---
title: "Hinton's Forward-Forward algorithm traces its own ancestry to Boltzmann machines — replacing backprop's backward pass with two forward passes"
type: "claim"
status: "budding"
audit_status: "verified-verbatim (queen extract_pdf read of the primary preprint in full at capture level; §6.1 lineage section confirmed)"
source_url: "https://arxiv.org/abs/2212.13345"
source_title: "The Forward-Forward Algorithm: Some Preliminary Investigations"
source_author: "Geoffrey Hinton"
source_date: 2022
source_venue: "'The Forward-Forward Algorithm: Some Preliminary Investigations'"
source_tier: 1
source_quote: "The Forward-Forward algorithm"
provenance: "Promotion from 10-inbox/raw/20260706-1501-does-hintons-forward-forward.md, 2026-07-06, queen cycle 9"
origin: "session"
date_created: "2026-07-06T00:00:00.000Z"
tags: ["hinton","forward-forward","boltzmann-machines","biological-plausibility","backpropagation-alternative"]
drafted_in: ["2026-07-13-cut-one-percent-of-the-bonds","cut-one-percent-of-the-bonds"]
---


Forward-Forward (Hinton, 2022) removes the objection backprop's whole second
phase raises ([[claim-hinton-biological-implausibility-four-objections]],
points 2–4): instead of a forward pass plus a distinct backward pass, it runs
two forward passes — one on real ("positive") data, one on "negative" data —
and each layer locally adjusts to raise a goodness measure on positive and
lower it on negative. No stored activations for a backward sweep, no global
differentiability requirement, no synchronized backward phase.

The paper is explicit about its own lineage: a dedicated §6.1 traces FF to
Boltzmann machines, and (per the capture's direct read) it does NOT
name-check contrastive Hebbian learning and treats equilibrium propagation
only as a prior "effort," not a peer. That self-genealogy matters for the
myth-adjacent habit this vault tracks — here the author states his own
ancestry precisely, which is the opposite of the citation vacuum around the
1986 paper ([[claim-rhw-1986-reference-list-four-works]]). Companion to
[[claim-feedback-alignment-random-weights-train]] as the two live
biological-plausibility candidates. See [[moc-backpropagation-origins]].