Xortran - A PDP-11 Neural Network With Backpropagation in Fortran IV (opens in new tab)

(github.com)

46 pointsrahen4mo ago11 comments

11 comments

When I studied cognitive psychology I remember one of the professors told us about how they had been playing with implementing neurals nets on their PDP11 back in the day. I remember thinking that had to have been be a total waste of time. Silly me.

rahenOP4mo ago

The first convolutional neural network, the Neocognitron, was AFAIK implemented on a PDP-11 as well: https://www.semanticscholar.org/paper/Neocognitron%3A-A-neur...

No backpropagation back then, this only appeared around 1986 with Rumelhart, probably on VAX machines by that time.

The 11/34 was hardly a powerhouse (roughly a turbo XT) but it was sturdy, could handle sustained load and its FPU made the whole difference.

PaulHoule4mo ago

If I remember right that FORTRAN IV compiler really sucked, it used a stack machine and that floating point accelerator "sucked" by normal standards but was actually 100% effective at accelerating that stack machine. The FORTRAN 77 compiler that came latter was better.

3 more replies

nxobject4mo ago

I always found it annoying that Rumelhart and McClelland named their books with the acronym “PDP” - Parallel Distributed Processing. Now I know that they were probably aware of the name collision…

fortran774mo ago

I did a few systems like this in the early 80s, but by then I was on a Vax and running Fortran 77.

Nice to see this. It’s a good way to learn the basics without getting bogged down with modern complexities.

j / k navigate · click thread line to collapse