ammi introduction to deep learning 4 1 dag networks
play

AMMI Introduction to Deep Learning 4.1. DAG networks Fran cois - PowerPoint PPT Presentation

Aug 20, 2023 •23 likes •353 views

AMMI Introduction to Deep Learning 4.1. DAG networks Fran cois Fleuret https://fleuret.org/ammi-2018/ Wed Aug 29 16:57:27 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Everything we have seen for an MLP w (1) b (1) w (2) b (2)

  1. AMMI – Introduction to Deep Learning 4.1. DAG networks Fran¸ cois Fleuret https://fleuret.org/ammi-2018/ Wed Aug 29 16:57:27 CAT 2018 ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE

  2. Everything we have seen for an MLP w (1) b (1) w (2) b (2) x + σ + σ f ( x ) × × Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 1 / 11

  3. Everything we have seen for an MLP w (1) b (1) w (2) b (2) x + σ + σ f ( x ) × × can be generalized to an arbitrary “Directed Acyclic Graph” (DAG) of operators w (1) φ (1) φ (3) f ( x ) φ (2) x w (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 1 / 11

  4. Remember that we use tensorial notation. If ( a 1 , . . . , a Q ) = φ ( b 1 , . . . , b R ), we have  ∂ a 1 ∂ a 1  . . . � ∂ a ∂ b 1 ∂ b R � . .  ...  . . = J φ =  .   . .   ∂ b  ∂ a Q ∂ a Q . . . ∂ b 1 ∂ b R This notation does not specify at which point this is computed. It will always be for the forward-pass activations. Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 2 / 11

  5. Remember that we use tensorial notation. If ( a 1 , . . . , a Q ) = φ ( b 1 , . . . , b R ), we have  ∂ a 1 ∂ a 1  . . . � ∂ a ∂ b 1 ∂ b R � . .  ...  . . = J φ =  .   . .   ∂ b  ∂ a Q ∂ a Q . . . ∂ b 1 ∂ b R This notation does not specify at which point this is computed. It will always be for the forward-pass activations. Also, if ( a 1 , . . . , a Q ) = φ ( b 1 , . . . , b R , c 1 , . . . , c S ), we use  ∂ a 1 ∂ a 1  . . . � ∂ a ∂ c 1 ∂ c S � . .  ...  . . = J φ | c =  .   . . ∂ c    ∂ a Q ∂ a Q . . . ∂ c 1 ∂ c S Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 2 / 11

  6. Forward pass w (1) φ (1) φ (3) f ( x ) = x (3) x (1) x (0) = x φ (2) x (2) w (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 3 / 11

  7. Forward pass w (1) φ (1) φ (3) f ( x ) = x (3) x (1) x (0) = x φ (2) x (2) w (2) x (0) = x Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 3 / 11

  8. Forward pass w (1) φ (1) φ (3) f ( x ) = x (3) x (1) x (0) = x φ (2) x (2) w (2) x (0) = x x (1) = φ (1) ( x (0) ; w (1) ) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 3 / 11

  9. Forward pass w (1) φ (1) φ (3) f ( x ) = x (3) x (1) x (0) = x φ (2) x (2) w (2) x (0) = x x (1) = φ (1) ( x (0) ; w (1) ) x (2) = φ (2) ( x (0) , x (1) ; w (2) ) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 3 / 11

  10. Forward pass w (1) φ (1) φ (3) f ( x ) = x (3) x (1) x (0) = x φ (2) x (2) w (2) x (0) = x x (1) = φ (1) ( x (0) ; w (1) ) x (2) = φ (2) ( x (0) , x (1) ; w (2) ) f ( x ) = x (3) = φ (3) ( x (1) , x (2) ; w (1) ) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 3 / 11

  11. Backward pass, derivatives w.r.t activations w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 4 / 11

  12. Backward pass, derivatives w.r.t activations w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ x (3) � � � = = J φ (3) | x (2) ∂ x (2) ∂ x (2) ∂ x (3) ∂ x (3) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 4 / 11

  13. Backward pass, derivatives w.r.t activations w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ x (3) � � � = = J φ (3) | x (2) ∂ x (2) ∂ x (2) ∂ x (3) ∂ x (3) � ∂ 퓁 � � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ 퓁 � � ∂ x (2) ∂ x (3) � � � � � = + = J φ (2) | x (1) + J φ (3) | x (1) ∂ x (1) ∂ x (1) ∂ x (2) ∂ x (1) ∂ x (3) ∂ x (2) ∂ x (3) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 4 / 11

  14. Backward pass, derivatives w.r.t activations w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ x (3) � � � = = J φ (3) | x (2) ∂ x (2) ∂ x (2) ∂ x (3) ∂ x (3) � ∂ 퓁 � � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ 퓁 � � ∂ x (2) ∂ x (3) � � � � � = + = J φ (2) | x (1) + J φ (3) | x (1) ∂ x (1) ∂ x (1) ∂ x (2) ∂ x (1) ∂ x (3) ∂ x (2) ∂ x (3) � ∂ 퓁 � � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ 퓁 � � ∂ x (1) ∂ x (2) � � � � � = + = J φ (1) | x (0) + J φ (2) | x (0) ∂ x (0) ∂ x (0) ∂ x (1) ∂ x (0) ∂ x (2) ∂ x (1) ∂ x (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 4 / 11

  15. Backward pass, derivatives w.r.t parameters w (1) φ (1) x (1) φ (3) f ( x ) = x (3) φ (2) x (0) = x x (2) w (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 5 / 11

  16. Backward pass, derivatives w.r.t parameters w (1) φ (1) x (1) φ (3) f ( x ) = x (3) φ (2) x (0) = x x (2) w (2) � ∂ 퓁 � � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ 퓁 � � ∂ x (1) ∂ x (3) � � � � � = + = J φ (1) | w (1) + J φ (3) | w (1) ∂ w (1) ∂ w (1) ∂ x (1) ∂ w (1) ∂ x (3) ∂ x (1) ∂ x (3) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 5 / 11

  17. Backward pass, derivatives w.r.t parameters w (1) φ (1) x (1) φ (3) f ( x ) = x (3) φ (2) x (0) = x x (2) w (2) � ∂ 퓁 � � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ 퓁 � � ∂ x (1) ∂ x (3) � � � � � = + = J φ (1) | w (1) + J φ (3) | w (1) ∂ w (1) ∂ w (1) ∂ x (1) ∂ w (1) ∂ x (3) ∂ x (1) ∂ x (3) � ∂ 퓁 � � ∂ 퓁 � ∂ 퓁 � ∂ x (2) � � � = = J φ (2) | w (2) ∂ w (2) ∂ w (2) ∂ x (2) ∂ x (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 5 / 11

  18. So if we have a library of “tensor operators”, and implementations of ( x 1 , . . . , x d , w ) �→ φ ( x 1 , . . . , x d ; w ) ∀ c , ( x 1 , . . . , x d , w ) �→ J φ | x c ( x 1 , . . . , x d ; w ) ( x 1 , . . . , x d , w ) �→ J φ | w ( x 1 , . . . , x d ; w ) , Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 6 / 11

  19. So if we have a library of “tensor operators”, and implementations of ( x 1 , . . . , x d , w ) �→ φ ( x 1 , . . . , x d ; w ) ∀ c , ( x 1 , . . . , x d , w ) �→ J φ | x c ( x 1 , . . . , x d ; w ) ( x 1 , . . . , x d , w ) �→ J φ | w ( x 1 , . . . , x d ; w ) , we can build an arbitrary directed acyclic graph with these operators at the nodes, compute the response of the resulting mapping, and compute its gradient with back-prop. Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 6 / 11

  20. Writing from scratch a large neural network is complex and error-prone. Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 7 / 11

  21. Writing from scratch a large neural network is complex and error-prone. Multiple frameworks provide libraries of tensor operators and mechanisms to combine them into DAGs and automatically differentiate them. Language(s) License Main backer PyTorch Python BSD Facebook Caffe2 C++, Python Apache Facebook TensorFlow Python, C++ Apache Google MXNet Python, C++, R, Scala Apache Amazon CNTK Python, C++ MIT Microsoft Torch Lua BSD Facebook Theano Python BSD U. of Montreal Caffe C++ BSD 2 clauses U. of CA, Berkeley Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 7 / 11

  22. Writing from scratch a large neural network is complex and error-prone. Multiple frameworks provide libraries of tensor operators and mechanisms to combine them into DAGs and automatically differentiate them. Language(s) License Main backer PyTorch Python BSD Facebook Caffe2 C++, Python Apache Facebook TensorFlow Python, C++ Apache Google MXNet Python, C++, R, Scala Apache Amazon CNTK Python, C++ MIT Microsoft Torch Lua BSD Facebook Theano Python BSD U. of Montreal Caffe C++ BSD 2 clauses U. of CA, Berkeley One approach is to define the nodes and edges of such a DAG statically (Torch, TensorFlow, Caffe, Theano, etc.) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 7 / 11

  23. In TensorFlow, to run a forward/backward pass on w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 8 / 11

  24. In TensorFlow, to run a forward/backward pass on w (1) φ (1) φ (3) f ( x ) = x (3) x (1) φ (2) x (0) = x x (2) w (2) φ (1) � x (0) ; w (1) � = w (1) x (0) φ (2) � x (0) , x (1) ; w (2) � = x (0) + w (2) x (1) φ (3) � x (1) , x (2) ; w (1) � = w (1) � x (1) + x (2) � Fran¸ cois Fleuret AMMI – Introduction to Deep Learning / 4.1. DAG networks 8 / 11

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

AMMI Introduction to Deep Learning 7.3. Networks for object detection Fran cois Fleuret

AMMI Introduction to Deep Learning 7.3. Networks for object detection Fran cois Fleuret

AMMI Introduction to Deep Learning 7.3. Networks for object detection Fran cois Fleuret https://fleuret.org/ammi-2018/ Wed Aug 29 16:58:03 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE The simplest strategy to move from image

656 views • 48 slides
AMMI Introduction to Deep Learning 10.1. Generative Adversarial Networks Fran cois Fleuret

AMMI Introduction to Deep Learning 10.1. Generative Adversarial Networks Fran cois Fleuret

AMMI Introduction to Deep Learning 10.1. Generative Adversarial Networks Fran cois Fleuret https://fleuret.org/ammi-2018/ Thu Sep 6 16:09:56 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE A different approach to learn

666 views • 63 slides
AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret

AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret

AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:38:28 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Residual networks Fran cois Fleuret AMMI

732 views • 36 slides
AMMI Introduction to Deep Learning 6.6. Using GPUs Fran cois Fleuret

AMMI Introduction to Deep Learning 6.6. Using GPUs Fran cois Fleuret

AMMI Introduction to Deep Learning 6.6. Using GPUs Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:38:37 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE The size of current state-of-the-art networks makes computation

946 views • 36 slides
AMMI Introduction to Deep Learning 7.2. Networks for image classification Fran cois

AMMI Introduction to Deep Learning 7.2. Networks for image classification Fran cois

AMMI Introduction to Deep Learning 7.2. Networks for image classification Fran cois Fleuret https://fleuret.org/ammi-2018/ Thu Sep 6 15:26:25 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Image classification, standard convnets

827 views • 71 slides
AMMI Introduction to Deep Learning 6.3. Dropout Fran cois Fleuret

AMMI Introduction to Deep Learning 6.3. Dropout Fran cois Fleuret

AMMI Introduction to Deep Learning 6.3. Dropout Fran cois Fleuret https://fleuret.org/ammi-2018/ Wed Aug 29 16:57:55 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE A first deep regularization technique is dropout (Srivastava

684 views • 29 slides
AMMI Introduction to Deep Learning 9.1. Transposed convolutions Fran cois Fleuret

AMMI Introduction to Deep Learning 9.1. Transposed convolutions Fran cois Fleuret

AMMI Introduction to Deep Learning 9.1. Transposed convolutions Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:39:08 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Constructing deep generative architectures

849 views • 46 slides
AMMI Introduction to Deep Learning 11.2. LSTM and GRU Fran cois Fleuret

AMMI Introduction to Deep Learning 11.2. LSTM and GRU Fran cois Fleuret

AMMI Introduction to Deep Learning 11.2. LSTM and GRU Fran cois Fleuret https://fleuret.org/ammi-2018/ November 12, 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE The Long-Short Term Memory unit (LSTM) by Hochreiter and Schmidhuber

310 views • 30 slides
AMMI Introduction to Deep Learning 8.4. Optimizing inputs Fran cois Fleuret

AMMI Introduction to Deep Learning 8.4. Optimizing inputs Fran cois Fleuret

AMMI Introduction to Deep Learning 8.4. Optimizing inputs Fran cois Fleuret https://fleuret.org/ammi-2018/ Thu Sep 6 16:00:44 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Maximum response samples Fran cois Fleuret AMMI

686 views • 45 slides
AMMI Introduction to Deep Learning 6.4. Batch normalization Fran cois Fleuret

AMMI Introduction to Deep Learning 6.4. Batch normalization Fran cois Fleuret

AMMI Introduction to Deep Learning 6.4. Batch normalization Fran cois Fleuret https://fleuret.org/ammi-2018/ Sun Sep 30 10:42:14 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE We saw that maintaining proper statistics of the

565 views • 31 slides
AMMI Introduction to Deep Learning 10.4. Model persistence and checkpoints Fran cois

AMMI Introduction to Deep Learning 10.4. Model persistence and checkpoints Fran cois

AMMI Introduction to Deep Learning 10.4. Model persistence and checkpoints Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:35:06 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Saving and loading models is key to use

335 views • 19 slides
AMMI Introduction to Deep Learning 5.3. PyTorch optimizers Fran cois Fleuret

AMMI Introduction to Deep Learning 5.3. PyTorch optimizers Fran cois Fleuret

AMMI Introduction to Deep Learning 5.3. PyTorch optimizers Fran cois Fleuret https://fleuret.org/ammi-2018/ Sat Nov 10 11:27:22 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE The PyTorch module torch.optim provides many

791 views • 14 slides
AMMI Introduction to Deep Learning 1.2. Current applications and success Fran cois Fleuret

AMMI Introduction to Deep Learning 1.2. Current applications and success Fran cois Fleuret

AMMI Introduction to Deep Learning 1.2. Current applications and success Fran cois Fleuret https://fleuret.org/ammi-2018/ Sat Oct 6 18:43:49 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Object detection and segmentation

482 views • 26 slides
AMMI Introduction to Deep Learning 1.3. What is really happening? Fran cois Fleuret

AMMI Introduction to Deep Learning 1.3. What is really happening? Fran cois Fleuret

AMMI Introduction to Deep Learning 1.3. What is really happening? Fran cois Fleuret https://fleuret.org/ammi-2018/ Wed Aug 29 16:56:56 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE (Zeiler and Fergus, 2014) Fran cois Fleuret

615 views • 16 slides
AMMI Introduction to Deep Learning 8.3. Visualizing the processing in the input Fran cois

AMMI Introduction to Deep Learning 8.3. Visualizing the processing in the input Fran cois

AMMI Introduction to Deep Learning 8.3. Visualizing the processing in the input Fran cois Fleuret https://fleuret.org/ammi-2018/ Thu Sep 6 15:58:38 CAT 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Occlusion sensitivity Fran

687 views • 46 slides
AMMI Introduction to Deep Learning 8.2. Looking at activations Fran cois Fleuret

AMMI Introduction to Deep Learning 8.2. Looking at activations Fran cois Fleuret

AMMI Introduction to Deep Learning 8.2. Looking at activations Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:39:02 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Convnet internal layer activations Fran cois

748 views • 50 slides
MA/CSSE 473 Day 13 Finish Topological Sort Permutation Generation MA/CSSE 473 Day 13

MA/CSSE 473 Day 13 Finish Topological Sort Permutation Generation MA/CSSE 473 Day 13

MA/CSSE 473 Day 13 Finish Topological Sort Permutation Generation MA/CSSE 473 Day 13 Student Questions Finish Topological Sort Permutation generation 1 Recap: Topologically sort a DAG DAG = Directed Aclyclic Graph Linearly

473 views • 11 slides
The Algebra of DAGs Marcelo Fiore Computer Laboratory University of Cambridge Samson@60

The Algebra of DAGs Marcelo Fiore Computer Laboratory University of Cambridge Samson@60

The Algebra of DAGs Marcelo Fiore Computer Laboratory University of Cambridge Samson@60 28.V.2013 Joint work with Marco Devesas Campos A Question of Robin Milner A Question of Robin Milner On the generalization from tree structure . . .

848 views • 46 slides
Nick Schrock Founder, Elementl @schrockn Our data is totally broken Our data is

Nick Schrock Founder, Elementl @schrockn Our data is totally broken Our data is

Nick Schrock Founder, Elementl @schrockn Our data is totally broken Our data is totally broken We dont know where our data comes from We dont know what it means We cannot reliably process and test it Our

951 views • 66 slides
CAUSAL DISCOVERY CAUSAL DISCOVERY Beware of the DAG! Beware of the DAG! Philip Dawid

CAUSAL DISCOVERY CAUSAL DISCOVERY Beware of the DAG! Beware of the DAG! Philip Dawid

CAUSAL DISCOVERY CAUSAL DISCOVERY Beware of the DAG! Beware of the DAG! Philip Dawid University of Cambridge Seeing and Doing Seeing and Doing Causality is about the effects of interventions To discover these we really should

640 views • 15 slides
CSE 421 Longest Path in a DAG, LIS, Shortest Path with Negative Weights Shayan Oveis Gharan 1

CSE 421 Longest Path in a DAG, LIS, Shortest Path with Negative Weights Shayan Oveis Gharan 1

CSE 421 Longest Path in a DAG, LIS, Shortest Path with Negative Weights Shayan Oveis Gharan 1 Longest Path in a DAG Longest Path in a DAG Goal: Given a DAG G, find the longest path. Recall: A directed graph G is a DAG if it has no cycle.

571 views • 23 slides
Digital Logic Design: a rigorous approach c Chapter 4: Directed Graphs Guy Even Moti Medina

Digital Logic Design: a rigorous approach c Chapter 4: Directed Graphs Guy Even Moti Medina

Digital Logic Design: a rigorous approach c Chapter 4: Directed Graphs Guy Even Moti Medina School of Electrical Engineering Tel-Aviv Univ. March 19, 2020 Book Homepage: http://www.eng.tau.ac.il/~guy/Even-Medina 1 / 27 Directed Graphs

311 views • 28 slides
Tracking P4 Program Execution in the Data Plane SOSR 20 Suriya Kodeswaran Mina Arashloo,

Tracking P4 Program Execution in the Data Plane SOSR 20 Suriya Kodeswaran Mina Arashloo,

Tracking P4 Program Execution in the Data Plane SOSR 20 Suriya Kodeswaran Mina Arashloo, Praveen Tammana, Jennifer Rexford 1 Background: P4 Compilation Input program Compiler maps programs to hardware target Optimizes to work

258 views • 15 slides
Learning in Bayes Nets Bayes Nets: 1. Parameter Learning/Estimation: infer from data, given G

Learning in Bayes Nets Bayes Nets: 1. Parameter Learning/Estimation: infer from data, given G

Learning in Bayes Nets Bayes Nets: 1. Parameter Learning/Estimation: infer from data, given G Learning Parameters and Parents P(W|Pa) P(~W|Pa) 1 =? 1 1 ~L,~R Structure 2 =? 1 2 ~L,R 3 =? 1 3 L,~R 4

401 views • 10 slides

More recommend