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

Oct 21, 2023 •214 likes •416 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 !

Recommend

Neural Networks Neural networks arise from attempts to model Neural Networks human/animal

Feed-forward Networks Network Training Error Backpropagation Deep Learning Feed-forward Networks Network Training Error Backpropagation Deep Learning Neural Networks Neural networks arise from attempts to model Neural Networks

382 views • 9 slides

Learning Neural Networks Learning Neural Networks Neural Networks can represent complex Neural

Learning Neural Networks Learning Neural Networks Neural Networks can represent complex Neural Networks can represent complex decision boundaries decision boundaries Variable size. Any boolean function can be Variable size. Any boolean

361 views • 14 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

530 views • 35 slides

Neural Networks and Handwriting Recognition Background Neural Networks Neural Network Steven

Neural Networks and Handwriting Recognition Steven Sloss Math 164 Neural Networks and Handwriting Recognition Background Neural Networks Neural Network Steven Sloss Structure Training Neural Networks Math 164 Motivation Problem

895 views • 41 slides

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

684 views • 44 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

815 views • 21 slides

Sequential Data with Neural Networks Recurrent Neural Networks Sequential input / output Greg

Recurrent Neural Networks Long Short-Term Memory Temporal Convolutional Networks Examples Recurrent Neural Networks Long Short-Term Memory Temporal Convolutional Networks Examples Sequential Data with Neural Networks Recurrent Neural

305 views • 4 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

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural IR tasks Neural IR architecture Feature Representations Neural IR query auto completion Neural IR query suggestion Neural IR document

1.48k views • 18 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

Weight Parameterizations in Deep Neural Networks Sergey Zagoruyko e Paris-Est, Universit

Weight Parameterizations in Deep Neural Networks Weight Parameterizations in Deep Neural Networks Sergey Zagoruyko e Paris-Est, Universit Ecole des Ponts ParisTech December 26, 2017 Weight Parameterizations in Deep Neural Networks

1.06k views • 45 slides

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning objectives What are neural networks? What are deep neural networks? How do we train neural networks? What variants of neural network

334 views • 31 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

DIVS DL/ID Verification Systems Verification of Legal Status DIVS Passport Verification

DIVS DL/ID Verification Systems Verification of Legal Status DIVS Passport Verification Projects Birth Record Verification State to State Verification DIVS State to State Verification Service (S2S) Program Benefits Mission

352 views • 8 slides

CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I :

Ugur HALICI - METU EEE - ANKARA 11/18/2004 CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I : Recurrent Neural Networks CHAPTER I Recurrent Neural Networks Introduction In this chapter first the

408 views • 27 slides

CHAPTER II III I CHAPTER Neural Networks as Neural Networks as Associative Memory

Ugur HALICI - METU EEE - ANKARA 11/18/2004 CHAPTER II III I CHAPTER Neural Networks as Neural Networks as Associative Memory Associative Memory CHAPTER III : III : Neural Networks as Associative Memory CHAPTER Neural Networks as

516 views • 22 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

454 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

1.53k 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

633 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

443 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

812 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

752 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

343 views • 16 slides

Download document

More recommend

Explore More Topics

Stay informed with curated content and fresh updates.

animals pets art culture automotive transportation business finance computer internet construction architecture education-career electronics communication

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

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

Neural Networks Neural networks arise from attempts to model Neural Networks human/animal

Learning Neural Networks Learning Neural Networks Neural Networks can represent complex Neural

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

Neural Networks and Handwriting Recognition Background Neural Networks Neural Network Steven

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

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

Sequential Data with Neural Networks Recurrent Neural Networks Sequential input / output Greg

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

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural

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

Weight Parameterizations in Deep Neural Networks Sergey Zagoruyko e Paris-Est, Universit

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

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

DIVS DL/ID Verification Systems Verification of Legal Status DIVS Passport Verification

CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I :

CHAPTER II III I CHAPTER Neural Networks as Neural Networks as Associative Memory

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

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

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

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

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

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

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

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

Explore More Topics

Sambuz

Useful Links

Newsletter

Mail Us

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

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

Neural Networks Neural networks arise from attempts to model Neural Networks human/animal

Learning Neural Networks Learning Neural Networks Neural Networks can represent complex Neural

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

Neural Networks and Handwriting Recognition Background Neural Networks Neural Network Steven

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

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

Sequential Data with Neural Networks Recurrent Neural Networks Sequential input / output Greg

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

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural

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

Weight Parameterizations in Deep Neural Networks Sergey Zagoruyko e Paris-Est, Universit

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

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

DIVS DL/ID Verification Systems Verification of Legal Status DIVS Passport Verification

CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I :

CHAPTER II III I CHAPTER Neural Networks as Neural Networks as Associative Memory

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

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

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

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

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

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

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

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

Explore More Topics

Sambuz

Useful Links

Newsletter

Mail Us

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

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