Search Results for author:
Found 4 papers, 3 papers with code
On Masked Language Models for Contextual Link Prediction
In the real world, many relational facts require context; for instance, a politician holds a given elected position only for a particular timespan.
Retrieve to Explain: Evidence-driven Predictions with Language Models
R2E is a retrieval-based language model that prioritizes amongst a pre-defined set of possible answers to a research question based on the evidence in a document corpus, using Shapley values to identify the relative importance of pieces of evidence to the final prediction.
Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks
Reservoir computing is a powerful tool to explain how the brain learns temporal sequences, such as movements, but existing learning schemes are either biologically implausible or too inefficient to explain animal performance.
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i. e. they typically require significantly more playing experience than humans to reach an equal performance level.
