In Chaps. 3 and 4, we have explored the theoretical aspects of feature extraction optimization processes for solving large-scale problems and overcoming machine learning limitations. Majority of optimization algorithms that have been introduced in Mohammadi et al. (Evolutionary computation, optimization and learning algorithms for data science, 2019. arXiv preprint arXiv: 1908.08006; Applications of nature-i nspired algorithms for dimension reduction: enabling efficient data analytics, 2019. arXiv preprint arXiv: 1908.08563) guarantee the optimal performance of supervised learning, given offline and discrete data, to deal with curse of dimensionality (CoD) problem. These algorithms, however, are not tailored for solving emerging learning problems. One of the important issues caused by online data is lack of sufficient samples per class. Further, traditional machine learning algorithms cannot achieve accurate training based on limited distributed data, as data has proliferated and dispersed significantly. Machine learning employs a strict model or embedded engine to train and predict which still fails to learn unseen classes and sufficiently use online data. In this chapter, we introduce these challenges elaborately. We further investigate meta-learning (MTL) algorithm, and their application and promises to solve the emerging problems by answering how autonomous agents can learn to learn?.
