Classification
Sorting inputs into categories by teaching a computer to recognize patterns, similar to how a person might sort mail into 'junk' and 'important' piles based on what the envelopes look like.
A supervised machine learning task where a model is trained to map input data to one of several predefined discrete labels, effectively sorting inputs into categories based on learned features.
A supervised learning paradigm wherein a model approximates a function mapping input vectors to a finite set of discrete class labels, optimizing a loss function to minimize classification error across a labeled dataset to ensure accurate sorting of inputs into categories.
evolution
- 1957 · historyPerceptron
Frank Rosenblatt developed the first artificial neural network capable of binary classification.
- 1986 · historyBackpropagation
Rumelhart, Hinton, and Williams popularized the algorithm that enabled multi-layer classification training.
- 1995 · historySupport Vector Machines
Cortes and Vapnik introduced SVMs, which became the industry standard for high-dimensional classification.
- 2012 · historyAlexNet
The success of deep convolutional neural networks in the ImageNet competition revolutionized image classification.
- 2017 · historyTransformer Architecture
The introduction of the Transformer model shifted classification tasks toward attention-based mechanisms for complex data.