mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-25 23:24:03 +00:00
4d5d3bb092
* docs: Add comprehensive GNN v2 implementation plans Add 22 detailed planning documents for 19 advanced GNN features: Tier 1 (Immediate - 3-6 months): - GNN-Guided HNSW Routing (+25% QPS) - Incremental Graph Learning/ATLAS (10-100x faster updates) - Neuro-Symbolic Query Execution (hybrid neural + logical) Tier 2 (Medium-Term - 6-12 months): - Hyperbolic Embeddings (Poincaré ball model) - Degree-Aware Adaptive Precision (2-4x memory reduction) - Continuous-Time Dynamic GNN (concept drift detection) Tier 3 (Research - 12+ months): - Graph Condensation (10-100x smaller graphs) - Native Sparse Attention (8-15x GPU speedup) - Quantum-Inspired Attention (long-range dependencies) Novel Innovations (10 experimental features): - Gravitational Embedding Fields, Causal Attention Networks - Topology-Aware Gradient Routing, Embedding Crystallization - Semantic Holography, Entangled Subspace Attention - Predictive Prefetch Attention, Morphological Attention - Adversarial Robustness Layer, Consensus Attention Includes comprehensive regression prevention strategy with: - Feature flag system for safe rollout - Performance baseline (186 tests + 6 search_v2 tests) - Automated rollback mechanisms Related to #38 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(micro-hnsw-wasm): Add neuromorphic HNSW v2.3 with SNN integration ## New Crate: micro-hnsw-wasm v2.3.0 - Published to crates.io: https://crates.io/crates/micro-hnsw-wasm - 11.8KB WASM binary with 58 exported functions - Neuromorphic vector search combining HNSW + Spiking Neural Networks ### Core Features - HNSW graph-based approximate nearest neighbor search - Multi-distance metrics: L2, Cosine, Dot product - GNN extensions: typed nodes, edge weights, neighbor aggregation - Multi-core sharding: 256 cores × 32 vectors = 8K total ### Spiking Neural Network (SNN) - LIF (Leaky Integrate-and-Fire) neurons with membrane dynamics - STDP (Spike-Timing Dependent Plasticity) learning - Spike propagation through graph topology - HNSW→SNN bridge for similarity-driven neural activation ### Novel Neuromorphic Features (v2.3) - Spike-Timing Vector Encoding (rate-to-time conversion) - Homeostatic Plasticity (self-stabilizing thresholds) - Oscillatory Resonance (40Hz gamma synchronization) - Winner-Take-All Circuits (competitive selection) - Dendritic Computation (nonlinear branch integration) - Temporal Pattern Recognition (spike history matching) - Combined Neuromorphic Search pipeline ### Performance Optimizations - 5.5x faster SNN tick (2,726ns → 499ns) - 18% faster STDP learning - Pre-computed reciprocal constants - Division elimination in hot paths ### Documentation & Organization - Reorganized docs into subdirectories (gnn/, implementation/, publishing/, status/) - Added comprehensive README with badges, SEO, citations - Added benchmark.js and test_wasm.js test suites - Added DEEP_REVIEW.md with performance analysis - Added Verilog RTL for ASIC synthesis 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
68 lines
1.5 KiB
TOML
68 lines
1.5 KiB
TOML
[package]
|
|
name = "spiking-network"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
rust-version = "1.77"
|
|
license = "MIT"
|
|
authors = ["Ruvector Team"]
|
|
description = "Event-driven spiking neural network for ASIC-optimized neuromorphic computing"
|
|
readme = "docs/README.md"
|
|
|
|
[dependencies]
|
|
# Core ruvector dependencies
|
|
ruvector-core = { path = "../../crates/ruvector-core", default-features = false }
|
|
ruvector-gnn = { path = "../../crates/ruvector-gnn", default-features = false }
|
|
|
|
# Math and numerics
|
|
ndarray = { version = "0.16", features = ["serde"] }
|
|
rand = "0.8"
|
|
rand_distr = "0.4"
|
|
|
|
# Serialization
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1.0"
|
|
|
|
# Error handling
|
|
thiserror = "2.0"
|
|
anyhow = "1.0"
|
|
|
|
# Performance
|
|
rayon = "1.10"
|
|
parking_lot = "0.12"
|
|
dashmap = "6.1"
|
|
|
|
# Collections for sparse operations
|
|
indexmap = { version = "2.0", features = ["serde"] }
|
|
smallvec = { version = "1.11", features = ["serde"] }
|
|
|
|
# Bitsets for spike encoding
|
|
bitvec = { version = "1.0", features = ["serde"] }
|
|
|
|
# Priority queue for event scheduling
|
|
priority-queue = "2.0"
|
|
|
|
[dev-dependencies]
|
|
criterion = { version = "0.5", features = ["html_reports"] }
|
|
proptest = "1.5"
|
|
|
|
[features]
|
|
default = ["simd"]
|
|
simd = []
|
|
wasm = []
|
|
visualization = []
|
|
|
|
[[bench]]
|
|
name = "spiking_bench"
|
|
harness = false
|
|
|
|
[[example]]
|
|
name = "edge_detection"
|
|
path = "src/examples/edge_detection.rs"
|
|
|
|
[[example]]
|
|
name = "pattern_recognition"
|
|
path = "src/examples/pattern_recognition.rs"
|
|
|
|
[[example]]
|
|
name = "asic_simulation"
|
|
path = "src/examples/asic_simulation.rs"
|