XORTRAN: A FORTRAN IV Neural Network for IBM 1130 and PDP-11 Computers
By
rahen
Crisp on the outside, thoughtful on the inside. A keeper.
Summary
XORTRAN is a multilayer perceptron neural network written in FORTRAN IV that runs on vintage IBM 1130 (1965) and PDP-11 (1970-1980) computers. The project implements the classic XOR problem on historical hardware, with the IBM 1130 version expected to take around 30 minutes to train on actual hardware, though this couldn't be measured due to the available IBM 1130 not being fully operational. The project is hosted on GitHub as an open-source implementation of neural networks on retro computing platforms.
Key quotes
· 4 pulledXORTRAN is a multilayer perceptron (MLP) neural network written in FORTRAN IV, compiled and executed for both the IBM 1130 (1965) and the PDP-11 (1970~1980).
For the IBM 1130, the code is written in IBM 1130 FORTRAN language from 1965, the manual for which can be consulted online.
Training the network on the real hardware is expected to take probably around 30 minutes, however, this couldn't be measured, as the only IBM 1130 available to me is not fully operational.
A neural network for the IBM 1130 and PDP-11. Contribute to dbrll/Xortran development by creating an account on GitHub.
You might also wanna read
Transformer AI Model Successfully Runs on Commodore 64 with 25,000 Parameters
A developer has successfully implemented a 25,000-parameter transformer neural network (the same architecture used by ChatGPT, Claude, and G
Transformer Neural Network Implemented in HyperTalk for Classic Macintosh
A complete transformer neural network implemented entirely in HyperTalk, a 1987 scripting language designed for interactive card stacks, run
NVIDIA Announces "Hack for Impact" London Event for Autonomous AI Agent Development
NVIDIA is hosting a "Hack for Impact" event in London, challenging participants to build autonomous agentic applications using open-source m
MerLean-Prover: A Recursive Agent Harness for Lean 4 Theorem Proving Outperforms Baselines
MerLean-Prover is an end-to-end Lean4 theorem prover that replaces 'sorry' declarations with kernel-checkable proofs using three agent types
ZX Spectrum BASIC interpreter rebuilt from scratch to run natively in web browsers
A developer has rebuilt the ZX Spectrum's BASIC interpreter from scratch to run in a web browser, without emulating the original Z80 hardwar
Reflections on DwarfStar 4's rapid rise in local AI inference
The author reflects on the unexpected popularity of DwarfStar 4 (DS4), a local AI inference project. They attribute its success to the conve
