ConceptAI & ML
Fully connected layer
A layer where a flattened 3072-dimensional input vector is multiplied by a weight matrix to compute 10 output neuron activations.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1Fei-Fei Li, Justin Johnson & Serena Yeung
Lectures that assume it
5Connections
16The lectures that define it or assume it, and the concepts next to it.