Tech Xplore

Reinforcement learning accelerates model-free training of optical AI systems

Optical computing has emerged as a powerful approach for high-speed and energy-efficient information processing. Diffractive ...
IEEE

An Online Multiple Kernel Parallelizable Learning Scheme

Abstract: The performance of reproducing kernel Hilbert space-based methods is known to be sensitive to the choice of the reproducing kernel. Choosing an adequate reproducing kernel can be challenging ...
GitHub

MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models

After downloading the WSIs, please use the CLAM repository to pre-process the WSIs and extract the features. The features should be put into the ./data directory. Then, use the h5toPyG.ipynb notebook ...
IEEE

Auto-Weighted Multi-View Deep Non-Negative Matrix Factorization With Multi-Kernel Learning

Abstract: Deep matrix factorization (DMF) has the capability to discover hierarchical structures within raw data by factorizing matrices layer by layer, allowing it to utilize latent information for ...