Back to Search
Start Over
On Tractable Representations of Binary Neural Networks
- Source :
- KR
- Publication Year :
- 2020
-
Abstract
- We consider the compilation of a binary neural network's decision function into tractable representations such as Ordered Binary Decision Diagrams (OBDDs) and Sentential Decision Diagrams (SDDs). Obtaining this function as an OBDD/SDD facilitates the explanation and formal verification of a neural network's behavior. First, we consider the task of verifying the robustness of a neural network, and show how we can compute the expected robustness of a neural network, given an OBDD/SDD representation of it. Next, we consider a more efficient approach for compiling neural networks, based on a pseudo-polynomial time algorithm for compiling a neuron. We then provide a case study in a handwritten digits dataset, highlighting how two neural networks trained from the same dataset can have very high accuracies, yet have very different levels of robustness. Finally, in experiments, we show that it is feasible to obtain compact representations of neural networks as SDDs.<br />In Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR) 2020
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Theoretical computer science
Artificial neural network
Quantitative Biology::Neurons and Cognition
Binary decision diagram
Computer science
Computer Science - Artificial Intelligence
Computer Science::Neural and Evolutionary Computation
Function (mathematics)
Binary neural network
Machine Learning (cs.LG)
Task (computing)
Artificial Intelligence (cs.AI)
Robustness (computer science)
Representation (mathematics)
Formal verification
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- KR
- Accession number :
- edsair.doi.dedup.....39776fa0ac67b2868cc2e72426ce6c61