1][i] * [2][j][i] for i in range(len([3]))) + biases[j]) for j in range(len(weights))]

Drag options to blanks, or click blank then click option'

Ainputs

Bweights

Dbiases

Attempts:

3 left

💡 Hint

Common Mistakes

Using biases instead of inputs in the sum.

Mixing up weights and biases indices.

For each neuron j, multiply inputs by weights[j], sum, add bias, then apply activation.