5 papers
Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling
Radha Kopparti, Tillman Weyde
Deep neural networks have become the dominant approach in natural language processing (NLP). However, in recent years, it has become apparent that there are shortcomings in systema…
Weight Priors for Learning Identity Relations
Radha Kopparti, Tillman Weyde
Learning abstract and systematic relations has been an open issue in neural network learning for over 30 years. It has been shown recently that neural networks do not learn relatio…
Factors for the Generalisation of Identity Relations by Neural Networks
Radha Kopparti, Tillman Weyde
Many researchers implicitly assume that neural networks learn relations and generalise them to new unseen data. It has been shown recently, however, that the generalisation of feed…
Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations
Tillman Weyde, Radha Manisha Kopparti
Basic binary relations such as equality and inequality are fundamental to relational data structures. Neural networks should learn such relations and generalise to new unseen data.…
Modelling Identity Rules with Neural Networks
Tillman Weyde, Radha Manisha Kopparti
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) ext…