deep learning
play

DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY - PowerPoint PPT Presentation

Jan 28, 2024 •5 likes •325 views

GPU-ACCELERATED DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY TYA A BALU SA SAMBIT IT GHADAI AI SO SOUMIK K SA SARKA KAR ADARS RSH H KR KRISH SHNAMUR AMURTHY THY Outline Volumetric Deep Learning based

  1. GPU-ACCELERATED DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY TYA A BALU SA SAMBIT IT GHADAI AI SO SOUMIK K SA SARKA KAR ADARS RSH H KR KRISH SHNAMUR AMURTHY THY

  2. Outline Volumetric Deep Learning based Design for Representations for Design for Explainable Deep Manufacturing CAD Models Manufacturing Learning May 15, 2017 2

  3. Reducing Product Cost DFM INFLUENCE OVER PRODUCT COST 100 • Design has a large influence on 90 final product cost 80 Design 70 Design knowledge 60 Percentage Cost of change • DFM helps identify production 50 issues early 40 30 Manufacturing 20 Design freedom to 10 make change 0 Time Design Production Source: David Stienstra (Rose-Hulman) May 15, 2017 3

  4. Challenges • Traditional DFM method involves rule based analysis Design • Depends on the experience of the engineers • Several rules for different processes • Example ISO/ASTM 52910:2017(E) Redesign Manufacturing Standard Guidelines for Design for Additive Manufacturing May 15, 2017 4

  5. Artificial Intelligence for Design for Manufacturing • Use deep learning to learn non- manufacturable features in a CAD model • Learn from examples of manufacturable and non-manufacturable models • Advantages • No explicit hand-crafting of rules • Learn complicated rules that are difficult to codify May 15, 2017 5

  6. Feasibility Demonstration – Drilling Holes • Common manufacturing operations • Fewer set of design rules • Can manually create ground-truth data • Complex design rules • Depth to diameter ratio • Blind vs. through holes • Proximity of holes to object boundaries May 15, 2017 6

  7. Boundary Representation (B-Rep) CAD Models • De-facto representation for CAD models • Can be easily tessellated into triangles for rendering • Difficult to interpret volumetric information • Size of a feature • Internal location of a feature May 15, 2017 7

  8. Voxel Representation • Binary occupancy information • Augmented with extra geometry information • Can be used as direct input to a convolutional neural network • Require a fast method to voxelize a large number of CAD models May 15, 2017 8

  9. Outline Volumetric Deep Learning based Design for Representations for Design for Explainable Deep Manufacturing CAD Models Manufacturing Learning May 15, 2017 9

  10. Volumetric Voxelization • Overlay a regular voxel grid on the object . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Test point membership of the . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . voxel bounding-box center . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . points, classify as in or out . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . May 15, 2017 10

  11. Point Membership Classification (PMC) Using GPU Slicing • Use standard PMC using odd ray Pixels intersection test • Slice the object perpendicular to an arbitrary axis • Render the sliced object and count the number of pixels • Extend to 3D; Each pixel corresponds to a grid point in a 2D slice View Direction May 15, 2017 11

  12. Outline Volumetric Deep Learning based Design for Representations for Design for Explainable Deep Manufacturing CAD Models Manufacturing Learning May 15, 2017 12

  13. Learning Local Features • Local Feature learning is different from object recognition • Variation in features affect the object classification • Learning the features by semi-supervised learning [1]. http://dfmpro.geometricglobal.com/files/2017/04/Whitepaper-A-new-approach- to-design-and-manufacturing-collaboration.pdf May 15, 2017 13

  14. Need for 3D Convolutional Nets • Hierarchical feature extraction from volumetric representation • Capability to learn features with object classification • Amenable to model interpretability due to learning of spatial location May 15, 2017 14

  15. Deep Learning Based Design for Manufacturing • Binary definition of manufacturability (binary cross-entropy loss) • Choice of input resolution depending on the GPUs • Architecture • 3D convolutional layer and 3D max. pooling layer • ReLU activation with output layer having Sigmoid activation May 15, 2017 15

  16. Deep Learning Based Design for Manufacturing (a) (c) (b) DLDFM (d) (f) (e) May 15, 2017 16

  17. Results Representative Test Data Manufacturable Representative Test Data Non-Manufacturable DLDFM (binary) DLDFM (binary) DLDFM (Orthogonal Distance Fields) DLDFM (Orthogonal Distance Fields) DLDFM (binary + normals) DLDFM (binary + normals) 0% 20% 40% 60% 80% 100% 0% 20% 40% 60% 80% 100% True Positive (Predicted Manufacturable, Actually Manufacturable) True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable) May 15, 2017 17

  18. Results Non-Representative Test Data Non-Manufacturable Non-Representative Test Data Manufacturable DLDFM (binary) DLDFM (binary) DLDFM (Orthogonal Distance Fields) DLDFM (Orthogonal Distance Fields) DLDFM (binary + normals) DLDFM (binary + normals) 0% 20% 40% 60% 80% 100% 0% 20% 40% 60% 80% 100% True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) True Positive (Predicted Manufacturable, Actually Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable) May 15, 2017 18

  19. Results DLDFM (binary) DLDFM (binary + normals) DLDFM (orthogonal distance fields) 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% True Positive (Predicted Manufacturable, Actually Manufacturable) True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable) May 15, 2017 19

  20. Outline Volumetric Deep Learning based Design for Representations for Design for Explainable Deep Manufacturing CAD Models Manufacturing Learning May 15, 2017 20

  21. Model Interpretability • Possible methods • Back-propagation • Guided back-propagation, saliency map, etc. Disadvantage : Not class discriminative • Grad-CAM • Class discriminative References: [1]. Zeiler, Matthew D., and Rob Fergus. "Visualizing and understanding convolutional networks." European conference on computer vision . Springer International Publishing, 2014. [2]. Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). [3]. Zhou, Bolei, et al. "Learning deep features for discriminative localization." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2016. [4]. Selvaraju, Ramprasaath R., et al. "Grad-CAM: Why did you say that?." arXiv preprint arXiv:1611.07450 (2016). May 15, 2017 21

  22. 3D Grad-CAM • Perform global average pooling and back-propagate the activations Convolution Filters 1 Output: Convolution Filters 2 Manufacturability (Yes/No) Fully Connected Pooling Layer Convolutional Layer Layer Convolutional Layer Input: Volumetric Representation Class Activation Map Interpretation May 15, 2017 22

  23. Insights from GradCAM May 15, 2017 23

  24. Insight: 3D Grad-CAM is class discriminative One Hole Manufacturable May 15, 2017 24

  25. Insight: DLDFM can predict manufacturability of multiple features simultaneously Two Holes Manufacturable (both) May 15, 2017 25

  26. Insight: DLDFM can predict manufacturability of individual features Two Holes Non-Manufacturable (due to one of them) May 15, 2017 26

  27. Insight: DLDFM can predict manufacturability of interacting features by generalizing the rules Two Holes Non-Manufacturable (due to interaction between them) May 15, 2017 27

  28. Insight: DLDFM can predict manufacturability based on a local feature instead of external geometry L-Shaped Block with Hole Non-Manufacturable (close to external face) May 15, 2017 28

  29. Insight: DLDFM can predict manufacturability based on a local feature even with complicated external geometry Cylindrical-Shaped Block with Hole Non- Manufacturable (close to external cylindrical face) May 15, 2017 29

  30. Demo May 15, 2017 30

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

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Deep 3D Representation Learning for Visual Computing Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms Conclusion 2 Outline Overview of 3D deep learning Background 3D deep learning tasks 3D deep

1.66k views • 122 slides
ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

307 views • 26 slides
Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views • 39 slides
Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods) Peter Henderson Statistical Society of Canada Annual Meeting 2018 Contributors Riashat Islam Phil Bachman Doina Precup David Meger Joelle

850 views • 37 slides
Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides
Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

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
Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin Clark Deep Learning for NLP 5 years ago No Seq2Seq No Attention No large-scale QA/reading comprehension datasets No TensorFlow or

1.41k views • 92 slides
An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning Microsoft Research Asia (MSRA) Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun. Deep Residual Learning for Image Recognition. arXiv

1.32k views • 54 slides
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

540 views • 15 slides
Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision : Image Classification,

1.53k views • 23 slides
Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Tofu: Parallelizing Deep Learning Systems with Automatic Tiling Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL system is based on dataflow GPU#0 w1 w2 data g1 g2 Forward propagation

405 views • 38 slides
Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations deeplearning.cce2020@gmail.com Deep Networks Intuition Neural networks with multiple hidden layers - Deep networks [Hinton, 2006] Deep Networks Intuition

1.33k views • 28 slides
Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu 2020 For the full list of references visit: http://bit.ly/deeplearn-sota-2020 Outline Deep Learning Growth, Celebrations, and Limitations

1.1k views • 87 slides
12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides
Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning www.deeplearningbook.org Ian Goodfellow 2016-09-27 Definition Regularization is any modification we make to a learning algorithm that is intended to reduce

179 views • 13 slides
Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention Transformer Pytorch Introduction Basics Examples RNNs Some slides borrowed from Fei-Fei Li & Justin Johnson &

1.1k views • 55 slides
accessing health care: whats the problem? Mrs. Kristin McBain-Rigg PhD candidate/Research

accessing health care: whats the problem? Mrs. Kristin McBain-Rigg PhD candidate/Research

Cultural barriers to accessing health care: whats the problem? Mrs. Kristin McBain-Rigg PhD candidate/Research Officer Mount Isa Centre for Rural and Remote Health, James Cook University Background Access barriers to mainstream services

213 views • 17 slides
Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks Chetan

Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks Chetan

Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks Chetan Kumar, Riazat Ryan, Ming Shao Department of Computer and Information Science, University of Massachusetts, Dartmouth Data Leakage: Limited time

294 views • 27 slides
POL POL201Y1: Po Politics of Development Karol Czuba, University of Toronto Lecture 9:

POL POL201Y1: Po Politics of Development Karol Czuba, University of Toronto Lecture 9:

POL POL201Y1: Po Politics of Development Karol Czuba, University of Toronto Lecture 9: Anarchy and the emergence of political order Re Recap Explanations of development (and lack thereof): Modernization Neoliberalism Dependency

422 views • 28 slides
Achieving Important Literacy Outcomes: Effective Vocabulary and Comprehension Instruction Breda

Achieving Important Literacy Outcomes: Effective Vocabulary and Comprehension Instruction Breda

Achieving Important Literacy Outcomes: Effective Vocabulary and Comprehension Instruction Breda OKeeffe, Ph.D. IHD EBP Conference July 24 th , 2017 1 Overview Building Blocks: Session 1 Phonemic Awareness, Alphabetic Principle

778 views • 74 slides
Modifying Irrevocable Trusts: Changing the Unchangeable? Navigating Modification Methods,

Modifying Irrevocable Trusts: Changing the Unchangeable? Navigating Modification Methods,

Presenting a live 90-minute webinar with interactive Q&A Modifying Irrevocable Trusts: Changing the Unchangeable? Navigating Modification Methods, Governing Law, Consent Requirements, and Tax Considerations TUESDAY, JULY 12, 2016 1pm

1.2k views • 108 slides
PROMOTING HUMAN RIGHTS AND MINORITY PROTECTION IN SOUTH EAST EUROPE Presentation of findings

PROMOTING HUMAN RIGHTS AND MINORITY PROTECTION IN SOUTH EAST EUROPE Presentation of findings

PROMOTING HUMAN RIGHTS AND MINORITY PROTECTION IN SOUTH EAST EUROPE Presentation of findings Deliverable 4 Contents 1. Introduction

256 views • 23 slides
Building Ventures for the Internet & Blockchain Economy Investo r P resenta tio n 8 M a

Building Ventures for the Internet & Blockchain Economy Investo r P resenta tio n 8 M a

Building Ventures for the Internet & Blockchain Economy Investo r P resenta tio n 8 M a y 2 0 1 8 Aus tra lia | Singa po re | M a la y s ia | UK | Sw eden Disc sclaimer The information contained in this document (this

490 views • 30 slides
BRIDGING THE PATHWAY FROM INSTRUCTION TO RESEARCH AAAS/AIBS Summit 15 May 2008 Diane Ebert-May

BRIDGING THE PATHWAY FROM INSTRUCTION TO RESEARCH AAAS/AIBS Summit 15 May 2008 Diane Ebert-May

BRIDGING THE PATHWAY FROM INSTRUCTION TO RESEARCH AAAS/AIBS Summit 15 May 2008 Diane Ebert-May Michigan State University www.first.ecoinfomatics.org Engage What are your reasons for conducting educational research or not doing so? 1.

830 views • 21 slides

More recommend