Walter Pitts | |
|---|---|
 Pitts around 1954 when he was at M.I.T. | |
| Born | Walter Harry Pitts Jr. (1923-04-23)April 23, 1923 |
| Died | May 14, 1969(1969-05-14) (aged 46) Cambridge,Massachusetts, U.S. |
| Known for | |
| Scientific career | |
| Fields | Logician |
Walter Harry Pitts Jr. (April 23, 1923 – May 14, 1969) was an Americanlogician who worked in the field ofcomputational neuroscience.[1] He proposed landmark theoretical formulations of neural activity and generative processes that influenced diverse fields such ascognitive sciences andpsychology,philosophy,neurosciences,computer science,artificial neural networks,cybernetics andartificial intelligence, together with what has come to be known as thegenerative sciences. He is best remembered for having written, along withWarren Sturgis McCulloch, a seminal paper in scientific history, titledA Logical Calculus of Ideas Immanent in Nervous Activity (1943). This paper proposed the first mathematical model of aneural network. The unit of this model, a simple formalized neuron, is still the standard of reference in the field of neural networks. It is often called aMcCulloch–Pitts neuron. Prior to that paper, he formalized his ideas regarding the fundamental steps to building aTuring machine in "The Bulletin of Mathematical Biophysics" in an essay titled "Some observations on the simple neuron circuit".
Walter Pitts was born inDetroit,Michigan on April 23, 1923, the son of Walter and Marie (née Welsia). Anautodidact, he taught himselflogic andmathematics as a child and became a proficient reader in several languages, includingGreek andLatin. He is widely remembered for having spent three days in a library, at the age of 12, readingPrincipia Mathematica and sent a letter toBertrand Russell pointing out what he considered serious problems with the first half of the first volume. Russell was appreciative and invited him to study atCambridge University at age 12. The offer was not taken up; however, Pitts did decide to become a logician. At age 15 he left home to study.
Pitts probably continued to correspond with Bertrand Russell; and at the age of 15 he attended Russell's lectures at theUniversity of Chicago.[1][2] He stayed there, without registering as a student. While there, in 1938 he metJerome Lettvin, apre-medical student, and the two became close friends.[3] Russell was a visiting professor at the University of Chicago in the fall of 1938, and he directed Pitts to study with the logicianRudolf Carnap.[3] Pitts met Carnap at Chicago by walking into his office during office hours, and presenting him with an annotated version of Carnap's recent book on logic,The Logical Syntax of Language.[4] Since Pitts did not introduce himself, Carnap spent months searching for him, and, when he found him, he obtained for him a menial job at the university and had Pitts study with him. Pitts at the time was homeless and without income.[5] He mastered Carnap's abstract logic, then met with and was intrigued by the work of the Ukrainian mathematical physicistNicolas Rashevsky, who was also at Chicago and was the founder ofmathematical biophysics, remodeling biology on the structure of the physical sciences andmathematical logic.[6] Pitts also worked closely with the mathematicianAlston Scott Householder, who was a member of Rashevsky's group.[7][8][9] During his studies under Carnap, Pitts was also a regular attendant at Nicolas Rashevsky’s seminars in theoretical biology, which included Frank Offner, Herbert Landahl, Alston Householder, and the neuroanatomist Gerhardt von Bonin from theUniversity of Illinois at Chicago. In 1940, Von Bonin introduced Lettvin toWarren McCulloch, who would become a professor of psychiatry at Illinois.
In 1941Warren McCulloch took a position as professor of psychiatry at theUniversity of Illinois at Chicago, and in early 1942 he invited Pitts, who was still homeless, together with Lettvin to live with his family.[10] In the evenings, McCulloch and Pitts collaborated. Pitts was familiar with the work ofGottfried Leibniz on computing and they considered the question of whether the nervous system could be considered a kind of universal computing device as described by Leibniz. This led to their seminalneural networks paper "A Logical Calculus of Ideas Immanent in Nervous Activity". After five years of unofficial studies, the University of Chicago awarded Pitts anAssociate of Arts (his only earned degree) for his work on the paper.[11]
In 1943, Lettvin introduced Pitts toNorbert Wiener at theMassachusetts Institute of Technology. Their first meeting, where they discussed Wiener's proof of theergodic theorem, went so well that Pitts moved toGreater Boston to work with Wiener. While Pitts was an unofficial student under the aegis of Wiener at MIT until their acrimonious parting in 1952, he formally enrolled as a graduate student in thephysics department during the 1943–1944 academic year and in theelectrical engineering department from 1956–1958.[11][12]
In 1944, Pitts was hired byKellex Corporation (later acquired in 1950 byVitro Corporation) in New York City, part of theAtomic Energy Project.[13]
From 1946, Pitts was a core member of theMacy conferences, whose principal purpose was to set the foundations for a general science of the workings of the human mind.
In 1951, Wiener convincedJerome Wiesner to hire some physiologists of the nervous system. A group was established with Pitts, Lettvin, McCulloch, andPat Wall. Pitts wrote a large dissertation on the properties of neural nets connected in three dimensions. Lettvin described him as "in no uncertain sense the genius of the group … when you asked him a question, you would get back a whole textbook."[14] Pitts never married.[1] Pitts was also described as an eccentric, refusing to allow his name to be made publicly available. He continued to refuse all offers of advanced degrees or positions of authority at MIT, in part as he would have to sign his name.
In 1952, Wiener suddenly turned against McCulloch—his wife, Margaret Wiener, hated McCulloch[15]—and broke off relations with anyone connected to him, including Pitts.[15]
Although he remained employed as aresearch associate in the Research Laboratory of Electronics at MIT "as little more than a technicality"[16] for the rest of his life, Pitts became increasinglysocially isolated. In 1959, the paradigmatic "What the Frog’s Eye Tells the Frog’s Brain" (credited toHumberto Maturana, Lettvin, McCulloch and Pitts) conclusively demonstrated that "analog processes in the eye were doing at least part of the interpretive work" in image processing as opposed to "the brain computing information digital neuron by digital neuron using the exacting implement of mathematical logic", leading Pitts to burn his unpublished doctoral dissertation on probabilistic three-dimensional neural networks and years of unpublished research. He took little further interest in work, excepting only a collaboration with Lettvin and Robert Gesteland which produced a paper onolfaction in 1965.
Pitts died in 1969 of bleedingesophageal varices, a condition usually associated withcirrhosis andalcoholism.[1][2][15]
There was just one person who wasn't happy about the reunion: Wiener's wife. Margaret Wiener was, by all accounts, a controlling, conservative prude—and she despised McCulloch's influence on her husband. McCulloch hosted wild get-togethers at his family farm in Old Lyme, Connecticut, where ideas roamed free and everyone went skinny-dipping. It had been one thing when McCulloch was in Chicago, but now he was coming to Cambridge and Margaret wouldn't have it. And so she invented a story. She sat Wiener down and informed him that when their daughter, Barbara, had stayed at McCulloch's house in Chicago, several of "his boys" had seduced her. Wiener immediately sent an angry telegram to Wiesner: "Please inform [Pitts and Lettvin] that all connection between me and your projects is permanently abolished. They are your problem. Wiener." He never spoke to Pitts again.
| International | |
|---|---|
| Academics | |
| People | |
| Other | |
