c5d0695acf
- Add :WEIGHT: extraction to build script (from Org PROPERTIES into Hugo TOML frontmatter) - Shorten architecture _index.org staged progression to a single-line summary pointing to stages/ directory - Weight order (sidebar now reads in this order): stages/ (10-20) — the roadmap, early so references make sense lisp-foundation.org (21) — why Lisp knowledge-layers/ (30-32) — how the system knows design-decisions through neuro-comparison (40-45) — design systemic-effects (50) — implications org-knowledge-base through repo-organization (60-64) — reference - Rebuild: 148 files, 0 errors
42 lines
2.8 KiB
Org Mode
42 lines
2.8 KiB
Org Mode
:PROPERTIES:
|
|
:CREATED: [2026-06-01 Mon]
|
|
:WEIGHT: 45
|
|
:ID: a7b8c9d0-1e2f-3a4b-5c6d-7e8f90abcdef
|
|
:END:
|
|
#+title: ANN vs Neuromorphic vs Symbolic
|
|
#+filetags: :passepartout:architecture:neurosymbolic:math:
|
|
|
|
**ANN vs Neuromorphic vs Symbolic**
|
|
|
|
**Core insight**
|
|
|
|
The gap between ANNs and biology is not substrate (binary vs analog). Both are continuous mathematics running on discrete hardware. The real differences are architectural:
|
|
|
|
1. Memory-binding: ANNs store weights separately from compute (von Neumann bottleneck). Biology co-locates weight and signal at the synapse.
|
|
2. Local vs global learning: ANNs need a global error signal backpropagated through every layer. Biology uses purely local plasticity (STDP) — each synapse adjusts based on its own pre/post partners.
|
|
3. Time: Biology is asynchronous, continuous, with rich temporal dynamics. ANNs are synchronous — everything computed in lockstep. Recurrence is an awkward addition.
|
|
4. One substrate, many functions: A biological synapse does memory, signal propagation, temporal integration, and plasticity in one structure. ANNs separate these across different passes and optimizers.
|
|
|
|
**When each mathematics is appropriate**
|
|
|
|
| Mathematics | Naturally good at | Awkward at |
|
|
+------------+-------------------+------------+
|
|
| ANN / gradient descent | Smooth function approximation, interpolation, pattern completion from dense data | Symbolic reasoning, exact constraints, sparse data, multi-step verification |
|
|
| Neuromorphic / spiking dynamics | Temporal pattern recognition, event-driven control, low-power always-on sensing | Complex multi-step planning, precise arithmetic, storing large lookup tables |
|
|
| Symbolic / deduction | Exact reasoning, proof, constraint satisfaction, verifiable behavior | Learning from raw data, generalization, handling noisy inputs |
|
|
|
|
**How Passepartout uses all three**
|
|
|
|
- LLM (ANN on GPU) handles the noisy real world — language, vision, imperfect input
|
|
- Screamer (symbolic constraint search on CPU) handles combinatorial reasoning — "find valid configuration"
|
|
- ACL2 (deductive proof) handles the verifiable kernel — "prove this decision follows from rules"
|
|
- P150 (RISC-V parallel accelerator, in-between arch) handles ambient awareness, parallel dispatch, anomaly detection
|
|
|
|
Each mathematics where it belongs. The failure mode of both pure ANN and pure symbolic approaches is forcing one mathematics to do what the other is better at.
|
|
|
|
**The neuromorphic opportunity**
|
|
|
|
A neuromorphic chip (Loihi-level) would add unsupervised temporal learning — learning daily rhythms, behavioral patterns, and detecting deviations without training, labels, or LLM involvement. This is the difference between responding to commands and anticipating needs.
|
|
|
|
But the P150 gets 80% there with programmable cores controlled directly, without waiting for neuromorphic hardware to mature.
|