Nina Narodytska
Senior Researcher
Palo Alto, CA, US
Recent invited talks/panels:
- Stanford Intelligent Systems Laboratory (June’20)
- PARC, a Xerox company (Dec’20)
- Explanation and, Human-centric CP @From Constraint Programming to Trustworthy AI (CPTAI 2020, workshop, Sep’20)
- International Conference on Principles and Practice of Constraint Programming, CP'19 Waterloo ML + Security + Verification Workshop'19
- AAAI Spring Symposium on Verification of Neural Networks (VNN19)
- In Search for a SAT-friendly Binarized Neural Network Architecture, Google Research, Mountain View, USA, 2019 and NASA, Mountain View, USA, 2019
An organizer/chair of :
Recent program committees:
- (Area Chair)International Joint Conferences on Artificial Intelligence'20
- Formal Methods in Computer-Aided Design'20
- International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research'20
- (senior PC) AAAI Conference on Artificial Intelligence'20
- International Joint Conferences on Artificial Intelligence'19
- (senior PC) AAAI Conference on Artificial Intelligence'19
- (senior PC) International Conference on Principles and Practice of Constraint Programming, CP'19
- AAAI Conference on Artificial Intelligence'18
- International Joint Conferences on Artificial Intelligence'18
- Object-oriented Programming, Systems, Languages, and Applications'18
- (Senior PC) AAAI Conference on Artificial Intelligence'19
Projects
Publications
- Verifying Properties of Binarized Neural Networks
- Simple Black-Box Adversarial Attacks on Deep Neural Networks.
- Network Approximation using Tensor Sketching
- Constrained Image Generation Using Binarized Neural Networks with Decision Procedures
- Learning Optimal Decision Trees with SAT
- A SAT-Based Approach to Learn Explainable Decision Sets
- Core-Guided Minimal Correction Set and Core Enumeration
- Formal Analysis of Deep Binarized Neural Networks
- Abduction-Based Explanations for Machine Learning Models
- RelGAN: Relational Generative Adversarial Networks for Text Generation
- Reasoning about Neural Networks: a Taxonomy of Current Approaches
- Simple and Precise Static Analysis of Untrusted Linux Kernel Extensions
- Assessing Heuristic Machine Learning Explanations with Model Counting*
- Synthesizing Cluster Management Code for Distributed Systems
- BDD-Based Algorithms for Packet Classification
- Automating Cluster Management with Weave
- In Search for a SAT-friendly Binarized Neural Network Architecture
- Verification of Recurrent Neural Networks for Cognitive Tasks via Reachability Analysis
- Building Scalable and Flexible Cluster Managers Using Declarative Programming
- Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay
- Explanations for Monotonic Classifiers
- Analyzing Learning-Based Networked Systems with Formal Verification
- Reasoning-Based Learning of Interpretable ML Models
- Constraint-Driven Explanations of Black-Box ML Models