SlideShare a Scribd company logo
1 of 14
Deep learning
Modeling high-level face features
through deep networks
Explaining deep learning to my mommy
Biological motivation
[1]
Scale
● Low costs
○ ≈ $ 4000/m
(100ECUs e 10TB)
● Elastic clusters
● Network vs. Disk
● GPUs
● Data
o Variability
o Volume
o Easy acquisition
Learning
● Lower learning time
● Distributed networks
● Feature extraction
● Deepness with low
error rates
[2]
Convolutional Networks
Layer n - Primitive shapes
[3]
Layer n+1 - Complex shapes
[3]
Performance ILSVRC2013
Team Comments Error rate
Clarifai
Average of multiple models on original
training data.
0.11743
Clarifai
Another attempt at multiple models on
original training data.
0.1215
Clarifai Single model trained on original data. 0.12535
NUS
adaptive non-parametric rectification of
all outputs from CNNs and refined
PASCAL VOC12 winning solution, with
further retraining on the validation set.
0.12953
NUS
adaptive non-parametric rectification of
all outputs from CNNs and refined
PASCAL VOC12 winning solution.
0.13303
[4]
Image Classification
Clarifai results
Face features recognition
Clarifai results
References
1. Wong, Rachel et al. (2005): "Circuits of vertebrate retina". Nature
Magazine, Volume 9 Number 1.
2. Huang G.B., Lee H., Miller E. L. (2012): “Learning Hierarchical
Representations for Face Verification with Convolutional Deep Belief
Networks”
3. Ng A. et al (2012): “Emergence of Object-Selective Features in
Unsupervised Feature Learning.”
4. Image-net.org, (2014). ImageNet. Available at: http://www.image-net.org/.

More Related Content

What's hot

Score based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential EquationsScore based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential EquationsSungchul Kim
 
Multidimension Scaling and Isomap
Multidimension Scaling and IsomapMultidimension Scaling and Isomap
Multidimension Scaling and IsomapCheng-Shiang Li
 
Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...Universitat Politècnica de Catalunya
 
Ashfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, PepperdataAshfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, PepperdataMLconf
 
Restricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for AttributionRestricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for Attributiontaeseon ryu
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...PyData
 
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드taeseon ryu
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...MLconf
 
Case Study of Convolutional Neural Network
Case Study of Convolutional Neural NetworkCase Study of Convolutional Neural Network
Case Study of Convolutional Neural NetworkNamHyuk Ahn
 
Learning the Structure of Related Tasks
Learning the Structure of Related Tasks Learning the Structure of Related Tasks
Learning the Structure of Related Tasks butest
 
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper reviewtaeseon ryu
 
Understanding Convolutional Neural Networks
Understanding Convolutional Neural NetworksUnderstanding Convolutional Neural Networks
Understanding Convolutional Neural NetworksJeremy Nixon
 
Why Batch Normalization Works so Well
Why Batch Normalization Works so WellWhy Batch Normalization Works so Well
Why Batch Normalization Works so WellChun-Ming Chang
 
Machine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural NetworksMachine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural NetworksAndrew Ferlitsch
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnnDebarko De
 
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Universitat Politècnica de Catalunya
 
How does unlabeled data improve generalization in self training
How does unlabeled data improve generalization in self trainingHow does unlabeled data improve generalization in self training
How does unlabeled data improve generalization in self trainingtaeseon ryu
 
Introduction To Tensorflow
Introduction To TensorflowIntroduction To Tensorflow
Introduction To TensorflowRayyan Khalid
 
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...Daiki Tanaka
 

What's hot (20)

Score based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential EquationsScore based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential Equations
 
Multidimension Scaling and Isomap
Multidimension Scaling and IsomapMultidimension Scaling and Isomap
Multidimension Scaling and Isomap
 
Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...
 
Ashfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, PepperdataAshfaq Munshi, ML7 Fellow, Pepperdata
Ashfaq Munshi, ML7 Fellow, Pepperdata
 
Restricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for AttributionRestricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for Attribution
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
 
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드
딥러닝 논문읽기 모임 - 송헌 Deep sets 슬라이드
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
 
Case Study of Convolutional Neural Network
Case Study of Convolutional Neural NetworkCase Study of Convolutional Neural Network
Case Study of Convolutional Neural Network
 
Learning the Structure of Related Tasks
Learning the Structure of Related Tasks Learning the Structure of Related Tasks
Learning the Structure of Related Tasks
 
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review
[딥논읽] Meta-Transfer Learning for Zero-Shot Super-Resolution paper review
 
Understanding Convolutional Neural Networks
Understanding Convolutional Neural NetworksUnderstanding Convolutional Neural Networks
Understanding Convolutional Neural Networks
 
Why Batch Normalization Works so Well
Why Batch Normalization Works so WellWhy Batch Normalization Works so Well
Why Batch Normalization Works so Well
 
Machine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural NetworksMachine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural Networks
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
 
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
 
How does unlabeled data improve generalization in self training
How does unlabeled data improve generalization in self trainingHow does unlabeled data improve generalization in self training
How does unlabeled data improve generalization in self training
 
Introduction To Tensorflow
Introduction To TensorflowIntroduction To Tensorflow
Introduction To Tensorflow
 
Network recasting
Network recastingNetwork recasting
Network recasting
 
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...
[Paper reading] L-SHAPLEY AND C-SHAPLEY: EFFICIENT MODEL INTERPRETATION FOR S...
 

Viewers also liked

Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...
Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...
Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...Istituto nazionale di statistica
 
3 velocidadesinferida&máximaseguracrítica
3 velocidadesinferida&máximaseguracrítica3 velocidadesinferida&máximaseguracrítica
3 velocidadesinferida&máximaseguracríticaSierra Francisco Justo
 
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16LifePointe Church
 
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd Endorsement
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd EndorsementAl Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd Endorsement
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd EndorsementAl Gage
 
Waarom Marc Rich gratie kreeg van Clinton
Waarom Marc Rich gratie kreeg van ClintonWaarom Marc Rich gratie kreeg van Clinton
Waarom Marc Rich gratie kreeg van ClintonThierry Debels
 
Walking in Place with Wearable Technology: the development of a system for tr...
Walking in Place with Wearable Technology: the development of a system for tr...Walking in Place with Wearable Technology: the development of a system for tr...
Walking in Place with Wearable Technology: the development of a system for tr...Karel Van Isacker
 
Economy – its meaning and types
Economy – its meaning and typesEconomy – its meaning and types
Economy – its meaning and typesindianeducation
 
Acta asamblea ambiental 11 junio (completa)
Acta asamblea ambiental 11 junio (completa)Acta asamblea ambiental 11 junio (completa)
Acta asamblea ambiental 11 junio (completa)Felipe Figueroa Tancara
 
Vicioceans
VicioceansVicioceans
VicioceansIDoDots
 
The Future of Wearable Technology
The Future of Wearable TechnologyThe Future of Wearable Technology
The Future of Wearable TechnologyFresh Digital Group
 
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...StevenHouben
 
The world of steel
The world of steelThe world of steel
The world of steelTata Steel
 
Who will be the next superpower ??
Who will be the next superpower ??Who will be the next superpower ??
Who will be the next superpower ??Abhishek Dawachya
 
THANK YOU THANK YOU THANK YOU.
THANK YOU THANK YOU THANK YOU.THANK YOU THANK YOU THANK YOU.
THANK YOU THANK YOU THANK YOU.Sarah Corbin
 
Strategic Human Resource Management Lecture 10
Strategic Human Resource Management Lecture 10Strategic Human Resource Management Lecture 10
Strategic Human Resource Management Lecture 10RECONNECT
 

Viewers also liked (20)

Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...
Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...
Progetto "Statistica a scuola" ICS Aldo Moro – Maddaloni (CE) - E' tempo di p...
 
Presentation1
Presentation1Presentation1
Presentation1
 
3 velocidadesinferida&máximaseguracrítica
3 velocidadesinferida&máximaseguracrítica3 velocidadesinferida&máximaseguracrítica
3 velocidadesinferida&máximaseguracrítica
 
img047
img047img047
img047
 
Resume
ResumeResume
Resume
 
Fluidos
FluidosFluidos
Fluidos
 
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16
Message Series - ADVENTure - Part 3 - Jesus Came To Bring Us To God - 12-18-16
 
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd Endorsement
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd EndorsementAl Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd Endorsement
Al Gage LOA Flag Pageant El Tore Marine Base 1st & 2nd Endorsement
 
0313_001-3
0313_001-30313_001-3
0313_001-3
 
Waarom Marc Rich gratie kreeg van Clinton
Waarom Marc Rich gratie kreeg van ClintonWaarom Marc Rich gratie kreeg van Clinton
Waarom Marc Rich gratie kreeg van Clinton
 
Walking in Place with Wearable Technology: the development of a system for tr...
Walking in Place with Wearable Technology: the development of a system for tr...Walking in Place with Wearable Technology: the development of a system for tr...
Walking in Place with Wearable Technology: the development of a system for tr...
 
Economy – its meaning and types
Economy – its meaning and typesEconomy – its meaning and types
Economy – its meaning and types
 
Acta asamblea ambiental 11 junio (completa)
Acta asamblea ambiental 11 junio (completa)Acta asamblea ambiental 11 junio (completa)
Acta asamblea ambiental 11 junio (completa)
 
Vicioceans
VicioceansVicioceans
Vicioceans
 
The Future of Wearable Technology
The Future of Wearable TechnologyThe Future of Wearable Technology
The Future of Wearable Technology
 
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...
[CHI2015] WatchConnect: A Toolkit for Prototyping Smartwatch-Centric Cross-De...
 
The world of steel
The world of steelThe world of steel
The world of steel
 
Who will be the next superpower ??
Who will be the next superpower ??Who will be the next superpower ??
Who will be the next superpower ??
 
THANK YOU THANK YOU THANK YOU.
THANK YOU THANK YOU THANK YOU.THANK YOU THANK YOU THANK YOU.
THANK YOU THANK YOU THANK YOU.
 
Strategic Human Resource Management Lecture 10
Strategic Human Resource Management Lecture 10Strategic Human Resource Management Lecture 10
Strategic Human Resource Management Lecture 10
 

Similar to Deep learning: Modeling high-level face features through deep networks

imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdfKammetaJoshna
 
Seminar_Presentation_ppt
Seminar_Presentation_pptSeminar_Presentation_ppt
Seminar_Presentation_pptAyushDixit52
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
Image classification with neural networks
Image classification with neural networksImage classification with neural networks
Image classification with neural networksSepehr Rasouli
 
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary study
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary studyDoes Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary study
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary studyUniversidad de los Andes
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...Edge AI and Vision Alliance
 
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015Jia-Bin Huang
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
Finding the best solution for Image Processing
Finding the best solution for Image ProcessingFinding the best solution for Image Processing
Finding the best solution for Image ProcessingTech Triveni
 
Bangla Hand Written Digit Recognition presentation slide .pptx
Bangla Hand Written Digit Recognition presentation slide .pptxBangla Hand Written Digit Recognition presentation slide .pptx
Bangla Hand Written Digit Recognition presentation slide .pptxKhondokerAbuNaim
 
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020Universitat Politècnica de Catalunya
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용홍배 김
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network Yan Xu
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesNamkug Kim
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksWilly Marroquin (WillyDevNET)
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsChester Chen
 

Similar to Deep learning: Modeling high-level face features through deep networks (20)

Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
 
MIRU2014 SLAC
MIRU2014 SLACMIRU2014 SLAC
MIRU2014 SLAC
 
Fa19_P1.pptx
Fa19_P1.pptxFa19_P1.pptx
Fa19_P1.pptx
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
 
Seminar_Presentation_ppt
Seminar_Presentation_pptSeminar_Presentation_ppt
Seminar_Presentation_ppt
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
Image classification with neural networks
Image classification with neural networksImage classification with neural networks
Image classification with neural networks
 
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary study
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary studyDoes Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary study
Does Neuron Coverage Matter for Deep Reinforcement Learning? A preliminary study
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
 
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
Finding the best solution for Image Processing
Finding the best solution for Image ProcessingFinding the best solution for Image Processing
Finding the best solution for Image Processing
 
Bangla Hand Written Digit Recognition presentation slide .pptx
Bangla Hand Written Digit Recognition presentation slide .pptxBangla Hand Written Digit Recognition presentation slide .pptx
Bangla Hand Written Digit Recognition presentation slide .pptx
 
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN Applications
 

More from Nelson Forte

Recomendando produtos baseado em imagens
Recomendando produtos baseado em imagensRecomendando produtos baseado em imagens
Recomendando produtos baseado em imagensNelson Forte
 
Ecossistema Hadoop no Magazine Luiza
Ecossistema Hadoop no Magazine LuizaEcossistema Hadoop no Magazine Luiza
Ecossistema Hadoop no Magazine LuizaNelson Forte
 
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando R
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando RImitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando R
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando RNelson Forte
 
Conversas sobre Big Data, Hadoop e elefantes amarelos
Conversas sobre Big Data, Hadoop e elefantes amarelosConversas sobre Big Data, Hadoop e elefantes amarelos
Conversas sobre Big Data, Hadoop e elefantes amarelosNelson Forte
 
Estudo sobre ferramentas de BI Open Source
Estudo sobre ferramentas de BI Open SourceEstudo sobre ferramentas de BI Open Source
Estudo sobre ferramentas de BI Open SourceNelson Forte
 

More from Nelson Forte (6)

Recomendando produtos baseado em imagens
Recomendando produtos baseado em imagensRecomendando produtos baseado em imagens
Recomendando produtos baseado em imagens
 
Ecossistema Hadoop no Magazine Luiza
Ecossistema Hadoop no Magazine LuizaEcossistema Hadoop no Magazine Luiza
Ecossistema Hadoop no Magazine Luiza
 
Redes neurais
Redes neuraisRedes neurais
Redes neurais
 
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando R
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando RImitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando R
Imitando a Mãe Dináh: Adivinhando o futuro com modelos de regressão usando R
 
Conversas sobre Big Data, Hadoop e elefantes amarelos
Conversas sobre Big Data, Hadoop e elefantes amarelosConversas sobre Big Data, Hadoop e elefantes amarelos
Conversas sobre Big Data, Hadoop e elefantes amarelos
 
Estudo sobre ferramentas de BI Open Source
Estudo sobre ferramentas de BI Open SourceEstudo sobre ferramentas de BI Open Source
Estudo sobre ferramentas de BI Open Source
 

Recently uploaded

Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 

Recently uploaded (20)

Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 

Deep learning: Modeling high-level face features through deep networks

Editor's Notes

  1. Invariance theory: Objects are recognized by structural information or individual parts. Rotation and completion are made by invariant brain models.
  2. Especialização das células Células horizontais -> Reconhecer formas difusas Células bipolares -> Contraste e luz Células amácrinas -> Resolução (ajuste de foco) Células ganglionares -> Separação e caracteríticas
  3. m1.medium HDD - 120MB/s SSD - 600MB/s GPUs +100x rápidos que CPUs (para operações matemáticas)
  4. Representações automáticas = Aprendizado não-supervisionado de características Redes neurais menos direcionadas = Aprendem características gerais
  5. Convolução resulta em aproveitamento de pesos.