Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis
Kavi Gupta, Peter Ebert Christensen, Xinyun Chen +1
The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it…
cs.LG2020
Autoencoding Undirected Molecular Graphs With Neural Networks
Jeppe Johan Waarkjær Olsen, Peter Ebert Christensen, Martin Hangaard Hansen +1
Discrete structure rules for validating molecular structures are usually limited to fulfillment of the octet rule or similar simple deterministic heuristics. We propose a model, in…