Start learning →

Claude MLP and Activations — practice questions

Explore 10 free MLP and Activations questions in Claude Aifoundations. Open each question or exercise to read its content, reference answers and available explanation.

Practise MLP and Activations with Quill →

MLP and Activations questions and exercises with answers

Showing questions 1–10 of 10.

What does an MLP add to a linear model?Read the answer and worked solution →Why does a stack of affine layers collapse without an activation function?Read the answer and worked solution →The ReLU activation function is defined asRead the answer and worked solution →The sigmoid function squashes its input to which interval?Read the answer and worked solution →The tanh function squashes its input to which interval?Read the answer and worked solution →The derivative of the ReLU function isRead the answer and worked solution →The derivative of sigmoid(x) equalsRead the answer and worked solution →For an MLP layer with input X ∈ ℝⁿˣᵈ, hidden width h and output q, the weight shapes areRead the answer and worked solution →Why is the sigmoid prone to the vanishing-gradient problem?Read the answer and worked solution →Flip and match each activationRead the answer and worked solution →

Worked practice questions

What does an MLP add to a linear model?

  1. One or more hidden layers between input and output
  2. A larger batch size only at training time
  3. A higher learning rate at every training step
  4. A different optimiser without architectural change
Show answer and solution

Correct answer: A. One or more hidden layers between input and output

An MLP stacks fully-connected hidden layers between input and output. With nonlinear activations, it can represent much richer mappings than a single linear layer.

Open this question →

Why does a stack of affine layers collapse without an activation function?

  1. Stacking them runs out of memory on the GPU
  2. Affine of affine is affine, equivalent to one layer
  3. The optimiser refuses to update multiple layers
  4. Stacking is only allowed with skip connections
Show answer and solution

Correct answer: B. Affine of affine is affine, equivalent to one layer

If H = XW¹ + b¹ and O = HW² + b², then O = X(W¹W²) + (b¹W² + b²), a single linear layer. Nonlinearity is what gives depth its power.

Open this question →

The ReLU activation function is defined as

  1. max(x, 0)
  2. 1 / (1 + exp(-x))
  3. tanh(x)
  4. exp(-x)
Show answer and solution

Correct answer: A. max(x, 0)

ReLU(x) = max(x, 0) — keep positive values, zero out negatives. Simple, fast, and the dominant activation in modern hidden layers.

Open this question →

How to practise

  1. Choose a MLP and Activations question and try to work out your answer.
  2. Open the question to check the correct answer and read its worked solution.
  3. Continue in the app for bite-sized lessons, explanations and review with Quill. You can start without creating an account.

More Aifoundations topics

AlexNet CNN ImageNetMany Shot in Context LearningLinear Regression and Supervised LearningMath for AI LA ProbabilityInstructGPT RLHFTransformer AttentionWhat Is AI Intro