Generative Tensor Network Classification Model for Supervised Machine Learning
This work addresses the challenge of developing efficient and high-performance classification models in machine learning, particularly for image recognition tasks, though it appears incremental as it builds on existing tensor network methods.
The authors tackled the problem of supervised machine learning by proposing a generative tensor network classification (GTNC) approach, which achieved competitive testing accuracy to state-of-the-art convolutional neural networks on MNIST and Fashion-MNIST datasets, while being more efficient than existing discriminative tensor network models.
Tensor network (TN) has recently triggered extensive interests in developing machine-learning models in quantum many-body Hilbert space. Here we purpose a generative TN classification (GTNC) approach for supervised learning. The strategy is to train the generative TN for each class of the samples to construct the classifiers. The classification is implemented by comparing the distance in the many-body Hilbert space. The numerical experiments by GTNC show impressive performance on the MNIST and Fashion-MNIST dataset. The testing accuracy is competitive to the state-of-the-art convolutional neural network while higher than the naive Bayes classifier (a generative classifier) and support vector machine. Moreover, GTNC is more efficient than the existing TN models that are in general discriminative. By investigating the distances in the many-body Hilbert space, we find that (a) the samples are naturally clustering in such a space; and (b) bounding the bond dimensions of the TN's to finite values corresponds to removing redundant information in the image recognition. These two characters make GTNC an adaptive and universal model of excellent performance.