Multi-Side Multi-Instance Algorithm

Multi-instance learning is a new machine learning framework following supervised learning, unsupervised learning and reinforcement learning. In order to solve the complex computing problems of many dimensions and large amount of samples better in multi-instance learning, a multi-instance learning algorithm based on multi-side is put forward in this paper. The algorithm selects the feature attributes of sample, and proceeds multi-instance learning to sample from different attribute sides. This is similar to the process that people acknowledge problems from different sides, also offer a simple way to solve many dimensions samples of multi-instance problem. The experimental results on benchmark data sets show that this algorithm is efficient and effective.