fullyConnectedLayer — Create a fully connected layer compatibility object.

fullyConnectedLayer(outputSize) returns a RunMat Deep Learning Toolbox compatibility object with layer metadata and common name-value properties.

Syntax

layer = fullyConnectedLayer(outputSize)
layer = fullyConnectedLayer(outputSize, Name, Value)

How fullyConnectedLayer works

  • outputSize must be a positive integer.
  • Name and Description are stored as layer properties.
  • Additional common layer name-value options are preserved as properties for layer graph construction.

GPU memory and residency

Layer construction is host metadata work and has no provider kernel.

Example

Create A Named Layer

layer = fullyConnectedLayer(10, 'Name', 'fc1')

Expected output:

`layer` is a `nnet.cnn.layer.FullyConnectedLayer` compatibility object.

Using fullyConnectedLayer with coding agents

Open a RunMat example with live inputs, then ask the agent to explain how fullyConnectedLayer changes the result.

Run a small fullyConnectedLayer example, explain the result, then change one input and compare the output.

About RunMat

RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.

  • RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
  • Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.

Getting started · Benchmarks · Pricing

Download RunMat

Download RunMat for full performance, or use RunMat in your browser for zero setup.