set.Learnables — Replace a network's validated parameter values.
The setter validates every table row, identity, shape, and storage form before updating the canonical Layers. It does not gather resident values.
Syntax
network = set.Learnables(network, learnables)Inputs
network- Type
Any- Required
- Yes
- Default
- —
- Description
- A dlnetwork, SeriesNetwork, or DAGNetwork value object.
learnables- Type
Any- Required
- Yes
- Default
- —
- Description
- A Layer/Parameter/Value table matching the network parameter topology.
Returns
network- Type
Any- Description
- The updated value network.
Errors
RunMat:deepLearning:InvalidInput- When
- The network or Learnables table does not match the supported parameter topology.
- Message
network Learnables access received invalid input
Atomic update
The table must contain exactly Layer, Parameter, and Value columns corresponding to the existing network. Rows can be reordered when every typed Layer/Parameter identity remains unique and complete. Empty numeric values make the network uninitialized; valid replacements can initialize it. RunMat also accepts direct real numeric Value entries and cell-of-text identity columns as input extensions, while its public projection uses dlarray values and string columns.
Invalid input returns an error without changing the value network or invoking a provider.
Using set.Learnables with coding agents
Open a RunMat example with live inputs, then ask the agent to explain how set.Learnables changes the result.
Run a small set.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.Learnables · get.State · globalAveragePooling1dLayer · layerGraph · layerNormalizationLayer · lstmLayer · padsequences · regressionLayer · reluLayer · sequenceInputLayer · set.State · softmaxLayer · trainingOptions · trainnet · trainNetwork
Source you can read
Every RunMat function's source is public. Read exactly how set.Learnables is executed, line by line, in Rust.
- View the source for set.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.