With a large dataset, limited computational resources or frequent new data to learn from, we can adopt what type of machine learning?

Online learning (or incremental learning) is a machine learning paradigm where data becomes available in a sequential order and is used to update the best predictor for future data at each step. This approach is highly effective when dealing with large datasets that cannot fit into main memory (out-of-core learning), when computational resources are limited, or when the model needs to adapt rapidly to frequent new data streams. Instead of retraining the entire model from scratch—as required in batch learning—online learning algorithms process one data point or a small mini-batch at a time, making them highly resource-efficient and adaptable to continuous data flows.

A. Batch learning requires training on the entire dataset at once, which is computationally expensive and unsuitable for limited resources or continuous new data streams.

B. "Big Data learning" is not a standard, formal machine learning paradigm or algorithmic approach recognized in academic literature for this specific scenario.

C. "Patchwork learning" is a fabricated term and does not represent a recognized machine learning methodology for handling continuous data streams or limited resources.

1. Bishop, C. M. (2006). "Pattern Recognition and Machine Learning." Springer, Section 2.1.1 (Sequential Learning), pp. 73-74.

2. Géron, A. (2019). "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow." O'Reilly Media, Chapter 1 (Online Learning), pp. 15-17.