Backpropagation concept in ML Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is backpropagation in simple terms?

Backpropagation is a way for a computer to learn by fixing its mistakes. It looks at the error it made and changes its steps to do better next time.

beginner

Why do we use backpropagation in neural networks?

We use backpropagation to teach the network how to adjust its connections so it can make better predictions or decisions.

beginner

What role does the 'error' play in backpropagation?

The error shows how far the network's guess is from the right answer. Backpropagation uses this error to know how to change the network.

intermediate

How does backpropagation update the weights in a neural network?

Backpropagation calculates how much each connection (weight) contributed to the error and then changes them a little to reduce the error.

intermediate

What is the connection between backpropagation and gradient descent?

Backpropagation finds the direction to change weights to reduce error, and gradient descent is the method that moves weights step-by-step in that direction.

What does backpropagation primarily help a neural network do?

A Learn from errors to improve predictions

B Increase the size of the network

C Randomly change weights

D Make the network run faster

Backpropagation helps the network learn by adjusting weights based on errors to improve predictions.

In backpropagation, what is the 'error' used for?

A To decide how to update weights

B To add more layers

C To stop training

D To increase the learning rate

The error tells the network how wrong its prediction was, guiding how to update weights.

Which method works with backpropagation to update weights?

A Data augmentation

B Random guessing

C Feature scaling

D Gradient descent

Gradient descent uses the directions found by backpropagation to update weights step-by-step.

Backpropagation moves backward through the network to:

A Shuffle the training data

B Add new neurons

C Calculate how each weight affects the error

D Increase the output size

Backpropagation calculates gradients by moving backward to see each weight's effect on error.

What happens if backpropagation is not used in training a neural network?

A The network becomes simpler

B The network cannot learn effectively

C The network uses less memory

D The network trains faster

Without backpropagation, the network lacks a way to adjust weights based on errors, so it cannot learn well.

Explain how backpropagation helps a neural network learn from its mistakes.

Think about how the network uses the difference between its guess and the correct answer.

Describe the relationship between backpropagation and gradient descent in training neural networks.

Consider how these two work together to improve the network.

Practice

1. What is the main purpose of backpropagation in training a neural network?

easy

A. To split the data into training and testing sets

B. To randomly change weights without any calculation

C. To increase the size of the neural network

D. To update the weights by moving backward through the network

Solution

1. Step 1: Understand the role of backpropagation

   Backpropagation is used to adjust the weights in a neural network by calculating errors from the output back to the input.

2. Step 2: Identify the correct purpose

   It moves backward through the network to update weights to reduce errors during training.

3. Final Answer:

   To update the weights by moving backward through the network -> Option D

4. Quick Check:

   Backpropagation = weight update backward [OK]

Hint: Backpropagation updates weights backward through the network [OK]

Common Mistakes:

• Thinking backpropagation randomly changes weights
• Confusing backpropagation with data splitting
• Believing it increases network size

2. Which of the following is the correct formula used in backpropagation to update a weight w given learning rate η and error gradient ∂E/∂w?

easy

A. w = w + η * ∂E/∂w

B. w = η * ∂E/∂w

C. w = w - η * ∂E/∂w

D. w = w / (η * ∂E/∂w)

Solution

1. Step 1: Recall the weight update rule in backpropagation

   Weights are updated by subtracting the product of learning rate and error gradient to reduce error.

2. Step 2: Match the formula

   The correct formula is w = w - η * ∂E/∂w, which moves weights opposite to the gradient direction.

3. Final Answer:

   w = w - η * ∂E/∂w -> Option C

4. Quick Check:

   Weight update = subtract learning rate times gradient [OK]

Hint: Weights subtract learning rate times gradient to reduce error [OK]

Common Mistakes:

• Adding instead of subtracting the gradient
• Replacing weight with only the product
• Dividing weights by gradient mistakenly

3. Consider this simple neural network code snippet for one weight update during backpropagation:

weight = 0.5
learning_rate = 0.1
error_gradient = 0.4
weight = weight - learning_rate * error_gradient
print(round(weight, 2))

What will be the printed output?

medium

A. 0.46

B. 0.40

C. 0.50

D. 0.54

Solution

1. Step 1: Calculate the weight update

   weight update = 0.5 - 0.1 * 0.4 = 0.5 - 0.04 = 0.46

2. Step 2: Print the rounded weight

   Rounded to two decimals, weight is 0.46.

3. Final Answer:

   0.46 -> Option A

4. Quick Check:

   0.5 - 0.1*0.4 = 0.46 [OK]

Hint: Subtract learning rate times gradient from weight [OK]

Common Mistakes:

• Adding instead of subtracting the product
• Rounding incorrectly
• Using wrong initial weight value

4. The following code tries to perform one step of backpropagation weight update but has an error:

weight = 0.3
learning_rate = 0.05
error_gradient = 0.2
weight = weight + learning_rate * error_gradient
print(weight)

What is the error and how to fix it?

medium

A. Error: weight should be initialized to zero, fix by setting weight=0

B. Error: Should subtract gradient product, fix by changing + to -

C. Error: learning_rate should be multiplied twice, fix by squaring it

D. No error, code is correct

Solution

1. Step 1: Identify the update rule mistake

   The code adds the product of learning rate and gradient, but backpropagation requires subtraction to reduce error.

2. Step 2: Correct the operator

   Change the + to - so weight = weight - learning_rate * error_gradient.

3. Final Answer:

   Error: Should subtract gradient product, fix by changing + to - -> Option B

4. Quick Check:

   Weight update subtracts gradient product [OK]

Hint: Backpropagation updates subtract gradient product [OK]

Common Mistakes:

• Adding instead of subtracting gradient product
• Changing weight initialization unnecessarily
• Multiplying learning rate incorrectly

5. In a neural network with two layers, if the output error is large, how does backpropagation help reduce this error through the layers?

hard

A. By calculating gradients layer by layer from output to input and updating weights accordingly

B. By increasing the number of neurons in each layer automatically

C. By randomly resetting all weights to zero and retraining

D. By only updating weights in the first layer and ignoring others

Solution

1. Step 1: Understand backpropagation across layers

   Backpropagation calculates error gradients starting from the output layer backward through each layer.

2. Step 2: Update weights in all layers

   It updates weights in every layer based on their contribution to the error, reducing overall error.

3. Final Answer:

   By calculating gradients layer by layer from output to input and updating weights accordingly -> Option A

4. Quick Check:

   Backpropagation = layer-wise gradient update [OK]

Hint: Backpropagation updates all layers backward to reduce error [OK]

Common Mistakes:

• Thinking it increases neurons automatically
• Resetting weights randomly
• Updating only the first layer weights