Claude Shannon Demonstrates Machine Learning (1952)

https://techchannel.att.com/play-video.cfm/2010/3/16/In-Their-Own-Words-Claude-Shannon-Demonstrates-Machine-Learning

by jchallis • 5 years ago

209 51 5 years ago

techchannel.att.com

What a grave misunderstanding! What he is demonstrating is remembering, or memory.

It appears that the state of the mouse is [X, Y, Heading], where X and Y are discrete positions in the available cells.

Once the maze has been solved by "a rather involved strategy of trial and error", the solution is saved, and for any of the known states, the mouse "remembers" its way to the exit of the maze.

optimuspaul• 5 years ago

sounds like learning to me. In the 1950s this was somewhat advanced machine learning.

witherk• 5 years ago

I kinda thought the point of the title was to show how what counts as AI is just the newest form a programming.

DaniloDias• 5 years ago

When standing on the shoulders of giants, it’s best to be compassionate in evaluating the implementations of the past.

jchallis2• 5 years ago

By any reasonable definition of learning, the mouse adapts to a new situation.

ARandomerDude• 5 years ago

1952. After 70 years, millions of people, and billions of dollars, it makes sense that our algorithms are more sophisticated and our definitions more precise.

coldtea4• 5 years ago

All learning amounts to remembering. A machine learning model is basically remembered weights. Everything we've learned is what we remember as solidified in our neurons, etc.

Note that learning is not about discovering yourself. You also learn if you're capable of remembering (and optionally applying) something that somebody else taught you. Students e.g. learn a formula for X, the periodic table, etc.

And this contraption not only remembers (that is, learns), but also has an algorithm to figure the solution in the first place (that is, tries and discovers).

So the title "machine learning" or even "AI" is perfectly legitimate. It's not GAI, but it's also not 2020 (not that we have GAI in 2020).

CodeGlitch• 5 years ago

2021 :)

Jugurtha2• 5 years ago

All learning amounts to remembering. A machine learning model is basically remembered weights. Everything we've learned is what we remember as solidified in our neurons, etc.

That's "not even wrong", as Pauli would say. Your paragraph suffers from using a shaky non inversible analogy:

Machine learning often uses an analogy for the brain, neurons, activation functions, etc. Some accuracy about the real world is sacrificed in that analogy for the sake of being useful and to have something to reason with and shared taxonomy. We accept that loss for the sake of being productive and for lack of actual equivalents.

What your first paragraph did is use that analogy of the brain used in machine learning, that is shaky to begin with, and use it to reason about the biological brain as if we did not have the actual thing.

In other words, we had a biological brain that we clumsily modeled to get work done in ML, and the paragraph used that model to reason about the brain itself. Similar to how you translate from French --> English --> French and get a different output than the input.

Remembering certainly plays a role in learning, though it is but one component. For it to be what learning is, everything has to be exactly the same with every instance.

To use the analogy, a machine learning model returns predictions/output for instances it has not necessarily seen. Our brain produces outputs based on situations that had not yet happened, at least not in the 'anisotropic time' universe, before that.

What do you think?

recursivedoubts• 5 years ago

I mean, what did Claude Shannon know about computers or anything else?

2mol• 5 years ago

I recently watched a charming documentary on Shannon, called The Bit Player [0]. The film has some annoying flaws, but it really highlights how much Shannon was outside the box for a mathematician. He seems to have been extremely playful, and tinkering with hardware projects throughout his life.

How he even managed to make a (very limited) endgame chess computer [1] ~70 years ago still blows my mind.

[0] https://thebitplayer.com/

[1] https://www.chess.com/article/view/the-man-who-built-the-che...

jointpdf• 5 years ago

Also, don’t miss Turing’s paper describing how to build a chess engine from scratch. The link to the .pdf is at the bottom of this contextual blurb:

https://historyofinformation.com/detail.php?id=3905

jazzyjackson• 5 years ago

What a wonderful era of creativity in machine design. Building a machine to reproduce the behavior of living systems goes a long way back, and this mouse acting like a mouse makes me think of a great documentary on automata, spending some time talking about the people and politics around building these fantastically expensive robotic birds and swans and whole towns driven by a clock. [1]

Building a machine that mimics neural processing is just a continuation of that tradition. One other machine that amazed me is Paul Westons's numa-rete, an early attempt at neural networks composed of 400 "synapses" which can count the number of objects on its surface without any CPU to coordinate it, just direct parallel analog computation. A good explanation is here [2], this was in 1961.

`What will be done is to show what is inside, revealing how little intelligence it really had. However, many uninitiated persons who tried and failed at the time to “trick” it into error by, e.g., inserting objects within holes in larger objects were ready to believe that it was intelligent`

[1] https://youtu.be/NcPA0jvp9IQ

[2] https://web.archive.org/web/20160401023457/http://bcl.ece.il...

sarthakjain2• 5 years ago

It's interesting to note why this was considered AI in 1952 and some may not consider it to be AI today. The AI was the search algorithm to find an effecient solution to the maze, not the mouse being able to navigate it later in a second run. The second run was just a demonstration of it having found the solution demonstrating it's intelligence. The actual intelligence was it's first run through the maze. Almost any configuration of the maze could be solved using algorithms like depth first, breadth first and a star search (didn't check which one the video demonstrates). Even though the algorithm was trivial it's ability to be applied to problems of today is still extraordinary. Nerural networks being equally trivial algorithms capable of remarkable things. Id argue this is as much AI today as it was back then, just more people know how Shannon performed this magic trick.

mkl95• 5 years ago

A star search as we know it wasn't developed until the mid 60s.

salty_biscuits• 5 years ago

I always say that AI is a forever moving goal post. It is simply a task a human can do that you wouldn't expect a machine to be able to do. So as soon as a machine can do it, people no longer consider it intelligent (i.e. it is just A*, it is just a chess engine, it is just a network picking up on patches of texture, ..., it isn't really "intelligent").

Jasper_• 5 years ago

This is because we originally thought "only a human would be able to play chess", "only a human would be able to drive a car". The thinking there is that if we were to solve these problems, we'd have to get closer to a true artificial intelligence (the kind that today we'd call "AGI" because "AI" doesn't mean anything anymore).

This line of thinking has been shown to be pretty faulty. We've come up with engines and algorithms that can play Go and Chess, but we aren't any closer to anything that resembles a general intelligence.

peter303• 5 years ago

The term A.I. was coined four years later in 1956. But an earlier term cybernetics encompassed some aspects of A.I.

sesqu• 5 years ago

Shannon did not use the word intelligence to describe the mouse in this demonstration - instead, he talked about learning. That's why the second run was considered more important than whatever algorithm was used to solve the maze.

To that end, I'm curious about their cache invalidation solution. Are there timestamps, or is it a flag system?

gnramires• 5 years ago

I'm curious about their cache invalidation solution

My guess: there would be a model somewhere (probably a binary relay map of walls) of the maze, and as soon as the mouse hits an inconsistency, this map is updated. So there isn't really a cache, it's more like a model, or perhaps you can think of collision-based cache (model) invalidation. The mouse probably then follows the solution to this modified maze, modified only insofar as it has measured modifications.

Is there a technical specification somewhere? I'd certainly be curious to read it.

mywittyname2• 5 years ago

You are being far, far, far too generous with the complexity of this design if you think there's some kind of cache invalidation. It's a purely mechanical computer, which means it is going to be very simple in abstract design, because doing anything even mildly complex would require an insane amount of space.

I can't find design documents for this, but I can make a pretty educated guess about its design.

Each square has two relays, representing the number of left turns necessary to exit the square. Each time a whisker touches a wall, a signal is sent to a mechanical adder which will add 1 to the relays in the space. When the mouse enters a square, a "register" is set with a value, based on if it entered from the left, top, right, or bottom, then the mouse is turned and the register decremented until it hit 0, then the mouse attempts to walk in the indicated direction.

The maze ends up looking something like this:

    +-----+
    |0|1 1|
    +-- - +
    |1 3|0|
    + --- +
    |1 3|x|
    +-- --+

Where the mice starts on x and turns the number of times in each square. You can actually put the mouse down anywhere and it will exit the maze, if the walls are left unchanged.

YeGoblynQueenne5• 5 years ago

> The AI was the search algorithm to find an effecient solution to the maze, not the mouse being able to navigate it later in a second run.

But that's not the whole story! The program can update its solution of the maze when the maze changes, but it is capable of only changing that part of the solution that has actually changed. When Shannon changes the maze and places Theseus in the modified part of the maze, I kind of rolled my eyes, sure that it was going to start a new search, all over again, but I was wrong: it searches until it finds where the unmodified part of the maze begins, then it continues on the path it learned before.

It seems that, in solving the maze, the program is building some kind of model of its world, that it can then manipulate with economy. For comparison, neural nets cannot update their models - when the world changes, a neural net can only train its model all over again, from scratch, just like I thought Theseus would start a whole new search when Shannon changed the maze. And neural nets can certainly not update parts of their models!

This demonstration looks primitive because everything is so old (a computer made with telephone relays!), but it's actually attacking problems that continue to tie AI systems of today into knots. It is certainly AI. And, in "early 1950's", it's AI avant la lettre.

jmoss20• 5 years ago

What is transfer learning if not partially updating the model...?

marcinzm• 5 years ago

For comparison, neural nets cannot update their models - when the world changes, a neural net can only train its model all over again, from scratch

I mean, sure they can. Training a neural network is literally nothing but the network's model being updated one batch of training examples at a time. You can stop, restart, extend or change the data at any point in the process. There's whole fields of transfer learning and online learning which extend that to updating a trained model with new data.

edit: Also in a way reinforcement learning where the model controls the future data it sees and updates itself on.

sarthakjain2• 5 years ago

Great observation. The solution to the update problem is relatively simple. It doesn't do a search again on update. Instead everytime it encounters an update in what it knows, it just changes the data stored in memory. All it is doing is updating its learned representation. After this it still knows what the other obstacles are without having to do DFS or BFS again. If the solution was a graph, it just deleted a edge it still knows what all the other edges are. If it encounters another change it updates the state of the graph again.

With regards to Neural Networks, if they are given a reward function, which can be dynamically evaluated (in this case did I reach the end or not) they are pretty good at learning without feedback.

jzer0cool2• 5 years ago

Here is our current modern version of mouse maze competition: https://youtu.be/NqdZ9wbXt8k?t=86 ... its so smooth. Would love to learn more how to build one of these if anyone has suggestions starting with basic servos for a light introduction.

tachyonbeam• 5 years ago

I don't think you'd want to use servos to drive the wheels for something like this. You probably want very fast steppers (so you can get precise rotations) or geared DC motors (so you can move very fast). I'm assuming the robot has some very basic black and white computer vision, or maybe even simple laser range finders, which would be simpler to work with and more likely to generalize to new mazes.

Here is an example of an inexpensive laser range sensor: https://www.ebay.com/itm/TOF10120-ToF-Laser-Range-Sensor-Las...

jzer0cool2• 5 years ago

added to my arduino projects I can try! thanks!

blackrock• 5 years ago

How did he store the memory? Using some kind of small gearings inside the mouse?

jchallis2• 5 years ago

Electromechanical relays below the maze. Phone switches at the phone company labs.

mywittyname2• 5 years ago

I couldn't find any design details online for how this was built. I'd love to read more technical details.

Since this is purely mechanical, it is probably extremely simple in design. I suspect that there are two relays (representing 2 bits) under each square's reed switch, encoding the number of "left turns" to make upon entering that square. The whiskers probably trigger a simple incrementer for each square to keep track of the number of left turns to make. When the mouse is dropped in a space, it probably turns left to reorient itself, but then knows the direction to walk once it reaches a point in the path where it has solved before because the number of left turns it needs to make in that space is already solved.

YeGoblynQueenne5• 5 years ago

The relays are behind the maze- what's under the maze is a couple of arms with electromagnets that move to drag the mouse around the maze.

In fact the "relays" are an electromechanical computer. I don't know much about the computers of that era, but since this is in Bell Labs in the early '50s, it may have been the model VI:

https://en.wikipedia.org/wiki/Model_V#Model_VI

YeGoblynQueenne5• 5 years ago

From the title I was sure that this would be some horrible misuse of "machine learning" to stand-in for "AI" but while Shannon himself never uses the term in the video, the title seems accurate enough.

To summarise: a model mouse, named Theseus, is moved around a maze by a system of electromagnets placed under the maze and guided by an electromechanical computer (made with telephone relays). The computer is from Bell Labs and given the date listed for the video ("early 1950's") it may be a Model VI.

The program that drives the mouse is a combination of a search algorithm with some kind of modular memory. The mouse first finds its way around the maze by successivly trying a set of four moves at right angles. The sequence seems to be: move forward; if that's impossible, turn 90° CW; repeat. This eventually finds a path to the end of the maze, where a goal is placed (possibly magnetic). In more modern terms, the program learns a plan to navigate the maze. Once the plan is learned it can be re-used any number of times to solve the maze without any more searching.

The interesting thing is that, if the maze changes, the program only needs to replace part of its learned plan. Shannon demonstrates this by moving around some of the walls of the maze, which are modular segments. Theseus initially enters its searching routine, until it finds its way to the part of the maze that it knows already. After that, it's smooth sailing, following the plan it already knows.

I have no idea what that technique is that does that. If I guessed, I'd guess that the program has a model of its world -a map of the maze- or, more interestingly, it builds one as it goes along. When the maze changes, the program updates its model, but it is able to update only as much of the model as corresponds to the part of the world that has really changed. This suggests some kind of object permanence assumption, an encoding of the knowledge that if the state of some entity in the world is not known to have changed, then it has not changed. Or, in other words, some solution to the frame problem (which was actually described about a decade later than Shannon's demonstration).

Note well that modern AI systems very rarely exhibit this ability. For instance, deep neural networks cannot update their models - not partly, not wholesale. Like I say, I have no idea what the approach is that is demonstrated. It may be something well-known but rarely used these days. It may be something that Shannon came up with before John McCarthy fathered AI and so it never really caught on as an AI approach. If anyone knows, please do tell, I'm very curious.

In any case "Theseus" (rather, its AI) seems to exhibit what McCarthy called "elaboration tolerance", making formal representations of facts that can be modified easily:

http://jmc.stanford.edu/articles/elaboration.html

dang• 5 years ago

If curious see also

2014 https://news.ycombinator.com/item?id=7758547

I think there have been other threads too?

zappo2938• 5 years ago

"The norms of consumer culture and domesticity were disseminated via new and popular forms of entertainment – not just the television, which became a fixture in middle-class American households during the 1950s, but also women’s magazines, popular psychology, and cinema. Shows promoting the values of domesticity, like Leave it to Beaver and Father Knows Best, became especially popular. These shows portrayed the primary roles of women as wives and mothers. Lucille Ball, in I Love Lucy, inevitably met with disaster whenever she pursued job opportunities or interests that took her outside of the household." [0]

What is striking about this video is not only the advancement of technology but also women actively working outside the home which was counter culture for the time even though the one woman sitting down symbolically is in a subordinate position with the man standing over her.

[0] https://www.khanacademy.org/humanities/us-history/postwarera...

(Yeah, I know better than to mention something like this here.)

heimatau2• 5 years ago

I'm no fan of Youtube but...not being able to increase the playback speed is highly sought after when I watch videos on any sites (like the OP on att.com). Here is YT's version of the same video [1].

Edit: I removed the link because the pixelation was unbearable.

[1] - removed

jmiskovic• 5 years ago

There are addons for Chrome / Firefox [0] that map keyboard shortcuts to playback speed control over any HTML5 video. It works amazingly well.

[0] https://github.com/codebicycle/videospeed

heimatau2• 5 years ago

It doesn't work with all videos and it's what I currently use. I might be having some conflicting plugins but I like the setup/attempt.

sjg0072• 5 years ago

Honestly this is pretty impressive even today. It'd be fun to work with a school class to implement it as a project. I mean it's the kind of thing you can gloss over and say, here's the algorithm but then to actually build it is really interesting. Maybe a lego kit or something.

AndrewKemendo• 5 years ago

Of note, he talks about using Bell systems for guided missiles.

I always want to reinforce that cutting edge computing systems and the defense department have always been bedfellows. The DoD isn't new to technology, even machine learning or reinforcement learning (The US Air Force sponsored the Dartmouth Conference on AI after all).

082349872349872• 5 years ago

Related, from 1953, Shannon's "Mind Reading Machine": https://literateprograms.org/mind_reading_machine__awk_.html

Claude Shannon Demonstrates Machine Learning (1952)

Related Stories