Detroit, 1935. Walter Pitts is running down the street, chased by bullies. He ducks into the public library to take a shelter, and he hides. He hides so well that the library staff don't even realize he's there, and they close for the night. Walter Pitts is locked inside.
He starts reading a really fascinating book that he discovers on the shelf. He reads the book from beginning to end for 3 days. The famous demonstration that 1+1=2 does not occur until page 379 of the two-thousand-page book, which is a treatise on formal logic. Because he thinks he has discovered a number of errors, Pitts chooses to write a letter to one of the authors, British philosopher Betrand Rusell.
Several weeks go by, and Pitts gets a letter in the mail postmarked from England. It's Betrand Rusell. Rusell thanks him for writing and invites Pitts to become one of his doctoral students at Cambridge.
Unfortunately, Walter Pitts must decline the offer - because he's only 12 years old and in the 7th grade. 3 years later, Pitts learns that Rusell will be visiting Chicago to give a public lecture. He runs away from home to attend. He never goes back.
At Russell's lecture, Pitts meets another teenager in the audience, named Jerry Letvin. Pitts only cares about logic. Letvin only cares about Poetry and, a distant second, medicine. They become inseparable friends.
Pitts begins hanging out around the University of Chicago campus, dropping in on all classes; he still lacks high school diploma and never formally enrolls. One of these classes is by the famed German logician Rudolf Carnap. Pitts walks into his office hours, declaring he's found a few 'flaws' in Carnap's latest book.
Skeptically, Carnap consults the book; Pitts, of course is right. They talk a while, then Pitts walks out without giving his name. Carnap spends months asking around about the 'newboy who knew about logic'. Eventually Carnap finds him and makes him his advocate, Pitts persuading the university to give him a menial job so he will atleast have some income.
It's now 1941. Letvin - still a poet first, in his own mind - has, despite himself, gotten into medical school at the university of Illinois, and finds himself working under the brilliant neurologist Warren McCulloch, newly arrived Yale. One day Letvin invites Pitts over to meet him.
At this point, Letvin is 21 and still living with his parents. Pitts is 17 and homeless. McCulloch and his wife take them both in.
Throughout the year that follows, McCulloch comes home in the evenings and he and Pitts - who is barely older than McCulloch's own children - regularly stay up past midnight tallking.
Intellectually, they are the perfect team: the esteemed midcareer neurologist and the prodigy logician. One lives in practice - the world of nervous systems and neuroses - and the other lives in theory - the world of symbols and proofs.
They both want nothing more than to understand the nature of truth: what it is, and how we know it. The fulcrum of this quest - the thing that sits at the perfect intersection of their two disparate worlds - ofcourse is, THE BRAIN.
It was already known by the early 1940s that the brain is built of neurons wired together, and that each neuron has 'inputs' (dendrites) as well as 'outputs' (axon). When impulses coming into a neuron exceed a certain threshold, then that neuron, in turn, emits a pulse ⚡. Immediately, this begins to feel, to McCulloch and Pitts, like logic: the pulse or its absence signifying ON or OFF, YES or NO, TRUE or FALSE.
They realize that a neuron with low-enough threshold, such that it would fire if any of its inputs did, functioned like a physical embodiment of the logical OR. A neuron with high-enough threshold, such that it would only fire if all its inputs did, was a physical embodiment of the logical AND. There was nothing, that could be done with logic - they start to realize- that such a 'neural network', so long as it was wired appropriately, could not do.
Within months they had written a paper together. They called it " A Logical Calculus of Ideas Immanent in Nervous Activity."
"Because of the "all-or-none" character of nervous activity", they write, "neural events and the relations among them can be treated by means of propositional logic. It is found that the behavior of every net can be described in these terms..... and that for any logical expression satisfying certain conditions, one can find a net behaving in the fashion it describes."
The paper is published in 1943 in the Bulletin of Mathematical Bio-physics. To Letvin's frustration, it makes little impact on the biology community. To Pitts' dissapointment, the neuroscience of the 1950s, notably a landmark study of the optical nerve of the frog -- done by none other than his best friend, Jerry Letvin -- will show that neurons appear to be much messier than simple "true" or "false" circuits he envisioned. Perhaps propositional logic -- its ands, ors, nots -- was not, ultimately, the language of the brain, or at least not in so straightforward as a form. This kind of impurity saddened Pitts.
But the impact of the paper - of those long conversations into the night at McCulloch's house - would be enormous, if not entirely in the way that McCulloch and Pitts envisioned. It would be the foundation for a completely new field: the project to actually build mechanisms out of these simplified versions of neurons, and see just what such "mechanical brains" could do.
Sourced and made with love , from the captivating article "THE ALIGNMENT PROBLEM, Machine Learning and human values" by Brian Christian.
Stay tuned as we embark on the journey to discover AI evolution! Enjoy!