Deep Learning
Encoding Human Behavior in Information Design through Deep Learning
We initiate the study of behavioral information design through deep learning.
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
The left part is about some existing approaches, e.g., IRNet [
Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory
To remove the limitation of short-term memory, Zhen et al.
SelectiveAttention: EnhancingTransformerthrough PrincipledContextControl
The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query.
Storchastic: AFrameworkfor GeneralStochasticAutomaticDifferentiation
Modelers use automatic differentiation (AD) of computation graphs to implement complex deep learning models without defining gradient computations.