LATENT REFERENCES / TAG2
Warren McCulloch
Original title: ウォーレン・マカロック
This reference note belongs to Tag2 in Latent References, an archive curated by Keigo Yoshida. Its archive region is Chaos theory · Lorenz equations. The note preserves its source text and links so that readers can trace the material behind the 3D map.
- Collection
- Tag2
- Archive region
- Chaos theory · Lorenz equations
Archived reference note
English translation of the archived note. JP shows the original text. Source links and literal code are retained; the translation does not update or independently verify the source claims.
The article on formal neurons discusses the modeled neurons treated in A Logical Calculus of the Ideas Immanent in Nervous Activity, published in 1943 by neurophysiologist and surgeon Warren McCulloch and logician and mathematician Walter Pitts (the original gives no explicit name to the neurons under discussion, and later commentators have used various names besides formal neuron). As pioneering published research on artificial neurons and neural networks, it influenced later proposals such as the perceptron (see also connectionism). Its characteristics are the use of the Heaviside step function as its transfer function (activation function), and input and output values restricted to the two binary values 0 and 1.
A pivotal figure in artificial intelligence.
https://scrapbox.io/files/6821e015ccc2eab093168ed6.png
形式ニューロン(けいしきニューロン)の記事では、1943年に神経生理学者・外科医であるウォーレン・マカロックと論理学者・数学者であるウォルター・ピッツが発表したA Logical Calculus of the Ideas Immanent in Nervous Activityで扱われた、モデル化されたニューロンについて述べる(原典では議論の対象であるニューロンについて明確な呼び名を与えておらず、後世の論者からの呼称は formal neuron の他、いろいろある)。人工ニューロン・ニューラルネットワークの研究を発表した先駆として、後のパーセプトロンの提案などに影響を与えた(コネクショニズムも参照)。伝達関数(活性化関数)として、ヘヴィサイドの階段関数を使い、入出力の値は 0 または 1 の二値だけをとるということに特徴がある。
人工知能の決定的人物。
https://scrapbox.io/files/6821e015ccc2eab093168ed6.png
Source updated 2025-06-01 · Snapshot 2026-10-08
Source links and calculated neighbors
Cosine values measure shared lexical features, not truth, agreement or identical meaning. Original reference links are labeled separately.
- Formal NeuronComputed lexical cosine similarity 0.583 · shared title, text, tags and references
- feed forward networkComputed lexical cosine similarity 0.121 · shared title, text, tags and references