Kernel methods form a foundational framework in statistical learning theory, enabling algorithms to operate in implicitly defined high-dimensional feature spaces without ever computing feature vectors ...

Label Distribution Learning (LDL) is a new learning paradigm to deal with label ambiguity and many researches have achieved the prominent performances. Compared with traditional supervised learning ...

In the machine learning world, the sizes of artificial neural networks — and their outsize successes — are creating conceptual conundrums. When a network named AlexNet won an annual image recognition ...