Deep Learning
Supplementary Material for " Generative Neurosymbolic Machines " 1 Additional qualitative Results 1.1 Generation
However, when training GNM, we observed a different learning pattern.
Contrastive learning of global and local features for medical image segmentation with limited annotations
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis.
Value-driven Hindsight Modelling
V alue estimation is a critical component of the reinforcement learning (RL) paradigm.
link prediction datasets. Each number is the average performance for 10 random initialization of the experiments. Bold
Each number is the average performance for 10 random initialization of the experiments. To compare our proposed methods with additional popular heuristics methods (Jaccard (Jac.), preferential attachment (P A), Katz, PageRank (PR), and SimRank (SR)) beyond overlapped neighbors-based Neo-GNN consistently shows better performance than overlapped-based heuristic methods. Interestingly, though overlap-based heuristic methods perform worse in Power dataset, our Neo-GNN show the best performance compared to all heuristic methods. This result shows that Neo-GNN is not limited to the limitations of existing neighborhood-overlap based heuristics. The direction of generalizing these heuristic methods will be a good future work.
Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients William S. Moses MIT CSAIL
On a machine-learning focused benchmark suite including Microsoft's ADBench, AD on optimized IR achieves a geometric mean speedup of 4.2 times