SIGNAL//DESK
AI/MLsrc: curated AI glossary

Machine learning

Machine learning is a way of teaching computers to do things by showing them many examples instead of giving them a strict list of instructions to follow.

A subfield of AI focused on building systems that identify statistical patterns within datasets to make predictions or decisions, rather than relying on hard-coded logic.

A field in which systems infer patterns from data rather than following explicit rules, improving performance on a task as they are exposed to more examples.

evolution

  1. 1952 · history
    Arthur Samuel's Checkers Program

    Arthur Samuel develops a self-learning checkers program, coining the term 'machine learning' to describe software that improves through experience.

  2. 1958 · history
    The Perceptron

    Frank Rosenblatt creates the Perceptron, an early artificial neural network capable of pattern recognition through iterative weight adjustment.

  3. 1986 · history
    Backpropagation Popularization

    Rumelhart, Hinton, and Williams demonstrate that backpropagation allows multi-layer neural networks to learn complex internal representations.

  4. 1997 · history
    Deep Blue vs. Kasparov

    IBM's Deep Blue defeats world chess champion Garry Kasparov, showcasing the power of search algorithms and pattern-based evaluation.

  5. 2012 · history
    AlexNet Breakthrough

    The AlexNet architecture wins the ImageNet challenge by a wide margin, triggering the modern era of deep learning and GPU-accelerated neural networks.


← all terms