egomlx

A toolkit for building, visualizing, and controlling gomlx neural network models using the emergent GUI, including the netview for displaying and interacting with the network.

• egomlx -- the core toolkit package: implements the emer Network, Layer, and Path interfaces on top of gomlx, providing netview visualization, the standard params setting system, looper integration helpers, and weights I/O.

• sims/ra25 -- a simple random-associator feedforward network with 2 hidden layers that maps 25 random 5x5 input to output patterns. It serves as the basic template for creating new models, mirroring the axon/v2/sims/ra25 structure.

The forward pass is fully implemented and live: activations, the output error statistic, and netview visualization all work with real gomlx computation (using the default XLA CPU backend; use SetBackend to select another). The backward learning pass is also live: Network.Backward builds one compiled graph with forward + loss + autodiff gradients + optimizer weight updates (via gomlx optimizers), so the example models genuinely learn. The loss function and optimizer settings are global in Network.NetworkParams; pathway-specific learning is controlled by PathParams.Learn. DWt (gradient) values are available as a netview synapse variable, read back only when actually being viewed.

• Go with the Cogent Core GUI framework. See install instructions there.

From sims/ra25:

$ core run [platform]

See the sims/ra25 README for full instructions.

This is coded largely using AI tools, under strong human supervision.