GradIEEEnt half decent: The hidden power of imprecise lines
Why Hacker News recommends it
Cited as a fun, unconventional example of neural networks built from floating point error.
What it is
Tom 7 (suckerpinch) delivers a long, comedic digression on gradient descent and floating-point imprecision. He shows how rounding behavior can supply the nonlinearity needed to build a neural network.
Recommended by 1 HN commenters across 1 different months, 2023 to 2024.
What Hacker News said
Recommends jcparkyn · 2024-05 · on “Your Transformer is Secretly Linear”
A fun example of that (making a neural network using floating point error as a source of non-linearity): [this video]
Cites Uehreka · 2023-10 · on “"We'll call it AI to sell it, Machine Learning to Build it"”
I don’t get what people are trying to say when they say these kinds of things about AI. That human-level writing is as simple as a linear regression? That we could’ve had computer programs capable of human-level writing decades ago? Have they not used these AIs enough to see how powerful they are? Are they seeing the bad outits and thinking that AIs are always doing that poorly? Like seriously, if you’re telling me that it was obvious that a “linear regression” could pass the LSAT I’ve got a macvlan to sell you. Edit: they’re also literally not linear regression! [this video]
Cites jcparkyn · 2024-10 · on “Were RNNs all we needed?”
> squash an output into a range This isn't the primary purpose of the activation function, and in fact it's not even necessary. For example see ReLU (probably the most common activation function), leaky ReLU, or for a sillier example: [this video]