SlideShare a Scribd company logo
1 of 17
Convolutional
Neural Network
Subash Chandra Pakhrin
PhD Student
Wichita State University
Wichita, Kansas
Convolutional Neural Network
[1] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in
Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
Back-Propagation
[2] Rumelhart, D., Hinton, G. & Williams, R. Learning representations by back-propagating errors. Nature 323,
533–536 (1986). https://doi.org/10.1038/323533a0
Image Net Classification with Deep
Convolutional Neural Networks
[3] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, Image Net Classification with Deep Convolutional Neural
Networks, Advances in Neural Information Processing Systems 25 (NIPS 2012)
Convolution Layer
Convolution Layer
7x7 input(spatially) assume 3x3 filter (Stride 1)
5 x 5 output
i.e. 5 spatial location horizontally,
5 spatial location vertically
7x7 input(spatially) assume 3x3 filter (Stride 2)
3 x 3 output
i.e. 3 spatial location horizontally,
3 spatial location vertically
A closer look at spatial dimensions:
• We don’t do convolution like this because it produces asymmetric output
7x7 input (spatially) assumes 3x3 filter applied
with stride 3?
Doesn’t fit!!!
Cannot apply 3x3 filter on 7x7 input with stride
3.
Output Size formula
In practice: Common to zero pad the border
e.g. input 7x7
3x3 filter, applied with stride 1
Pad with 1 pixel border => what is the output?
Output => 7x7 !!!
(recall:)
(N-F)/stride +1
Example:
Input volume: 32x32x3
10, 5x5 filters with stride 1, pad 2
New N = 36 after pad 2, F = 5, stride = 1
(N-F)/stride +1
Output volume size:?
32 x 32 x 10
Number of parameters in this layer?
each filter has 5*5*3+1 = 76 parameters (+1 for bias)
=>76*10=760
Convolution Layer
For example, if we had 6 5x5 filters, we’ll get 6 separate activation maps.
ConvNet is a sequence of Convolutional Layers,
interspersed with activation functions
Caution!!!
32x32 input convolved repeatedly with 5x5 filters shrinks volumes spatially!
Shrinking too fast is not good, doesn’t work well.
References:
[1] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document
recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998
[2] Rumelhart, D., Hinton, G. & Williams, R. Learning representations by back-propagating errors.
Nature 323, 533–536 (1986)
[3] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, Image Net Classification with Deep
Convolutional Neural Networks, Advances in Neural Information Processing Systems 25 (NIPS 2012)
[4] Fei-Fei Li, Justin Johnson & Serena Yeung, Lecture 5| Convolutional Neural Networks,
https://youtu.be/bNb2fEVKeEo
[5] Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object
Detection with Region Proposal Networks, Advances in Neural Information Processing Systems 28
(NIPS 2015)
[6] Daniel Levy, Arzav Jain, Breast Mass Classification from Mammograms using Deep Convolutional
Neural Networks, Computer Vision and Pattern Recognition, NIPS 2016
[7] Jonathan Krause, Justin Johnson, Ranjay Krishna, Li Fei-Fei, A Hierarchical Approach for
Generating Descriptive Image Paragraphs The IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 2017, pp. 317-325

More Related Content

Similar to Cnn april 8 2020

Deep randomized neural networks
Deep randomized neural networksDeep randomized neural networks
Deep randomized neural networksClaudio Gallicchio
 
Community Analysis of Deep Networks (poster)
Community Analysis of Deep Networks (poster)Community Analysis of Deep Networks (poster)
Community Analysis of Deep Networks (poster)Behrang Mehrparvar
 
Neural Networks and Deep Learning Syllabus
Neural Networks and Deep Learning SyllabusNeural Networks and Deep Learning Syllabus
Neural Networks and Deep Learning SyllabusAndres Mendez-Vazquez
 
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...Universitat Politècnica de Catalunya
 
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...Universitat Politècnica de Catalunya
 
Paper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsPaper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsYOU SHENG CHEN
 
neuronal network of NS systems short.ppt
neuronal network of NS systems short.pptneuronal network of NS systems short.ppt
neuronal network of NS systems short.pptAnanua1
 
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appDetails of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appPAY2 YOU
 
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...GeeksLab Odessa
 
Learning Sparse Neural Networksvia Sensitivity-Driven Regularization
Learning Sparse Neural Networksvia Sensitivity-Driven RegularizationLearning Sparse Neural Networksvia Sensitivity-Driven Regularization
Learning Sparse Neural Networksvia Sensitivity-Driven RegularizationEnzo Tartaglione
 
Brain Networks
Brain NetworksBrain Networks
Brain NetworksJimmy Lu
 
A scoping review of Machine Learning in Seismic Geophysics
A scoping review of Machine Learning in Seismic GeophysicsA scoping review of Machine Learning in Seismic Geophysics
A scoping review of Machine Learning in Seismic GeophysicsChristopher Mancuso
 
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...Hakka Labs
 
Iterative Multi-document Neural Attention for Multiple Answer Prediction
Iterative Multi-document Neural Attention for Multiple Answer PredictionIterative Multi-document Neural Attention for Multiple Answer Prediction
Iterative Multi-document Neural Attention for Multiple Answer PredictionAlessandro Suglia
 
intrusion-detection-using-ML.pptx
intrusion-detection-using-ML.pptxintrusion-detection-using-ML.pptx
intrusion-detection-using-ML.pptxSahilSingh316535
 
AI alignment from the Active Inference perspective 2023.pdf
AI alignment from the Active Inference perspective 2023.pdfAI alignment from the Active Inference perspective 2023.pdf
AI alignment from the Active Inference perspective 2023.pdfRoman Leventov
 
Evolution of Deep Learning and new advancements
Evolution of Deep Learning and new advancementsEvolution of Deep Learning and new advancements
Evolution of Deep Learning and new advancementsChitta Ranjan
 
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Universitat Politècnica de Catalunya
 
Multi sensor-fusion
Multi sensor-fusionMulti sensor-fusion
Multi sensor-fusion万言 李
 

Similar to Cnn april 8 2020 (20)

Deep randomized neural networks
Deep randomized neural networksDeep randomized neural networks
Deep randomized neural networks
 
Community Analysis of Deep Networks (poster)
Community Analysis of Deep Networks (poster)Community Analysis of Deep Networks (poster)
Community Analysis of Deep Networks (poster)
 
Neural Networks and Deep Learning Syllabus
Neural Networks and Deep Learning SyllabusNeural Networks and Deep Learning Syllabus
Neural Networks and Deep Learning Syllabus
 
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...
Advanced Deep Architectures (D2L6 Deep Learning for Speech and Language UPC 2...
 
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...
Interpretability of Convolutional Neural Networks - Xavier Giro - UPC Barcelo...
 
Functional Brain Networks - Javier M. Buldù
Functional Brain Networks - Javier M. BuldùFunctional Brain Networks - Javier M. Buldù
Functional Brain Networks - Javier M. Buldù
 
Paper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsPaper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applications
 
neuronal network of NS systems short.ppt
neuronal network of NS systems short.pptneuronal network of NS systems short.ppt
neuronal network of NS systems short.ppt
 
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appDetails of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
 
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
 
Learning Sparse Neural Networksvia Sensitivity-Driven Regularization
Learning Sparse Neural Networksvia Sensitivity-Driven RegularizationLearning Sparse Neural Networksvia Sensitivity-Driven Regularization
Learning Sparse Neural Networksvia Sensitivity-Driven Regularization
 
Brain Networks
Brain NetworksBrain Networks
Brain Networks
 
A scoping review of Machine Learning in Seismic Geophysics
A scoping review of Machine Learning in Seismic GeophysicsA scoping review of Machine Learning in Seismic Geophysics
A scoping review of Machine Learning in Seismic Geophysics
 
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...
Intuidex - To be or not to be iid by William M. Pottenger (NYC Machine Learni...
 
Iterative Multi-document Neural Attention for Multiple Answer Prediction
Iterative Multi-document Neural Attention for Multiple Answer PredictionIterative Multi-document Neural Attention for Multiple Answer Prediction
Iterative Multi-document Neural Attention for Multiple Answer Prediction
 
intrusion-detection-using-ML.pptx
intrusion-detection-using-ML.pptxintrusion-detection-using-ML.pptx
intrusion-detection-using-ML.pptx
 
AI alignment from the Active Inference perspective 2023.pdf
AI alignment from the Active Inference perspective 2023.pdfAI alignment from the Active Inference perspective 2023.pdf
AI alignment from the Active Inference perspective 2023.pdf
 
Evolution of Deep Learning and new advancements
Evolution of Deep Learning and new advancementsEvolution of Deep Learning and new advancements
Evolution of Deep Learning and new advancements
 
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
 
Multi sensor-fusion
Multi sensor-fusionMulti sensor-fusion
Multi sensor-fusion
 

More from Subash Chandra Pakhrin

Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMTorsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMSubash Chandra Pakhrin
 
Characterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedCharacterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedSubash Chandra Pakhrin
 
Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Subash Chandra Pakhrin
 
Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Subash Chandra Pakhrin
 

More from Subash Chandra Pakhrin (20)

Prismoid
PrismoidPrismoid
Prismoid
 
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMTorsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
 
COVID 19
COVID 19 COVID 19
COVID 19
 
Lstm covid 19 prediction
Lstm covid 19 predictionLstm covid 19 prediction
Lstm covid 19 prediction
 
Rnn & Lstm
Rnn & LstmRnn & Lstm
Rnn & Lstm
 
Characterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedCharacterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites based
 
Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network
 
Ncit 1st ai lab
Ncit 1st ai labNcit 1st ai lab
Ncit 1st ai lab
 
Ai lab
Ai labAi lab
Ai lab
 
Constraint satisfaction problem
Constraint satisfaction problem Constraint satisfaction problem
Constraint satisfaction problem
 
Analysis
AnalysisAnalysis
Analysis
 
Planning
PlanningPlanning
Planning
 
Intelligent agents (bsc csit) lec 2
Intelligent agents (bsc csit) lec 2Intelligent agents (bsc csit) lec 2
Intelligent agents (bsc csit) lec 2
 
Final slide4 (bsc csit) chapter 4
Final slide4 (bsc csit) chapter 4Final slide4 (bsc csit) chapter 4
Final slide4 (bsc csit) chapter 4
 
Final slide (bsc csit) chapter 5
Final slide (bsc csit) chapter 5Final slide (bsc csit) chapter 5
Final slide (bsc csit) chapter 5
 
Lec 6 bsc csit
Lec 6 bsc csitLec 6 bsc csit
Lec 6 bsc csit
 
Two player games
Two player gamesTwo player games
Two player games
 
Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15
 
Final slide (bsc csit) chapter 2
Final slide (bsc csit) chapter 2Final slide (bsc csit) chapter 2
Final slide (bsc csit) chapter 2
 
Final slide (bsc csit) chapter 3
Final slide (bsc csit) chapter 3Final slide (bsc csit) chapter 3
Final slide (bsc csit) chapter 3
 

Recently uploaded

18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...RKavithamani
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3JemimahLaneBuaron
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 

Recently uploaded (20)

18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 

Cnn april 8 2020

  • 1. Convolutional Neural Network Subash Chandra Pakhrin PhD Student Wichita State University Wichita, Kansas
  • 2. Convolutional Neural Network [1] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
  • 3. Back-Propagation [2] Rumelhart, D., Hinton, G. & Williams, R. Learning representations by back-propagating errors. Nature 323, 533–536 (1986). https://doi.org/10.1038/323533a0
  • 4. Image Net Classification with Deep Convolutional Neural Networks [3] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, Image Net Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems 25 (NIPS 2012)
  • 5.
  • 8. 7x7 input(spatially) assume 3x3 filter (Stride 1) 5 x 5 output i.e. 5 spatial location horizontally, 5 spatial location vertically
  • 9. 7x7 input(spatially) assume 3x3 filter (Stride 2) 3 x 3 output i.e. 3 spatial location horizontally, 3 spatial location vertically
  • 10. A closer look at spatial dimensions: • We don’t do convolution like this because it produces asymmetric output 7x7 input (spatially) assumes 3x3 filter applied with stride 3? Doesn’t fit!!! Cannot apply 3x3 filter on 7x7 input with stride 3.
  • 12. In practice: Common to zero pad the border e.g. input 7x7 3x3 filter, applied with stride 1 Pad with 1 pixel border => what is the output? Output => 7x7 !!! (recall:) (N-F)/stride +1
  • 13. Example: Input volume: 32x32x3 10, 5x5 filters with stride 1, pad 2 New N = 36 after pad 2, F = 5, stride = 1 (N-F)/stride +1 Output volume size:? 32 x 32 x 10 Number of parameters in this layer? each filter has 5*5*3+1 = 76 parameters (+1 for bias) =>76*10=760
  • 14. Convolution Layer For example, if we had 6 5x5 filters, we’ll get 6 separate activation maps.
  • 15. ConvNet is a sequence of Convolutional Layers, interspersed with activation functions Caution!!! 32x32 input convolved repeatedly with 5x5 filters shrinks volumes spatially! Shrinking too fast is not good, doesn’t work well.
  • 16.
  • 17. References: [1] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998 [2] Rumelhart, D., Hinton, G. & Williams, R. Learning representations by back-propagating errors. Nature 323, 533–536 (1986) [3] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, Image Net Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems 25 (NIPS 2012) [4] Fei-Fei Li, Justin Johnson & Serena Yeung, Lecture 5| Convolutional Neural Networks, https://youtu.be/bNb2fEVKeEo [5] Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, Advances in Neural Information Processing Systems 28 (NIPS 2015) [6] Daniel Levy, Arzav Jain, Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks, Computer Vision and Pattern Recognition, NIPS 2016 [7] Jonathan Krause, Justin Johnson, Ranjay Krishna, Li Fei-Fei, A Hierarchical Approach for Generating Descriptive Image Paragraphs The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 317-325