Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Jifunze Mtandaoni× | Jifunze kwa Kujisimamia× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Mashine | Ujifunzaji wa Mashine |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 1958–2000s | 2018–2020 |
| Mwanzilishi≠ | Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors) | LeCun, Y. and community (formalized ~2018–2020) |
| Aina≠ | Learning paradigm (sequential model update) | Representation learning paradigm |
| Chanzo asilia≠ | Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194. DOI ↗ | LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/ link ↗ |
| Majina mbadala | incremental learning, sequential learning, streaming learning, online machine learning | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| Zinazohusiana≠ | 6 | 3 |
| Muhtasari≠ | Online learning is a machine learning paradigm in which a model is updated incrementally as each new data point arrives, rather than being trained once on a fixed dataset. It is essential when data streams continuously, storage is limited, or the underlying distribution shifts over time. Theoretical performance is measured by cumulative regret relative to the best fixed predictor in hindsight. | Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples. |
| ScholarGateSeti ya data ↗ |
|
|