LATENT REFERENCES / TAG2
Formal Neuron
Original title: 形式ニューロン
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 the formal neuron (Japanese reading: keishiki nyuron) discusses modeled neurons treated in “A Logical Calculus of the Ideas Immanent in Nervous Activity”1, published in 1943 by neurophysiologist and surgeon Warren McCulloch and logician and mathematician Walter Pitts (the original text did not give the neurons under discussion a specific name, 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). It is characterized by using the Heaviside step function as its transfer function (activation function), with inputs and outputs taking only the 2 values 0 or 1.
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 Activity1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。
Source updated 2025-04-15 · 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.
- Warren McCullochComputed lexical cosine similarity 0.583 · shared title, text, tags and references
- New AcademismComputed lexical cosine similarity 0.134 · shared title, text, tags and references
- NeuromancerComputed lexical cosine similarity 0.133 · shared title, text, tags and references
- feed forward networkComputed lexical cosine similarity 0.122 · shared title, text, tags and references
- NeuromelaninComputed lexical cosine similarity 0.115 · shared title, text, tags and references
- Max MathewsComputed lexical cosine similarity 0.110 · shared title, text, tags and references
- The Californian IdeologyComputed lexical cosine similarity 0.108 · shared title, text, tags and references
- Nonlinear BiologyComputed lexical cosine similarity 0.104 · shared title, text, tags and references