get.Learnables — Read the parameter table projected from a network's Layers.
Network parameters are stored once in Layers. The Learnables table is derived when read; its resident values retain their GPU leases without a download.
Syntax
learnables = get.Learnables(network)Inputs
network- Type
Any- Required
- Yes
- Default
- —
- Description
- A dlnetwork, SeriesNetwork, or DAGNetwork value object.
Returns
learnables- Type
Any- Description
- A table derived from the network's canonical Layers.
Errors
RunMat:deepLearning:InvalidInput- When
- The network or Learnables table does not match the supported parameter topology.
- Message
network Learnables access received invalid input
Parameter ownership
Layer and Parameter are string-array columns. Value is a cell column of dlarray values, with an empty value for an uninitialized parameter. Rows appear in layer order. Supported roles include fully connected and convolutional Weights/Bias, recurrent InputWeights/RecurrentWeights/Bias, and normalization Scale/Offset.
Reading Learnables does not update the network. Assignment to the dependent property uses set.Learnables and validates the complete table before replacing any parameter.
RunMat also exposes this projection on its SeriesNetwork and DAGNetwork values; this is a RunMat extension, not a claim that MATLAB publishes a Learnables property on those classes.
This supported parameter subset is real numeric. Complex learnables are not currently admitted; they are not coerced to real values.
Using get.Learnables with coding agents
Open a RunMat example with live inputs, then ask the agent to explain how get.Learnables changes the result.
Run a small get.Learnables example, explain the result, then change one input and compare the output.
Related Deep Learning functions
adamupdate · analyzeNetwork · bilstmLayer · classificationLayer · combvec · convolution1dLayer · crossentropy · dlarray · dlarray.minus · dlarray.mtimes · dlarray.plus · dlarray.rdivide · dlarray.sum · dlarray.times · dlfeval · dlgradient · dlnetwork · dlupdate · eluLayer · exportONNXNetwork · featureInputLayer · forward · fullyConnectedLayer · get.State · globalAveragePooling1dLayer · layerGraph · layerNormalizationLayer · lstmLayer · padsequences · regressionLayer · reluLayer · sequenceInputLayer · set.Learnables · set.State · softmaxLayer · trainingOptions · trainnet · trainNetwork
Source you can read
Every RunMat function's source is public. Read exactly how get.Learnables is executed, line by line, in Rust.
- View the source for get.Learnables in Rust on GitHub
- Learn how the RunMat runtime works
- Found a bug? Open an issue with a minimal reproduction.
About RunMat
RunMat is a runtime that executes MATLAB-syntax code fast on any GPU. The runtime is free for individuals, including freelancers; students and faculty at an academic institution, for teaching or research there; contributors to an open-source project, for work on that project; organizations with 250 or fewer people and US$10M or less in annual revenue; and anyone, for non-production use. See runmat.com/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.