9
Recent work has explored the possibility of pruning neural networks at initialization. We assess proposals for doing so: SNIP (Lee et …
Active learning is able to reduce the amount of labelling effort by using a machine learning model to query the user for specific …
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two …
Decision making based on statistical association alone can be a dangerous en- deavor due to non-causal associations. Ideally, one would …
Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in …
We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time. CBS achieves …
Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in …
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random …
The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research …
The fields of artificial intelligence and neuroscience have a long history of fertile bi-directional interactions. On the one hand, …