20 citations · 23 across the 4 of their papers we have counts for
4 papers
Symbolic Neural Generation with Applications to Lead Discovery in Drug Design
Ashwin Srinivasan, Tirtharaj Dash, A Baskar +3
We investigate a relatively under-explored class of hybrid neurosymbolic models that integrate symbolic learning with neural reasoning to construct data generators meeting formal c…
A Model for Intelligible Interaction Between Agents That Predict and Explain
A. Baskar, Ashwin Srinivasan, Michael Bain +1
Machine Learning (ML) has emerged as a powerful form of data modelling with widespread applicability beyond its roots in the design of autonomous agents. However, relatively little…
Composition of Relational Features with an Application to Explaining Black-Box Predictors
Ashwin Srinivasan, A Baskar, Tirtharaj Dash +1
Relational machine learning programs like those developed in Inductive Logic Programming (ILP) offer several advantages: (1) The ability to model complex relationships amongst data…
Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
Tirtharaj Dash, Ashwin Srinivasan, A Baskar
We present a general technique for constructing Graph Neural Networks (GNNs) capable of using multi-relational domain knowledge. The technique is based on mode-directed inverse ent…