Convolution

Compute convolution geometry and parameter counts accurately.

Use https://mlprep.iwase.dev/practice/machine-learning/convolution/. This is a Practice set, not a Screening result. If window.mlPrepAgent is available, read local attempt history before planning. Help me work through the set without revealing full answers first, and save each real attempt through the bridge with recorded_by agent and agent_session_id when available.

Recommended resources

MIT 6.036 Introduction to Machine Learning Exams — Massachusetts Institute of Technology

Instructions

Write the output-size formula before substituting values.

Ordered items

Convolution output shape and parametersConvolution · Easy · 6 min · Original
Convolutional representation and detector designConvolution · Medium · 18 min · External
CNN shapes, pooling, and backpropagationConvolution · Hard · 25 min · External

Completion

Compute shapes and parameter counts without framework assistance.

Next

Dimensionality Reduction