394 convert misc nn classes to num power #395

apphp · 2026-01-25T15:02:31Z

No description provided.

…neural network layers.

…hensive unit tests and fixed broken source file link in the documentation

…d updated documentation with fixed source file link. Added `Parametric` interface to define parameterized layers.

…on support

…ith `NumPower` utilities

…ical stability during inference, and gradient computation logic

…itional tests and updated shape handling

…interface definition for output layers.

…entation and unit tests

…d/backward passes

…ence/backward passes, unit tests, and documentation updates

…ith `NumPower` utilities

…rd/inference/backward passes, unit tests

…ference/backward passes, unit tests

…rward/inference/backward passes, unit tests

Copilot

Pull request overview

This PR refactors various neural network classes to use the NumPower library. It introduces new implementations for neural network layers, networks, snapshots, and their corresponding test files. The changes also update documentation paths to reflect the new class structure organized into subdirectories.

Changes:

Adds new neural network layer implementations (Dense, Activation, Binary, Continuous, Multiclass, Dropout, Noise, BatchNorm, PReLU, Swish, Placeholder1D) using NumPower
Introduces Network and FeedForward classes with comprehensive test coverage
Updates initializers to include explicit loc parameter for NumPower compatibility
Updates documentation paths to reflect new directory structure

Reviewed changes

Copilot reviewed 51 out of 51 changed files in this pull request and generated 10 comments.

Show a summary per file

File	Description
src/NeuralNet/Networks/Network.php	New base Network class implementation using NumPower
src/NeuralNet/FeedForwards/FeedForward.php	New FeedForward network extending Network
src/NeuralNet/Layers//.php	New layer implementations (Dense, Activation, Binary, etc.)
src/NeuralNet/Snapshots/Snapshot.php	New snapshot class for network state management
tests/NeuralNet//.php	Comprehensive test coverage for new implementations
src/NeuralNet/Initializers//.php	Updated to include explicit loc parameter
docs/neural-network/hidden-layers/*.md	Documentation path updates
phpunit.xml	Memory limit increase for tests

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-28T17:12:54Z

src/NeuralNet/Layers/Base/Contracts/Layer.php

+use Stringable;
+
+/**
+ * Hidden


The docblock says "Hidden" but this is the Layer interface, not the Hidden interface. This should be corrected to say "Layer" instead of "Hidden".

Suggested change

* Hidden

* Layer

Copilot · 2026-01-28T17:12:55Z

tests/Helpers/GraphvizTest.php

@@ -14,9 +16,8 @@
 #[CoversClass(GraphvizTest::class)]


The CoversClass attribute incorrectly references GraphvizTest::class instead of Graphviz::class. This should be changed to #[CoversClass(Graphviz::class)] to correctly indicate that this test covers the Graphviz class.

Copilot · 2026-01-28T17:12:55Z

src/NeuralNet/FeedForwards/FeedForward.php

+    /**
+     * Return an array of hidden layers indexed left to right.
+     *
+     * @return list<Layers\Hidden>


The return type annotation uses Layers\Hidden which is incorrect. It should be list<Hidden> since the proper namespace is already imported with use Rubix\ML\NeuralNet\Layers\Base\Contracts\Hidden; at the top of the file.

Suggested change

* @return list<Layers\Hidden>

* @return list<Hidden>

Copilot · 2026-01-28T17:12:55Z

src/NeuralNet/FeedForwards/FeedForward.php

+use NumPower;
+use Rubix\ML\NeuralNet\Layers\Base\Contracts\Hidden;
+use Rubix\ML\NeuralNet\Layers\Base\Contracts\Input;
+use Rubix\ML\NeuralNet\Layers\Base\Contracts\Output;


The import use Rubix\ML\NeuralNet\Layers\Base\Contracts\Layer; is missing at the top of the file. This is needed because line 127 references Traversable<Layers\Layer> in a docblock. Either add the import and change the reference to Traversable<Layer>, or use the full namespace path in the docblock.

Suggested change

use Rubix\ML\NeuralNet\Layers\Base\Contracts\Output;

use Rubix\ML\NeuralNet\Layers\Base\Contracts\Output;

use Rubix\ML\NeuralNet\Layers\Base\Contracts\Layer;

Copilot · 2026-01-28T17:12:55Z

tests/NeuralNet/Layers/Binary/BinaryTest.php

@@ -0,0 +1,192 @@
+<?php
+
+declare(strict_types = 1);


The spacing in the strict_types declaration is inconsistent with other test files in the codebase. The majority of test files use declare(strict_types=1); without spaces, but this file uses declare(strict_types = 1); with spaces. For consistency, it should match the predominant pattern in the codebase which is without spaces.

Copilot · 2026-01-28T17:12:56Z

tests/NeuralNet/Layers/Binary/BinaryTest.php

+        }
+        $expected = NumPower::array([$expected]);
+
+        $batchSize = count($this->labels);


The variable $batchSize is calculated but never used (other than the erroneous call on line 176). This line should be removed.

Copilot · 2026-01-28T17:12:56Z

tests/NeuralNet/Layers/Binary/BinaryTest.php

+    }
+
+    #[Test]
+    #[TestDox('Computes gradient directly given input, output, expected, and batch size')]


The TestDox attribute mentions "input, output, expected, and batch size" but the gradient method does not accept a batch size parameter. The description should be updated to remove the mention of "batch size" since it's not actually a parameter to the gradient method.

Copilot · 2026-01-28T17:12:56Z

src/NeuralNet/Layers/Swish/Swish.php

+        // Original formulation:
+        // derivative = (output / input) * (1 - output) + output
+        // Implemented using NumPower operations to avoid explicit ones matrix.
+        $term1 = NumPower::divide($output, $input);


The differentiate method performs division NumPower::divide($output, $input) which could cause division by zero if the input contains zero values. While NumPower might handle this, it would be safer to add a comment explaining the expected behavior or add explicit handling for this edge case.

Copilot · 2026-01-28T17:12:56Z

tests/NeuralNet/Layers/Placeholder1D/Placeholder1DTest.php

@@ -0,0 +1,114 @@
+<?php
+
+declare(strict_types = 1);


The spacing in the strict_types declaration is inconsistent with other test files in the codebase. The majority of test files use declare(strict_types=1); without spaces, but this file uses declare(strict_types = 1); with spaces. For consistency, it should match the predominant pattern in the codebase which is without spaces.

Copilot · 2026-01-28T17:12:57Z

tests/NeuralNet/Layers/Binary/BinaryTest.php

+
+        $batchSize = count($this->labels);
+
+        $gradient = $this->layer->gradient($input, $output, $expected, $batchSize);


The test calls the gradient method with 4 parameters ($input, $output, $expected, $batchSize), but the Binary::gradient method signature only accepts 3 parameters (NDArray $input, NDArray $output, NDArray $expected). The fourth parameter $batchSize should be removed from this test call since it's not used by the gradient method.

apphp added 28 commits December 6, 2025 18:55

ML-392 Added Layer and Hidden interfaces to define contracts for …

fc14381

…neural network layers.

ML-393 Added standalone Activation layer implementation with compre…

9546c9d

…hensive unit tests and fixed broken source file link in the documentation

ML-394 Implemented BatchNorm layer with comprehensive unit tests an…

14a2b6f

…d updated documentation with fixed source file link. Added `Parametric` interface to define parameterized layers.

ML-395 Refactored BatchNorm layer to improve row/column normalizati…

46e101b

…on support

ML-396 Refactored BatchNorm layer to optimize normalization logic w…

a44e86a

…ith `NumPower` utilities

ML-397 Enhanced BatchNorm layer with improved axis constants, numer…

5a3f5a7

…ical stability during inference, and gradient computation logic

ML-397 Enhanced BatchNorm layer with improved axis constants, numer…

ec3c236

…ical stability during inference, and gradient computation logic

ML-398 Improved BatchNorm behavior for varying batch sizes with add…

00955f9

…itional tests and updated shape handling

ML-398 Improved BatchNorm behavior for varying batch sizes with add…

3fb79a9

…itional tests and updated shape handling

ML-399 Added Binary output layer and comprehensive unit tests with …

b4e507d

…interface definition for output layers.

ML-400 Added Continuous output layer with complete interface implem…

d5f7c57

…entation and unit tests

ML-392 Added Dense hidden layer implementation with complete forwar…

cca97f9

…d/backward passes

ML-401 Added Dropout hidden layer implementation with forward/infer…

9767a1f

…ence/backward passes, unit tests, and documentation updates

ML-392 Refactored Dropout layer to replace custom mask generation w…

8d7c938

…ith `NumPower` utilities

ML-392 Added Multiclass output layer with complete interface, forwa…

5ad0ed2

…rd/inference/backward passes, unit tests

ML-392 Added Noise output layer with complete interface, forward/in…

a6c634f

…ference/backward passes, unit tests

ML-392 Added Placeholder1D output layer with complete interface, fo…

7013a56

…rward/inference/backward passes, unit tests

ML-392 Fixed wrong exception for AssertsShapes and exception texts

08ad6b4

ML-392 Increased memory for tests

ce99147

ML-392 Added PReLU output layer with complete interface and unit tests

7628fec

ML-392 Added Swish output layer with complete interface and unit tests

f83fed6

ML-392 Fixed syntax issues in tests annotations

be52a09

ML-392 Typo fixes

0b591ed

Merge branch '3.0' into 392-convert-layers-to-numpower

c346296

ML-394 Converted FeedForward to use NumPower

106c070

ML-394 Converted Network to use NumPower

e118309

ML-394 Converted Snapshot to use NumPower

5dfc354

ML-394 Improved FeedForwardTest

0e815da

apphp requested review from a team and andrewdalpino January 25, 2026 15:02

apphp removed the request for review from a team January 26, 2026 17:46

andrewdalpino requested review from a team and Copilot January 28, 2026 17:05

Copilot started reviewing on behalf of andrewdalpino January 28, 2026 17:05 View session

Copilot AI reviewed Jan 28, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

394 convert misc nn classes to num power #395

394 convert misc nn classes to num power #395

Uh oh!

apphp commented Jan 25, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Copilot AI Jan 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

	use Rubix\ML\NeuralNet\Layers\Base\Contracts\Output;
	use Rubix\ML\NeuralNet\Layers\Base\Contracts\Output;
	use Rubix\ML\NeuralNet\Layers\Base\Contracts\Layer;


		$batchSize = count($this->labels);

		$gradient = $this->layer->gradient($input, $output, $expected, $batchSize);

Uh oh!

394 convert misc nn classes to num power #395

Are you sure you want to change the base?

394 convert misc nn classes to num power #395

Uh oh!

Conversation

apphp commented Jan 25, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant