VERIFICATION OF DEEP NEURAL NETWORKS SOURADEEP DUTTA*, SUSMIT JHA # , - PowerPoint PPT Presentation

Oct 21, 2023 •214 likes •413 views

VERIFICATION OF DEEP NEURAL NETWORKS SOURADEEP DUTTA, SUSMIT JHA # , SRIRAM SANKARANARAYANAN, ASHISH TIWARI # * UNIVERSITY OF COLORADO, BOULDER # SRI INTERNATIONAL, MENLO PARK PROBLEM STATEMENT A much simpler problem. ? PROBLEM STATEMENT

VERIFICATION OF DEEP NEURAL NETWORKS SOURADEEP DUTTA*, SUSMIT JHA # , SRIRAM SANKARANARAYANAN*, ASHISH TIWARI # * UNIVERSITY OF COLORADO, BOULDER # SRI INTERNATIONAL, MENLO PARK
PROBLEM STATEMENT A much simpler problem…. ?
PROBLEM STATEMENT A much simpler problem…. ? LET’S FIND THE MAXIMA ( MINIMA )
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA LOCAL MAXIMA Random Sample
THE OVERALL IDEA BETTER POINT Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Random Sample
THE OVERALL IDEA Cannot Improve further STOP ! Random Sample
THE OVERALL IDEA KEY COMPONENTS : 1. Gradient search technique 2. Counter Example Generation
Thanks !

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan Zelener Machine Learning Reading Group January 7 th 2016 The Graduate Center, CUNY Objectives Explain some of the trends of deep learning and

680 views • 44 slides

Approximate Verification of Deep Neural Networks with Provable Guarantees Xiaowei Huang,

Approximate Verification of Deep Neural Networks with Provable Guarantees Xiaowei Huang, University of Liverpool Outline Background and Challenges Safety Definition and Layer-by-Layer Refinement Game-based Approach for a Single Layer

853 views • 54 slides

Testing Deep Neural Networks Xiaowei Huang, University of Liverpool Outline Safety Problem of AI

Testing Deep Neural Networks Xiaowei Huang, University of Liverpool Outline Safety Problem of AI Verification (brief) Testing Conclusions and Future Works Human-Level Intelligence Robotics and Autonomous Systems Deep neural networks all

1.5k views • 63 slides

Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker

Introduction HMM based method Deep Neural Networks (DNNs) Experiments and Results Conclusions Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker Verification Hossein Zeinali 1 , 2 , Luk s Burget 2 ,

301 views • 11 slides

Deep Neural Networks based Text- Dependent Speaker Verification Gautam Bhattacharya, Jahangir

Odyssey Speaker & Language Recognition Workshop 2016 Deep Neural Networks based Text- Dependent Speaker Verification Gautam Bhattacharya, Jahangir Alam, Themos Stafylakis & Patrick Kenny Computer Research Institute of Montreal (CRIM) 1

519 views • 25 slides

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In

987 views • 40 slides

Visualizing and Interpreting Deep Neural Networks Bolei Zhou Department of Information

Visualizing and Interpreting Deep Neural Networks Bolei Zhou Department of Information Engineering The Chinese University of Hong Kong Deep Neural Networks are Everywhere Playing Go Making Medical Decision Understanding Scenes Deep Neural

1.1k views • 46 slides

On the Expressive Power of Deep Neural Networks Maithra Raghu, Ben Poole, Jon Kleinberg, Surya

On the Expressive Power of Deep Neural Networks Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, Jascha Sohl Dickstein Tom Brady Deep Neural Networks Recent successes in using Deep neural networks for image classification,

1.32k views • 17 slides

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova November 21, 2016 Neural Networks 2/20 Neural Networks 3/20 Neural Networks Neural computing requires a number of neurons , to be connected

813 views • 21 slides

Optimizing Deep Neural Networks Leena Chennuru Vankadara 26-10-2015 Table of Contents Neural

Optimizing Deep Neural Networks Leena Chennuru Vankadara 26-10-2015 Table of Contents Neural Networks and loss surfaces Problems of Deep Architectures Optimization in Neural Networks Under fitting Proliferation of Saddle

1.67k views • 41 slides

Deep Neural Networks and Molecular Dynamics Roberto Car Princeton University MAX Conference

Deep Neural Networks and Molecular Dynamics Roberto Car Princeton University MAX Conference ICTP, Trieste, Jan 29-31 2018 Deep Neural Networks When properly trained, deep NN are capable of learning the complex functional dependence of

442 views • 17 slides

CS7015 (Deep Learning) : Lecture 13 Visualizing Convolutional Neural Networks, Guided

CS7015 (Deep Learning) : Lecture 13 Visualizing Convolutional Neural Networks, Guided Backpropagation, Deep Dream, Deep Art, Fooling Convolutional Neural Networks Mitesh M. Khapra Department of Computer Science and Engineering Indian Institute

1.07k views • 72 slides

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and Courville [chapt. 6,7,8]; AIMA [sect. 21.1-21.3]; Sutton and Barto, Reinforcement Learning: an

527 views • 35 slides

Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Learning in Neural Networks w 1,3 w 3,5 1 3 5 w w 1,4 3,6 w w 2,3 4,5 2 4 6 w w 2,4 4,6 Class #18: Back-Propagation; } A neural network can learn a classification function by Tuning Hyper-Parameters adjusting its weights to

259 views • 4 slides

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Umut Gcl and Marcel A. J. van Gerven Article overview by Ilya Kuzovkin Computational Neuroscience Seminar University of Tartu

852 views • 63 slides

CAR' 2010 Soraya Arias Florine Boudin Roger Pissard-Gibollet Daniel Simon 2 Orccad : status

1 Orccad, a Model Driven Architecture and Environment for Robot Control May 18 th & 19 th 2010, Douai CAR' 2010 Soraya Arias Florine Boudin Roger Pissard-Gibollet Daniel Simon 2 Orccad : status and motivations Model: Control

450 views • 29 slides

Local null-controllability of the 2-D Vlasov-Navier-Stokes system Iv an Moyano CMLS,

Local null-controllability of the 2-D Vlasov-Navier-Stokes system Iv an Moyano CMLS, Ecole Polytechnique June 22, 2016 Iv an Moyano Local null-controllability of the 2-D Vlasov-Navier-Stokes system The Vlasov-Navier-Stokes system

1.52k views • 103 slides

The LIA Summarization Systems at DUC 2007 florian.boudin@univ-avignon.fr Laboratoire

The LIA Summarization Systems at DUC 2007 florian.boudin@univ-avignon.fr Laboratoire Informatique dAvignon, France co-authors : Frdric Bchet, Marc El-Bze, Benoit Favre, Laurent Gillard and Juan-Manuel Torres-Moreno April 26, 2007

630 views • 33 slides

Multicriteria optimization of force field models for molecular simulation of interfacial and bulk

Multicriteria optimization of force field models for molecular simulation of interfacial and bulk properties Martin Thomas Horsch, 1, 2 Stephan Werth, 1 Katrin Stbener, 1, 3 Peter Klein, 3 Karl-Heinz Kfer, 3 and Hans Hasse 1 1 Laboratory of

440 views • 17 slides

SUMMARY OF RECENT RHIC RESULTS THEODORE KOBLESKY UNIVERSITY OF COLORADO BOULDER MPI@LHC 2016

SUMMARY OF RECENT RHIC RESULTS THEODORE KOBLESKY UNIVERSITY OF COLORADO BOULDER MPI@LHC 2016 SAN CRISTBAL DE LAS CASAS, CHIAPAS, MXICO 2016-12 2 OVERVIEW HEAVY ION COLLISION TOPICS JETS QUENCHING COLLECTIVE FLOW Theodore Koblesky

808 views • 49 slides

Simulations of BH Collisions in AdS Spacetimes Paul Romatschke CU Boulder & CTQM & JET

Simulations of BH Collisions in AdS Spacetimes Paul Romatschke CU Boulder & CTQM & JET Collaboration Based on arXiv: 1410.4799 with Hans Ban8lan Outline Motivation Simulating BH Collisions

898 views • 69 slides

Gradient flows in the framework of (Cartesian) Currents Malte Kampschulte Department for

Gradient flows in the framework of (Cartesian) Currents Malte Kampschulte Department for Mathematics I, RWTH Aachen University Conference on Nonlinearity, Transport, Physics and Patterns Fields Institute 07.10.2014 Vortices as singularities

748 views • 47 slides

Gulf Stream effects on the NAO: Theory, modeling and observations M. Ghil 1 , 2 , E. Simonnet 3 ,

Gulf Stream effects on the NAO: Theory, modeling and observations M. Ghil 1 , 2 , E. Simonnet 3 , Y. Feliks 1 , 4 1 Dept. of Atmospheric and Oceanic Sciences and IGPP , UCLA, USA. 2 Geosciences Dept. and LMD (CNRS and IPSL), ENS, Paris. 3 Institut

334 views • 16 slides