Skip to content
emerPublic

About

emergent GUI interface for gomlx neural network models

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

13 Commits

Folders and files

Repository files navigation

egomlx

pkg.go.dev docs GitHub Actions Workflow Status Test Coverage Version

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.

Structure

  • 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.

Status

Supports the following features, wrapped in the emer framework:

  • Feedforward and recurrent networks (NetworkParams.NCycles > 1) with selectable activation functions, output error statistics, and netview visualization

  • Backward learning pass: Network.Backward builds one compiled graph with forward + loss + autodiff gradients + optimizer weight updates (via gomlx optimizers). 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.

  • Recurrent settling: with NetworkParams.NCycles > 1, the network is unrolled for that many cycles, with the weights shared across cycles. Forward paths use the sender's current-cycle activity, and the recurrent Back and Lateral paths use the sender's previous-cycle activity (zero on the first cycle). The loss is computed on the final cycle, so learning is backpropagation through time.

  • ActParams.Noise adds Gaussian noise to a layer's net input on every cycle. NetworkParams.Decay < 1 carries over the final activity of the previous trial: the first cycle of the next trial starts from (1 − Decay) times that activity, within each data-parallel stream, with no gradient flowing back into the previous trial. ActParams.Dropout sets a layer's activity to zero with that probability on each cycle of the training passes only (scaling the rest to keep the mean), with no effect on Forward passes.

  • Connectivity: ConnectLayers accepts any paths.Pattern. Each pathway is a dense gomlx layer, and patterns other than full connectivity (e.g., paths.PoolOneToOne) are implemented by multiplying its weights by a fixed 0/1 connectivity mask (Path.Mask), so the unconnected weights stay zero and get no gradient. The weights are initialized using the actual number of connected senders (Path.FanIn). Note that paths.Full leaves out each unit's connection to itself for a lateral (self) pathway, unless its SelfCon is set.

Compute backends

gomlx runs the compiled graphs on a pluggable backend. compute.MustNew() picks the backend named by the environment variable GOMLX_BACKEND, and uses XLA if it is not set. Network.SetBackend sets one explicitly in code.

GOMLX_BACKEND Hardware (macOS) Notes
xla (default) CPU XLA has no GPU support on macOS. Slowest to compile, fastest per call for small networks. Uses several CPU threads.
mps Apple GPU Metal Performance Shaders, from go-darwinml. No extra install needed.
mlx Apple GPU Apple MLX, from go-darwinml. Needs the MLX library: brew install mlx, and then a full rebuild (see below).

For example:

GOMLX_BACKEND=mlx ./conflict_rnn -nogui

Network.TimerReport names the backend in use, so check it to confirm that the one you asked for was picked up.

Rebuilding after installing MLX

go-darwinml decides whether to include MLX support at compile time, by checking whether the MLX headers exist (__has_include(<mlx/mlx.h>)). Go's build cache does not notice when those headers are installed later. So a binary built before brew install mlx keeps reporting "MLX is not installed", even after rebuilding normally. Force a full rebuild once, which refreshes the cached cgo package:

brew install mlx
go build -a .

After that, ordinary builds of any program pick up the MLX-enabled package from the cache. Do the same after upgrading or removing MLX.

Timing

Network.CompileTimer, ForwardTimer and BackwardTimer time graph compilation separately from the computation (each Exec call, including reading back the results), and Network.TimerReport reports all three. Changing the network parameters (UpdateParams) or the batch shape rebuilds the graphs, so applying params in bulk (one UpdateParams per sheet) keeps the number of compiles down.

For reference, a 40-epoch run of the small recurrent conflict_rnn network (10 cycles, batch of 16, on an Apple Silicon Mac) gave identical results on all three backends, with these times:

Backend Wall CPU (user) Compile (9 graphs) Forward / call Backward / call
XLA 8.2 s 14.9 s 2.17 s 0.58 ms 2.17 ms
MPS 11.6 s 7.8 s 0.44 s 1.36 ms 4.48 ms
MLX 10.9 s 4.9 s 0.02 s 1.62 ms 4.09 ms

For small networks and batches like this, the per-call overhead of the GPU backends outweighs their compute advantage, so XLA on the CPU is fastest for a single run. MLX compiles almost instantly and uses the least CPU, so it may be the better choice for running many jobs in parallel. Larger networks and batches should favor the GPU backends.

Requirements

Running the example

From sims/ra25:

$ core run [platform]

See the sims/ra25 README for full instructions.

Use of AI

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

About

emergent GUI interface for gomlx neural network models

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages