Hacker News new | past | comments | ask | show | jobs | submit

The Smallest Brain You Can Build: A Perceptron in Python

https://ranpara.net/posts/perceptron-explained-from-scratch/
280DevarshRanpara | | 63 | HN
loading story #48445662
loading story #48446686
loading story #48443684
rahen | parent | next
In the early days of machine learning (before the first AI winter), networks like this were often implemented and trained in hardware: https://en.wikipedia.org/wiki/ADALINE

That was the first thing that came to mind when I read "the smallest brain you can build". Nowadays, that "small brain" would likely be built on a breadboard using op-amps instead.

zkmon | parent | next
The IF statement is the root creator of software programming. It has the ability to compare two values against each other and branch out to blocks of instructions. So it is perceiving (reading), decision making and routing - all that which differentiate life from inanimate objects. The AI agents perform the exact same loop, by delegating the first two steps to a model.

Going further backwards, the transistor (or a PNP junction) is the hardware level enabler of the IF statement. The action (switching) driven by the current which in turn controls other switches, is the first manifestation of "observe and act" by inanimate things at the speed of electricity.

Mechanical equivalents existed ofcourse - speed of a governer which controls the flow of fuel which in turn controls the speed of the governer.

loading story #48442993
loading story #48443000
loading story #48442977
loading story #48442563
loading story #48445899
ankit84 | parent | next
I learnt a lot today from the interactive demo. You have the best clarity and right skill to educate
DevarshRanpara | parent
Thank you, I will try to make more demo on other concepts.
trekhleb | parent | next
Nice and minimalistic

I played with similar approach in JavaScript and built a NanoNeuron https://github.com/trekhleb/nano-neuron (it is more verbose than Python though)

loading story #48446497
loading story #48443807
Bimos | parent | next
> A perceptron *is* the smallest brain you can build.

> In 1958, a researcher named Frank Rosenblatt built a machine *he called* the perceptron.

> It was *inspired* by a single brain cell, a neuron.

loading story #48442009
loading story #48443562
esafak | parent | next
If you want to learn the fundamentals of ML I recommend a book, such as Deep Learning: Foundations and Concepts by Chris Bishop. If you insist on staying online, one option is https://course.fast.ai/

If you don't know ML I don't think you're going to learn much through ad hoc demos.

mysterydip | parent | next
Checked out the book on your recommendation, and they even have a free online option on their site! Very generous: https://www.bishopbook.com/
rishabhaiover | parent | next
This book equipped me with the right intuition and tools to visualize machine learning. I wish I was smart enough to hold it all together.
andai | root | parent
>I wish I was smart enough to hold it all together.

I used to have a wife, but they took her in the divorce!

The human mind isn't very good at correlating its contents[0]. You can "know" something for years without realizing its implications.

The human mind traverses its knowledge like a man with a small flashlight in total darkness. Our beam of attention is small and narrow, so you need to put the right things in it, or the magic doesn't happen.

This has important implications for learning. I don't know what they are though.

Probably something like, "you can know something without knowing what it means." You haven't connected it to the things it's supposed to be connected to yet. I don't know how to fix that though. (Something involving the Feynman technique, maybe?)

[0] H.P. Lovecraft quote - https://www.goodreads.com/quotes/193944-the-most-merciful-th...

stuxnet79 | parent | next
I didn't know Bishop had released a new textbook. I will have to take a look at it. I wasn't the biggest fan of his Pattern Recognition book as I found it overly dense. I much preferred the Murphy and Alpaydin books.

EDIT: His son is co-author?

zxexz | root | parent
I still find his pattern recognition book useful and informative. It may be dense, but some of us consider that a positive for 'reference' literature. That book was one of very few that still holds up well fr when it was published - truly in on of the last "dark ages" of ML.

I think those down voting you are perhaps overly eager. I upvoted. Grab "Deep Learning" - you'll find it useful, imteresting, and likely less 'dense' in the negative sense!

stuxnet79 | root | parent
Appreciate your comment. I skimmed the online version and it covers all the 2010s era developments all the way to Transformers which is enough to earn it a spot on my bookshelf.

> Grab "Deep Learning" - you'll find it useful, imteresting, and likely less 'dense' in the negative sense!

Absolutely! I just ordered it and it's enroute :)

DevarshRanpara | parent
This fast AI course looks soo good man! Definitely I will start learning soon. Thank you!
warengonzaga | parent | next
This is amazing insight, thanks for sharing!
| parent | next
{"deleted":true,"id":48440065,"parent":48440064,"time":1780878517,"type":"comment"}
charcircuit | parent | next
I can build a smaller brain.

f(x) = 0.

loading story #48443590
lioeters | parent | next
I take your brain, add a couple more rules, and presto! It can perform any computation.

    Ix = x
    Kxy = x
    Sxyz = xz(yz)
rippeltippel | parent | next
That's great, now make it learn something :)
jeffwass | root | parent
It's the simplest AI nihilist!
loading story #48443167
loading story #48446319
| parent | next
{"dead":true,"deleted":true,"id":48443189,"parent":48440064,"time":1780911794,"type":"comment"}
b33j0r | parent
Okay, it’s conscious. But can it run doom? I rest my case.
Waterluvian | parent
Can you run Doom? Let’s find out!
Rapzid | root | parent | next
I can speed run Doom. Appeal denied!
| root | parent | next
{"deleted":true,"id":48440409,"parent":48440363,"time":1780882293,"type":"comment"}