Search Results for author:
Found 13 papers, 5 papers with code
Convex Bounds on the Softmax Function with Applications to Robustness Verification
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.
VeriX: Towards Verified Explainability of Deep Neural Networks
We present VeriX, a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models.
On Optimizing Back-Substitution Methods for Neural Network Verification
A key component in many state-of-the-art verification schemes is computing lower and upper bounds on the values that neurons in the network can obtain for a specific input domain -- and the tighter these bounds, the more likely the verification is to succeed.
Toward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.
Efficient Neural Network Analysis with Sum-of-Infeasibilities
Given a convex relaxation which over-approximates the non-convex activation functions, we encode the violations of activation functions as a cost function and optimize it with respect to the convex relaxation.
Scalable Verification of GNN-based Job Schedulers
Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics.
DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers
We introduce DeepCert, a tool-supported method for verifying the robustness of deep neural network (DNN) image classifiers to contextually relevant perturbations such as blur, haze, and changes in image contrast.
An SMT-Based Approach for Verifying Binarized Neural Networks
One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components.
Global Optimization of Objective Functions Represented by ReLU Networks
However, individual "yes or no" questions cannot answer qualitative questions such as "what is the largest error within these bounds"; the answers to these lie in the domain of optimization.
Parallelization Techniques for Verifying Neural Networks
Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification.
G2SAT: Learning to Generate SAT Formulas
The Boolean Satisfiability (SAT) problem is the canonical NP-complete problem and is fundamental to computer science, with a wide array of applications in planning, verification, and theorem proving.
Improve SAT-solving with Machine Learning
We first used a logistic regression model to predict the satisfiability of propositional boolean formulae after fixing the values of a certain fraction of the variables in each formula.
BIG-bench Machine Learning
Multi-Stage Campaigning Optimization
+1
Gene Ontology (GO) Prediction using Machine Learning Methods
We applied machine learning to predict whether a gene is involved in axon regeneration.
