Franklin Moormann

Fix Issue 401 Error

1

This commit implements three critical Graph Neural Network architectures to expand the AiDotNet library's GNN capabilities: 1. **Graph Attention Networks (GAT)** - Multi-head attention mechanism for graph-structured data - Learns...

fix: fix vector database and choose implementation version

2

## PR Title (Auto-Fixed) **Note:** PR titles are automatically fixed to follow [Conventional Commits](https://www.conventionalcommits.org/) format for automated releases. The workflow will intelligently detect the appropriate type based on: - Title...

Claude/fix issue 417 chain of thought 011 c uu sh u85 jd b ngn qq2dc1 j

5

## User Story / Context - Reference: [US-XXX] (if applicable) - Base branch: `merge-dev2-to-master` ## Summary - What changed and why (scoped strictly to the user story / PR intent)...

Fix issue 419

3

This commit implements comprehensive continual learning and active learning capabilities as requested in issue #419. ## Continual Learning Implementation ### Core Infrastructure: - IContinualLearner interface for continual learning systems -...

## Problem Statement The Knowledge Distillation (KD) framework's interfaces are correctly generic with `IKnowledgeDistillationTrainer` and `IDistillationStrategy`, but concrete implementations are hardcoded to `Vector`, forcing conversions and defeating the purpose of...

Fix Issue 409

9

…zation (Issue #409) This commit implements a comprehensive inference optimization system that achieves 2-5x speedup through graph-level optimizations and operator fusion. Key Features: 1. Operator Fusion (CRITICAL): - Conv +...

Add comprehensive benchmarks for AiDotNet library

1

## User Story / Context - Reference: [US-XXX] (if applicable) - Base branch: `merge-dev2-to-master` ## Summary - What changed and why (scoped strictly to the user story / PR intent)...

Add comprehensive integration tests to repo

1

## User Story / Context - Reference: [US-XXX] (if applicable) - Base branch: `merge-dev2-to-master` ## Summary - What changed and why (scoped strictly to the user story / PR intent)...

## Problem Statement Currently, neural network classes accept `ILossFunction` as a separate constructor parameter, even though the default loss function is already determined by `architecture.TaskType` via `NeuralNetworkHelper.GetDefaultLossFunction()`. **Current pattern:** ```csharp...

## Goal: Evaluate SuperNet Architecture for Better Neural Network Integration Investigate whether SuperNet (DARTS-based Neural Architecture Search) should inherit from NeuralNetworkBase to align with the library's neural network architecture patterns....