A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence
arXiv:2401.03188 · doi:10.1109/TAI.2024.3351798
Abstract
Neurosymbolic artificial intelligence (AI) is an emerging branch of AI that combines the strengths of symbolic AI and sub-symbolic AI. A major drawback of sub-symbolic AI is that it acts as a "black box", meaning that predictions are difficult to explain, making the testing & evaluation (T&E) and validation & verification (V&V) processes of a system that uses sub-symbolic AI a challenge. Since neurosymbolic AI combines the advantages of both symbolic and sub-symbolic AI, this survey explores how neurosymbolic applications can ease the V&V process. This survey considers two taxonomies of neurosymbolic AI, evaluates them, and analyzes which algorithms are commonly used as the symbolic and sub-symbolic components in current applications. Additionally, an overview of current techniques for the T&E and V&V processes of these components is provided. Furthermore, it is investigated how the symbolic part is used for T&E and V&V purposes in current neurosymbolic applications. Our research shows that neurosymbolic AI as great potential to ease the T&E and V&V processes of sub-symbolic AI by leveraging the possibilities of symbolic AI. Additionally, the applicability of current T&E and V&V methods to neurosymbolic AI is assessed, and how different neurosymbolic architectures can impact these methods is explored. It is found that current T&E and V&V techniques are partly sufficient to test, evaluate, verify, or validate the symbolic and sub-symbolic part of neurosymbolic applications independently, while some of them use approaches where current T&E and V&V methods are not applicable by default, and adjustments or even new approaches are needed. Our research shows that there is great potential in using symbolic AI to test, evaluate, verify, or validate the predictions of a sub-symbolic model, making neurosymbolic AI an interesting research direction for safe, secure, and trustworthy AI.
arXiv comment16 pages, 8 figures
References in corpus (18)
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- DLFuzz: Differential Fuzzing Testing of Deep Learning Systems
- An approach to reachability analysis for feed-forward ReLU neural networks
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing
- A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
- Certifiable Robustness and Robust Training for Graph Convolutional Networks
- A Review of Safe Reinforcement Learning: Methods, Theory and Applications
- Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
- Learning to Infer and Execute 3D Shape Programs
- Output Range Analysis for Deep Neural Networks
- Neurosymbolic Reinforcement Learning and Planning: A Survey
- A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
- Basic Reasoning with Tensor Product Representations
- Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing
- Neurosymbolic AI and its Taxonomy: a survey
- SURFACE: Semantically Rich Fact Validation with Explanations
- Neurosymbolic AI for Reasoning on Biomedical Knowledge Graphs