perceptronCobol

It was fun. Not even that hard, to be honest. https://github.com/victorqribeiro/perceptronCobol

I used to work in a bank with people that came from mainframes. They use to talk about Cobol and how it was a well paid job, cause of the lack of programmers. As a way of learning the language I end up writing a perceptron in it [1]. It was a fun exercise. 1 - https://github.com/victorqribeiro/perceptronCobol

I don't know if this could be considered "learning" in the sense that you mean, but I chose code that I wrote in a familiar language and re-wrote it in Cobol. It was fun and I end up learning a lot. https://github.com/victorqribeiro/perceptronCobol

Really? COBOL is younger than neural network algorithms and seems like a prime language to write neural networks! The first artificial neural network was invented in 1958 by psychologist Frank Rosenblatt. Called Perceptron, it was intended to model how the human brain processed visual data and learned to recognize objects. Other researchers have since used similar ANNs to study human cognition. [0] COBOL is a high-level programming language first developed by the CODASYL Committee (Conference on Data Systems Languages) in 1960. [1] A COBOL-like neural network simulation language based on layer macro definition [2] Perceptron in COBOL [3] My first program in COBOL, a single neuron neural network. [4] [0] https://www.computerworld.com/article/2591759/artificial-neural-networks.html [1] http://www.csis.ul.ie/cobol/course/COBOLInt

I once wrote a perceptron in cobol, just for fun. https://github.com/victorqribeiro/perceptronCobol It was a challenge I was able to do in about 4 hours of code I didn't find that much harder to program in a Cobol (given that you use the right IDE, I wrote it in Gedit and the identation was a pain at first)