Search Results for author:
Found 10 papers, 3 papers with code
NLP Verification: Towards a General Methodology for Certifying Robustness
We propose a number of practical NLP methods that can help to identify the effects of the embedding gap; and in particular we propose the metric of falsifiability of semantic subpspaces as another fundamental metric to be reported as part of the NLP verification pipeline.
Efficient compilation of expressive problem space specifications to neural network solvers
Recent work has described the presence of the embedding gap in neural network verification.
Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic Programs
Neuro-symbolic programs -- programs containing both machine learning components and traditional symbolic code -- are becoming increasingly widespread.
ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification
In particular, many known neural network verification methods that work for computer vision and other numeric datasets do not work for NLP.
Logic of Differentiable Logics: Towards a Uniform Semantics of DL
A DL consists of a syntax in which specifications are stated and an interpretation function that translates expressions in the syntax into loss functions.
Differentiable Logics for Neural Network Training and Verification
What difference does a specific choice of DL make in the context of continuous verification?
Why Robust Natural Language Understanding is a Challenge
With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive to small input perturbations.
Vehicle: Interfacing Neural Network Verifiers with Interactive Theorem Provers
However, although work has managed to incorporate the results of these verifiers to prove larger properties of individual systems, there is currently no general methodology for bridging the gap between verifiers and interactive theorem provers (ITPs).
Actions You Can Handle: Dependent Types for AI Plans
Verification of AI is a challenge that has engineering, algorithmic and programming language components.
Neural Network Robustness as a Verification Property: A Principled Case Study
Neural networks are very successful at detecting patterns in noisy data, and have become the technology of choice in many fields.
