Backward propagation

{
  "id": "MLC-T-CHM-001091",
  "term": "Backward propagation",
  "field": "Chemistry",
  "definition": "An algorithm used in artificial neural networks to train the model by adjusting its internal weights. It calculates the gradient of the loss function with respect to each weight by propagating the error from the output layer back to the input layer. This method is a practical application of the chain rule from calculus for updating network parameters during supervised learning.",
  "synonyms": [
    "back-propagation learning rule",
    "back-propagation of errors"
  ],
  "subject": "Analytical Chemistry",
  "see_also": [
    "supervised classification"
  ],
  "references": [
    "PAC, 2016, 88, 407. 'Vocabulary of concepts and terms in chemometrics (IUPAC Recommendations 2016)' on page 426 (https://doi.org/10.1515/pac-2015-0605)"
  ],
  "url": "https://mlchart.com/terminology/chemistry/backward-propagation/"
}