Скачать с ютуб Dan Vilenchik - Towards Reverse Algorithmic Engineering of Neural Networks в хорошем качестве

Dan Vilenchik - Towards Reverse Algorithmic Engineering of Neural Networks

Presented on Thursday, February 1st, 2024, 10:30 AM, room C221 Speaker Dan Vilenchik (BGU) Title Towards Reverse Algorithmic Engineering of Neural Networks Abstract: As machine learning models get more complex, they can outperform traditional algorithms and tackle a broader range of problems, including challenging combinatorial optimization tasks.However, this increased complexity can make understanding how the model makes its decisions difficult. Explainable models can increase trust in the model’s decisions and may even lead to improvements in the algorithm itself. Algorithms like GradCAM or SHAP provide good explanations in terms of feature importance,typically for classification tasks. Still, they provide little insight when the ML pipeline is designed to work, for example, as an algorithm for solving optimization problems. In this talk,we present a framework for explaining a neural machine-learning model’s decision-making process from an algorithmic point of view. Using the NeuroSAT algorithm for SAT solving as a case study, we demonstrate how our framework finds the learned combinatorial features of a SAT formula and the algorithmic concepts that drive the operation of NeuroSAT. We discover that NeuroSAT learns a general algorithmic concept applied in many domains of statistical inference: (a) compute confidence levels for every variable, (b) fix variables with the highest confidence and simplify the instance, (c) solve the (hopefully simpler) residual formula using some simple technique.(Such a principle guides, for example, the well-known Belief-Propagation-Decimation algorithm). Join work with Elad Shoham (Phd student, BGU), Kahalil Wattad (MsC student BGU),Hadar Cohen (MsC student BGU), Havana Rica (Tel-Aviv-Yafo Academic College) and Claire Chen (MIT, undergraduate student). Bio: Dan Vilenchik holds a PhD in computer science from Tel Aviv University.He did a postdoc at UC Berkeley and UCLA. He is currently a tenured member of the school of Electrical Engineering at Ben-Gurion University. His research includes both theoretical (challenges of high-dimensional data) and applicative (NLP and multidisciplinary projects) aspects of machine learning. https://www.bgu.ac.il/~vilenchi Link for the Panopto Meetinghttps://huji.cloud.panopto.eu/Panopto... Link to past lectures    / @hujimachinelearningclub8982   Online Calendar Learning Club @ HUJI https://www.google.com/calendar/embed... Calendar ID: [email protected] Mailing List subscription-manager: http://mailman.cs.huji.ac.il/mailman/...