nuonuo/doc/p4_lifecycle.md
Fam Zheng d923aa1e31 NuoNuo: Hippocampal memory module prototype
Hopfield + Hebbian hybrid memory system for LLMs.
Two nights of experiments (16 iterations), validated on LongMemEval (ICLR 2025).

Architecture:
- Single-hop: Two-Stage Hopfield (NN top-20 → softmax settle)
- Multi-hop: Hebbian W matrix with WTA pattern separation
- 64% on LongMemEval (500 questions), retrieval-only, no LLM dependency
- 4ms latency @ 20K memories, ~1GB VRAM

Key findings:
- Hopfield attention solved noise tolerance (20% → 100% vs flat Hebbian)
- WTA pattern separation enables 20K+ capacity
- Multi-hop associative chains (6 hops, CosSim=1.0) — RAG can't do this
- MiniLM-L6 is optimal (discrimination gap > absolute similarity)
- Paraphrase cue augmentation: 55% → 100% on synthetic, 36% → 64% on benchmark
- SNN encoder viable (CosSim 0.99) but not needed for current architecture
2026-04-07 10:37:24 +01:00

1.4 KiB
Raw Blame History

P4: 记忆生命周期管理

Deduplication

可行。cosine threshold=0.7 正确识别了 2 组近似重复9 → 6 memories

  • "The database is slow" / "Database is really slow today" / "DB performance terrible" → 合并
  • "The API returns 500 errors" / "Getting 500 errors from API" → 合并

实现简单pairwise cosine on cue embeddings → group → keep best per group. O(N²) 但可以离线做(夜间整合),或用 ANN 加速。

Importance Scoring

Heuristic 规则 6/7 准确:

  • 关键词检测crash, compromised, secret → critical有效
  • 回答长度 > 15 词 → 更可能包含有用信息
  • 简单问答(时间、天气)正确标记为 low

待 LLM 可用时,可以让 LLM 评分——更准确但有延迟。

Forgetting 策略

三种策略FIFO / LRU / 重要性加权)在当前测试中效果相同——因为没有差异化的 access pattern。

实际系统中应该用 importance + access count + recency 的加权组合:

forget_score = age_days * 0.3 + (max_access - access_count) * 0.5 + (1 - importance) * 0.2

低分优先遗忘。

整合到 hippocampus.py 的建议

  1. Store 时importance scoringheuristic 或 LLM低于阈值不存
  2. 每晚deduplicationcos > 0.7 合并)+ capacity check超限时按 forget_score 裁剪)
  3. Recall 时:自动 +1 access_count已实现