SIGNAL//DESK
AI/MLsrc: curated AI glossary

Training

Training is like teaching a student by showing them many examples and letting them practice until they get the right answers more often.

Training is the iterative process of updating a model's internal parameters based on a dataset to reduce error and improve performance on specific tasks.

The process of adjusting a model's weights to minimise a loss on data: pre-training builds general capability, while post-training (fine-tuning, RLHF) shapes behaviour and alignment.

evolution

  1. 1958 · history
    Perceptron Learning Rule

    Frank Rosenblatt introduced the first algorithm for training a single-layer neural network using iterative weight adjustments.

  2. 1986 · history
    Backpropagation Popularization

    Rumelhart, Hinton, and Williams demonstrated that backpropagation could efficiently train multi-layer neural networks.

  3. 2006 · history
    Deep Belief Networks

    Geoffrey Hinton introduced greedy layer-wise pre-training, enabling the effective training of deeper neural architectures.

  4. 2017 · history
    Transformer Architecture

    The introduction of the Transformer model enabled massive parallelization of training, shifting the paradigm toward large-scale pre-training.

  5. 2020 · history
    Few-Shot Learning via Scaling

    GPT-3 demonstrated that training massive models on diverse datasets allows for emergent capabilities without task-specific fine-tuning.


← all terms