4 papers
Converge to Surprise: Evolutionary Self-supervised Image Clustering
Canlin Zhang, Xiuwen Liu
Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step r…
A Theory of Machine Understanding via the Minimum Description Length Principle
Canlin Zhang, Xiuwen Liu
Deep neural networks trained through end-to-end learning have achieved remarkable success across various domains in the past decade. However, the end-to-end learning strategy, orig…
Inductive Link Prediction in Knowledge Graphs using Path-based Neural Networks
Canlin Zhang, Xiuwen Liu
Link prediction is a crucial research area in knowledge graphs, with many downstream applications. In many real-world scenarios, inductive link prediction is required, where predic…
Learning Regularities from Data using Spiking Functions: A Theory
Canlin Zhang, Xiuwen Liu
Deep neural networks trained in an end-to-end manner are proven to be efficient in a wide range of machine learning tasks. However, there is one drawback of end-to-end learning: Th…