Author

Zhi-Min Li

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Oct 2023

Instance-wise Linearization of Neural Network for Model Interpretation

This work proposes an instance-wise linearization approach to reformulates the forward computation process of a neural network prediction and discusses the application of this technique in both supervise classification and unsupervised neural network learning parametric t-SNE dimension reduction.

Zhi-Min Li, Shu-Sen Liu, B. Kailkhura et al. · arXiv.org · 0 citations