SlideShare a Scribd company logo
Alma Mater Studiorum - University of Bologna
School of Science
Department of Computer Science and Engineering DISI
Deep Learning for Computer Vision
Candidate
dott. Vincenzo Lomonaco
Supervisor
prof. Davide Maltoni
Co-examiner
prof. Mauro Gaspari
A comparison between Convolutional Neural
Networks and Hierarchical Temporal Memories on
object recognition tasks
08.09.15 Vincenzo Lomonaco 2
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
NORB-sequences
Original NORB dataset
New benchmark design
Experiments and Results
Experiments design
Results
Conclusions
Contents
08.09.15 Vincenzo Lomonaco 3
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
NORB-sequences
Original NORB dataset
New benchmark design
Experiments and Results
Experiments design
Results
Conclusions
Contents
08.09.15 Vincenzo Lomonaco 4
Deep Learning
In the last decade, Deep Learning techniques have shown to
perform incredibly well on a large variety of problems both in
Computer Vision and Natural Language Processing, resulting in
the state of the art in many tasks.
08.09.15 Vincenzo Lomonaco 5
Deep Learning advantages
Deep Learning is a branch of machine learning based on a set of
algorithms that attempt to model high-level abstractions in data by
using model architectures composed of multiple non-linear
transformations.
08.09.15 Vincenzo Lomonaco 6
Deep Learning disadvantages
● Poorly understood surrounding theory
● Non-optimal method
● Very difficult to train
● Huge quantity of data needed
● High Performance Computing environment needed
Possible limitations:
08.09.15 Vincenzo Lomonaco 7
Objectives
Proving that taking inspiration from biological learning
systems can help again in advancing the field of DL.
Proving that, with less data, it is however possible to reach
good levels of accuracy.
08.09.15 Vincenzo Lomonaco 8
How
We would like to show that, with a lower quantity of available
data, HTM can outperfom CNN on these tasks remaining
comparable in terms of training times.
Comparing two very different deep learning algorithms on
object recognition tasks:
– CNN: classical approach, state-of-the-art for object
recognition
– HTM: new biologically inspired approach
08.09.15 Vincenzo Lomonaco 9
NORB-sequences
Experiments and Results
Conclusions
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
Original NORB dataset
New benchmark design
Experiments design
Results
Contents
08.09.15 Vincenzo Lomonaco 10
CNN
CNNs are MLP variants where individual neurons are tiled in
such a way that they respond to overlapping regions in the
visual field. They are architectural inspired by Hubel and
Wiesel’s early work on the cat’s visual cortex.
● Python
● Using Theano
● 11 source files, 2550+ lns
● Pure supervised method
● Sparse Connectivity
● Shared Weights
Key features: Implementation:
08.09.15 Vincenzo Lomonaco 11
HTM
HTM is known as a new emerging paradigm that is more
biologically inspired. It tries to incorporate concepts like time,
context and attention during the learning process that are
typical of the human brain.
● C#, OPENMP version
● Provided by Biometric
System Lab (DISI)
● Mainly unsupervised method
● Top down and bottom-up
information flow
● Bayesian probabilistic
formulation
Key features: Implementations:
08.09.15 Vincenzo Lomonaco 12
Experiments and Results
Conclusions
Original NORB dataset
New benchmark design
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
Experiments design
Results
Contents
NORB-sequences
08.09.15 Vincenzo Lomonaco 13
NORB-Sequences
Since the computer vision community is starting to investigate
object recognition algorithms on videos, we would like to move
our comparison to that direction.
To this purpose, a new benchmark of a large collection of image
sequences starting from the well-know small NORB DATASET
has been created.
THE original NORB DATASET:
● Stores 48,600 96x96 image (5 categories, 10 instances, 6 lightings,
9 elevations, and 18 azimuths).
● Is well-know and accepted by the research community in the
context of object-recognition
08.09.15 Vincenzo Lomonaco 14
original NORB DATASET
Training instances Test instances
08.09.15 Vincenzo Lomonaco 15
Java sequencer
NORB-sequences is made possible thanks to a Java software
that takes in input the small NORB DATASET, and given a
number of different tuning parameters, return a number of
training and a test image sequences.
time
● The sequences are created ad hoc to simulate a camera moving
around a specific object including changes in the surround lighting.
● Integrated KNN baseline, GUI, 10 source files, 2600+ lns
Key features:
08.09.15 Vincenzo Lomonaco 16
NORB Sequences GUI
08.09.15 Vincenzo Lomonaco 17
NORB-sequences
Conclusions
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
Original NORB dataset
New benchmark design
Experiments design
Results
Contents
Experiments and Results
08.09.15 Vincenzo Lomonaco 18
Experiments design
1) Validate the CNN implementation on the NORB dataset
2) Evaluate the performance of both algorithms on the plain
NORB dataset
3) Evaluate the performance of both algorithms on the NORB
sequences
08.09.15 Vincenzo Lomonaco 19
CNN validation
In order to validate the new implementation,the goal was to
reproduce Y. LeCun original results on the plain NORB
DATASET.
08.09.15 Vincenzo Lomonaco 20
Plain NORB results
Accuracy results comparison between CNN and HTM on the
plain NORB dataset.
08.09.15 Vincenzo Lomonaco 21
Training times
Training times comparison between CNN and HTM on the
NORB sequences.
Training size CNN times HTM times
100 + 800jit 10.94 m 21.19 m
250 + 2000jit 31.15 m 23.13 m
500 + 4000jit 38.24 m 22.14 m
1000 + 4000jit 91.26 m 26.04 m
2500 + 4000jit 94.90 m 61.08 m
5000 + 4000jit 124.7 m 89.58 m
10000 + 4000jit 187.7 m 143.5 m
24300 + 4000jit 51.31 m 596.2 m
● CNN: GPU Tesla C2075 Fermi
(GPU speedup x3.2)
● HTM: CPU Xeon W3550, 4
cores.
Architectures:
08.09.15 Vincenzo Lomonaco 22
NORB sequences results
Accuracy results comparison between CNN and HTM on the
NORB sequences.
Train Test dist. CNN HTM
2x20 1 84.1% 86.36%
2x20 2 82.96% 86.16%
2x20 3 82.26% 86.16%
2x20 4 81.35% 84.20%
3x20 1 89.27% 91.0%
3x20 2 88.46% 89.52%
3x20 3 88.42% 88.68%
3x20 4 88.0% 85.88%
5x20 1 95.11% 92.69%
5x20 2 94.4% 91.62%
5x20 3 93.1% 92.86%
5x20 4 92.13% 91.23%
Train Test dist. CNN HTM
2x20 1 37.56% 37.08%
2x20 2 34.38% 37.82%
2x20 3 30.71% 33.17%
2x20 4 25.47% 28.89%
3x20 1 49.89% 43.68%
3x20 2 48.01% 44.08%
3x20 3 40.56% 37.93%
3x20 4 33.77% 34.93%
5x20 1 55.17% 52.57%
5x20 2 52.55% 49.74%
5x20 3 45.86% 45.52%
5x20 4 40.08% 41.30%
5-classes 50-classes
08.09.15 Vincenzo Lomonaco 23
NORB-sequences
Experiments and Results
Conclusions
ContentsBackground & Motivations
Objectives
Introduction
CNN and HTM
Key features
Implementations
Original NORB dataset
New benchmark design
Experiments design
Results
Contents
08.09.15 Vincenzo Lomonaco 24
Conclusions
In this dissertation three different milestones have been
achieved:
1) A LeNet-7 with Theano has been successfully implemented.
2) A new benchmark for object recognition in image
sequences has been created.
3) HTM and CNN have been compared on different object
recognition tasks.
It has been proven that the HTM bio-inspired approach can
be highly competitive and could be instrumental for
advancing the field of Deep Learning
08.09.15 Vincenzo Lomonaco 25
The End
http://vincenzolomonaco.com
vincenzo.lomonaco@studio.unibo.it
“If we want machines to think, we need to teach them to see”
Fei-Fei Li, Stanford Computer Vision Lab
Thank you for your attention
Vincenzo Lomonaco

More Related Content

What's hot

TensorFlow Tutorial Part2
TensorFlow Tutorial Part2TensorFlow Tutorial Part2
TensorFlow Tutorial Part2
Sungjoon Choi
 
TensorFlow Tutorial Part1
TensorFlow Tutorial Part1TensorFlow Tutorial Part1
TensorFlow Tutorial Part1
Sungjoon Choi
 
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
datasciencekorea
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
Hannes Hapke
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
David Dao
 
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
GeeksLab Odessa
 
Transformer in Vision
Transformer in VisionTransformer in Vision
Transformer in Vision
Sangmin Woo
 
Convolutional neural networks deepa
Convolutional neural networks deepaConvolutional neural networks deepa
Convolutional neural networks deepa
deepa4466
 
Neuroevolution and deep learing
Neuroevolution and deep learing Neuroevolution and deep learing
Neuroevolution and deep learing
Accenture
 
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
PyData
 
AlexNet
AlexNetAlexNet
AlexNet
Bertil Hatt
 
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
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
Sungjoon Choi
 
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic SegmentationReview : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
Dongmin Choi
 
Deep Learning Tutorial
Deep Learning Tutorial Deep Learning Tutorial
Deep Learning Tutorial
Ligeng Zhu
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Turi, Inc.
 
150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks
Junho Cho
 
160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation
Junho Cho
 
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
Universitat Politècnica de Catalunya
 
Efficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image ClassficationEfficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image Classfication
Yogendra Tamang
 

What's hot (20)

TensorFlow Tutorial Part2
TensorFlow Tutorial Part2TensorFlow Tutorial Part2
TensorFlow Tutorial Part2
 
TensorFlow Tutorial Part1
TensorFlow Tutorial Part1TensorFlow Tutorial Part1
TensorFlow Tutorial Part1
 
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
AI&BigData Lab 2016. Александр Баев: Transfer learning - зачем, как и где.
 
Transformer in Vision
Transformer in VisionTransformer in Vision
Transformer in Vision
 
Convolutional neural networks deepa
Convolutional neural networks deepaConvolutional neural networks deepa
Convolutional neural networks deepa
 
Neuroevolution and deep learing
Neuroevolution and deep learing Neuroevolution and deep learing
Neuroevolution and deep learing
 
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
 
AlexNet
AlexNetAlexNet
AlexNet
 
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 ...
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic SegmentationReview : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
 
Deep Learning Tutorial
Deep Learning Tutorial Deep Learning Tutorial
Deep Learning Tutorial
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
 
150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks
 
160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation
 
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
Transfer Learning (D2L4 Insight@DCU Machine Learning Workshop 2017)
 
Efficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image ClassficationEfficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image Classfication
 

Viewers also liked

¿Qué es Slide Share?
¿Qué es Slide Share? ¿Qué es Slide Share?
¿Qué es Slide Share?
Family
 
Magazine Genre Research
Magazine Genre ResearchMagazine Genre Research
Magazine Genre Research
daltonsenger
 
Tab
TabTab
Sarcina nr 2 roma
Sarcina nr 2 romaSarcina nr 2 roma
Sarcina nr 2 roma
florinaarsenie
 
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_ENKakim Goh
 
A Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in JavaA Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in Java
Vincenzo Lomonaco
 
Kato Mivule: An Overview of Adaptive Boosting – AdaBoost
Kato Mivule: An Overview of  Adaptive Boosting – AdaBoostKato Mivule: An Overview of  Adaptive Boosting – AdaBoost
Kato Mivule: An Overview of Adaptive Boosting – AdaBoost
Kato Mivule
 
CVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
CVPR2016読み会 Sparsifying Neural Network Connections for Face RecognitionCVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
CVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
Koichi Takahashi
 
Machine learning with ADA Boost
Machine learning with ADA BoostMachine learning with ADA Boost
Machine learning with ADA Boost
Aman Patel
 
Captcha as graphical passwords a new security primitive based on hard ai prob...
Captcha as graphical passwords a new security primitive based on hard ai prob...Captcha as graphical passwords a new security primitive based on hard ai prob...
Captcha as graphical passwords a new security primitive based on hard ai prob...
IGEEKS TECHNOLOGIES
 
Face recognization using artificial nerual network
Face recognization using artificial nerual networkFace recognization using artificial nerual network
Face recognization using artificial nerual network
Dharmesh Tank
 
Face recognition technology
Face recognition technologyFace recognition technology
Face recognition technology
SARATHGOVINDKK
 
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Universitat Politècnica de Catalunya
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORK
codebangla
 
Captcha as graphical password
Captcha as graphical passwordCaptcha as graphical password
Captcha as graphical password
Gopinath Ramanna
 

Viewers also liked (20)

¿Qué es Slide Share?
¿Qué es Slide Share? ¿Qué es Slide Share?
¿Qué es Slide Share?
 
Magazine Genre Research
Magazine Genre ResearchMagazine Genre Research
Magazine Genre Research
 
Curriculum Vita1
Curriculum Vita1Curriculum Vita1
Curriculum Vita1
 
Tab
TabTab
Tab
 
Sarcina nr 2 roma
Sarcina nr 2 romaSarcina nr 2 roma
Sarcina nr 2 roma
 
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN
2016-03-31 FAA Visual Arts at MDC Frontenac_May 2016_Press Kit_EN
 
A Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in JavaA Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in Java
 
SCHEMATIC REPORT
SCHEMATIC REPORTSCHEMATIC REPORT
SCHEMATIC REPORT
 
Kato Mivule: An Overview of Adaptive Boosting – AdaBoost
Kato Mivule: An Overview of  Adaptive Boosting – AdaBoostKato Mivule: An Overview of  Adaptive Boosting – AdaBoost
Kato Mivule: An Overview of Adaptive Boosting – AdaBoost
 
Gsm architecture
Gsm architectureGsm architecture
Gsm architecture
 
CVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
CVPR2016読み会 Sparsifying Neural Network Connections for Face RecognitionCVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
CVPR2016読み会 Sparsifying Neural Network Connections for Face Recognition
 
Machine learning with ADA Boost
Machine learning with ADA BoostMachine learning with ADA Boost
Machine learning with ADA Boost
 
Captcha as graphical passwords a new security primitive based on hard ai prob...
Captcha as graphical passwords a new security primitive based on hard ai prob...Captcha as graphical passwords a new security primitive based on hard ai prob...
Captcha as graphical passwords a new security primitive based on hard ai prob...
 
Face recognization using artificial nerual network
Face recognization using artificial nerual networkFace recognization using artificial nerual network
Face recognization using artificial nerual network
 
Face recognition technology
Face recognition technologyFace recognition technology
Face recognition technology
 
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural network
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORK
 
Captcha as graphical password
Captcha as graphical passwordCaptcha as graphical password
Captcha as graphical password
 
ARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCEARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCE
 

Similar to Deep Learning for Computer Vision: A comparision between Convolutional Neural Networks and Hierarchical Temporal Memories on object recognition tasks - Slides

Machine Learning approaches at video compression
Machine Learning approaches at video compression Machine Learning approaches at video compression
Machine Learning approaches at video compression
Roberto Iacoviello
 
Bic bellec 2016_small
Bic bellec 2016_smallBic bellec 2016_small
Bic bellec 2016_small
Pierre Bellec
 
Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks
Mah Sa
 
Anomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NETAnomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NET
Marco Parenzan
 
Neural_Programmer_Interpreter
Neural_Programmer_InterpreterNeural_Programmer_Interpreter
Neural_Programmer_InterpreterKaty Lee
 
Interactive Data Analysis for End Users on HN Science Cloud
Interactive Data Analysis for End Users on HN Science CloudInteractive Data Analysis for End Users on HN Science Cloud
Interactive Data Analysis for End Users on HN Science Cloud
Helix Nebula The Science Cloud
 
convolutional_neural_networks.pptx
convolutional_neural_networks.pptxconvolutional_neural_networks.pptx
convolutional_neural_networks.pptx
MsKiranSingh
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .net
Marco Parenzan
 
161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs
Junho Cho
 
Deep Learning Jeff-Shomaker_1-20-17_Final_
Deep Learning Jeff-Shomaker_1-20-17_Final_Deep Learning Jeff-Shomaker_1-20-17_Final_
Deep Learning Jeff-Shomaker_1-20-17_Final_
Jeffrey Shomaker
 
Object Detection with Tensorflow
Object Detection with TensorflowObject Detection with Tensorflow
Object Detection with Tensorflow
ElifTech
 
01-06 OCRE Test Suite - Fernandes.pdf
01-06 OCRE Test Suite - Fernandes.pdf01-06 OCRE Test Suite - Fernandes.pdf
01-06 OCRE Test Suite - Fernandes.pdf
OCRE | Open Clouds for Research Environments
 
Survey of recent deep learning with low precision
Survey of recent deep learning with low precisionSurvey of recent deep learning with low precision
Survey of recent deep learning with low precision
Mila, Université de Montréal
 
Opencv
OpencvOpencv
Opencv
Ethishkumar
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
pratik pratyay
 
Deep Learning for Fast Simulation
Deep Learning for Fast SimulationDeep Learning for Fast Simulation
Deep Learning for Fast Simulation
Helix Nebula The Science Cloud
 
Continual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsContinual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary Environments
Vincenzo Lomonaco
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
SharanrajK22MMT1003
 
TinyML as-a-Service
TinyML as-a-ServiceTinyML as-a-Service
TinyML as-a-Service
Hiroshi Doyu
 
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
CSCJournals
 

Similar to Deep Learning for Computer Vision: A comparision between Convolutional Neural Networks and Hierarchical Temporal Memories on object recognition tasks - Slides (20)

Machine Learning approaches at video compression
Machine Learning approaches at video compression Machine Learning approaches at video compression
Machine Learning approaches at video compression
 
Bic bellec 2016_small
Bic bellec 2016_smallBic bellec 2016_small
Bic bellec 2016_small
 
Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks
 
Anomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NETAnomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NET
 
Neural_Programmer_Interpreter
Neural_Programmer_InterpreterNeural_Programmer_Interpreter
Neural_Programmer_Interpreter
 
Interactive Data Analysis for End Users on HN Science Cloud
Interactive Data Analysis for End Users on HN Science CloudInteractive Data Analysis for End Users on HN Science Cloud
Interactive Data Analysis for End Users on HN Science Cloud
 
convolutional_neural_networks.pptx
convolutional_neural_networks.pptxconvolutional_neural_networks.pptx
convolutional_neural_networks.pptx
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .net
 
161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs
 
Deep Learning Jeff-Shomaker_1-20-17_Final_
Deep Learning Jeff-Shomaker_1-20-17_Final_Deep Learning Jeff-Shomaker_1-20-17_Final_
Deep Learning Jeff-Shomaker_1-20-17_Final_
 
Object Detection with Tensorflow
Object Detection with TensorflowObject Detection with Tensorflow
Object Detection with Tensorflow
 
01-06 OCRE Test Suite - Fernandes.pdf
01-06 OCRE Test Suite - Fernandes.pdf01-06 OCRE Test Suite - Fernandes.pdf
01-06 OCRE Test Suite - Fernandes.pdf
 
Survey of recent deep learning with low precision
Survey of recent deep learning with low precisionSurvey of recent deep learning with low precision
Survey of recent deep learning with low precision
 
Opencv
OpencvOpencv
Opencv
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
 
Deep Learning for Fast Simulation
Deep Learning for Fast SimulationDeep Learning for Fast Simulation
Deep Learning for Fast Simulation
 
Continual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsContinual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary Environments
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
 
TinyML as-a-Service
TinyML as-a-ServiceTinyML as-a-Service
TinyML as-a-Service
 
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
 

More from Vincenzo Lomonaco

2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
Vincenzo Lomonaco
 
Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021
Vincenzo Lomonaco
 
Toward Continual Learning on the Edge
Toward Continual Learning on the EdgeToward Continual Learning on the Edge
Toward Continual Learning on the Edge
Vincenzo Lomonaco
 
Continual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent MachinesContinual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent Machines
Vincenzo Lomonaco
 
Tutorial inns2019 full
Tutorial inns2019 fullTutorial inns2019 full
Tutorial inns2019 full
Vincenzo Lomonaco
 
Continual/Lifelong Learning with Deep Architectures
Continual/Lifelong Learning with Deep ArchitecturesContinual/Lifelong Learning with Deep Architectures
Continual/Lifelong Learning with Deep Architectures
Vincenzo Lomonaco
 
Continual Learning for Robotics
Continual Learning for RoboticsContinual Learning for Robotics
Continual Learning for Robotics
Vincenzo Lomonaco
 
Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...
Vincenzo Lomonaco
 
Open-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an OverviewOpen-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an Overview
Vincenzo Lomonaco
 
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Vincenzo Lomonaco
 
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
Vincenzo Lomonaco
 
Continuous Learning with Deep Architectures
Continuous Learning with Deep ArchitecturesContinuous Learning with Deep Architectures
Continuous Learning with Deep Architectures
Vincenzo Lomonaco
 
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterCORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
Vincenzo Lomonaco
 
Continuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep ArchitecturesContinuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep Architectures
Vincenzo Lomonaco
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Vincenzo Lomonaco
 
Deep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with TheanoDeep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with Theano
Vincenzo Lomonaco
 
Word2vec on the italian language: first experiments
Word2vec on the italian language: first experimentsWord2vec on the italian language: first experiments
Word2vec on the italian language: first experiments
Vincenzo Lomonaco
 
Machine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An OverviewMachine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An Overview
Vincenzo Lomonaco
 

More from Vincenzo Lomonaco (18)

2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
 
Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021
 
Toward Continual Learning on the Edge
Toward Continual Learning on the EdgeToward Continual Learning on the Edge
Toward Continual Learning on the Edge
 
Continual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent MachinesContinual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent Machines
 
Tutorial inns2019 full
Tutorial inns2019 fullTutorial inns2019 full
Tutorial inns2019 full
 
Continual/Lifelong Learning with Deep Architectures
Continual/Lifelong Learning with Deep ArchitecturesContinual/Lifelong Learning with Deep Architectures
Continual/Lifelong Learning with Deep Architectures
 
Continual Learning for Robotics
Continual Learning for RoboticsContinual Learning for Robotics
Continual Learning for Robotics
 
Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...
 
Open-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an OverviewOpen-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an Overview
 
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
 
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
 
Continuous Learning with Deep Architectures
Continuous Learning with Deep ArchitecturesContinuous Learning with Deep Architectures
Continuous Learning with Deep Architectures
 
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterCORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
 
Continuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep ArchitecturesContinuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep Architectures
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
 
Deep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with TheanoDeep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with Theano
 
Word2vec on the italian language: first experiments
Word2vec on the italian language: first experimentsWord2vec on the italian language: first experiments
Word2vec on the italian language: first experiments
 
Machine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An OverviewMachine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An Overview
 

Recently uploaded

(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
Scintica Instrumentation
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
muralinath2
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
Columbia Weather Systems
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
AlaminAfendy1
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
AADYARAJPANDEY1
 
SCHIZOPHRENIA Disorder/ Brain Disorder.pdf
SCHIZOPHRENIA Disorder/ Brain Disorder.pdfSCHIZOPHRENIA Disorder/ Brain Disorder.pdf
SCHIZOPHRENIA Disorder/ Brain Disorder.pdf
SELF-EXPLANATORY
 
Structural Classification Of Protein (SCOP)
Structural Classification Of Protein  (SCOP)Structural Classification Of Protein  (SCOP)
Structural Classification Of Protein (SCOP)
aishnasrivastava
 
extra-chromosomal-inheritance[1].pptx.pdfpdf
extra-chromosomal-inheritance[1].pptx.pdfpdfextra-chromosomal-inheritance[1].pptx.pdfpdf
extra-chromosomal-inheritance[1].pptx.pdfpdf
DiyaBiswas10
 
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of LipidsGBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
Areesha Ahmad
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Sérgio Sacani
 
Penicillin...........................pptx
Penicillin...........................pptxPenicillin...........................pptx
Penicillin...........................pptx
Cherry
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
muralinath2
 
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
Health Advances
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
muralinath2
 
Hemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptxHemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptx
muralinath2
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
Sérgio Sacani
 
Lab report on liquid viscosity of glycerin
Lab report on liquid viscosity of glycerinLab report on liquid viscosity of glycerin
Lab report on liquid viscosity of glycerin
ossaicprecious19
 
ESR_factors_affect-clinic significance-Pathysiology.pptx
ESR_factors_affect-clinic significance-Pathysiology.pptxESR_factors_affect-clinic significance-Pathysiology.pptx
ESR_factors_affect-clinic significance-Pathysiology.pptx
muralinath2
 
Lateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensiveLateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensive
silvermistyshot
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
Areesha Ahmad
 

Recently uploaded (20)

(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
(May 29th, 2024) Advancements in Intravital Microscopy- Insights for Preclini...
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
 
SCHIZOPHRENIA Disorder/ Brain Disorder.pdf
SCHIZOPHRENIA Disorder/ Brain Disorder.pdfSCHIZOPHRENIA Disorder/ Brain Disorder.pdf
SCHIZOPHRENIA Disorder/ Brain Disorder.pdf
 
Structural Classification Of Protein (SCOP)
Structural Classification Of Protein  (SCOP)Structural Classification Of Protein  (SCOP)
Structural Classification Of Protein (SCOP)
 
extra-chromosomal-inheritance[1].pptx.pdfpdf
extra-chromosomal-inheritance[1].pptx.pdfpdfextra-chromosomal-inheritance[1].pptx.pdfpdf
extra-chromosomal-inheritance[1].pptx.pdfpdf
 
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of LipidsGBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
 
Penicillin...........................pptx
Penicillin...........................pptxPenicillin...........................pptx
Penicillin...........................pptx
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
 
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
 
Hemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptxHemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptx
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
 
Lab report on liquid viscosity of glycerin
Lab report on liquid viscosity of glycerinLab report on liquid viscosity of glycerin
Lab report on liquid viscosity of glycerin
 
ESR_factors_affect-clinic significance-Pathysiology.pptx
ESR_factors_affect-clinic significance-Pathysiology.pptxESR_factors_affect-clinic significance-Pathysiology.pptx
ESR_factors_affect-clinic significance-Pathysiology.pptx
 
Lateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensiveLateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensive
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
 

Deep Learning for Computer Vision: A comparision between Convolutional Neural Networks and Hierarchical Temporal Memories on object recognition tasks - Slides

  • 1. Alma Mater Studiorum - University of Bologna School of Science Department of Computer Science and Engineering DISI Deep Learning for Computer Vision Candidate dott. Vincenzo Lomonaco Supervisor prof. Davide Maltoni Co-examiner prof. Mauro Gaspari A comparison between Convolutional Neural Networks and Hierarchical Temporal Memories on object recognition tasks
  • 2. 08.09.15 Vincenzo Lomonaco 2 ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations NORB-sequences Original NORB dataset New benchmark design Experiments and Results Experiments design Results Conclusions Contents
  • 3. 08.09.15 Vincenzo Lomonaco 3 ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations NORB-sequences Original NORB dataset New benchmark design Experiments and Results Experiments design Results Conclusions Contents
  • 4. 08.09.15 Vincenzo Lomonaco 4 Deep Learning In the last decade, Deep Learning techniques have shown to perform incredibly well on a large variety of problems both in Computer Vision and Natural Language Processing, resulting in the state of the art in many tasks.
  • 5. 08.09.15 Vincenzo Lomonaco 5 Deep Learning advantages Deep Learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures composed of multiple non-linear transformations.
  • 6. 08.09.15 Vincenzo Lomonaco 6 Deep Learning disadvantages ● Poorly understood surrounding theory ● Non-optimal method ● Very difficult to train ● Huge quantity of data needed ● High Performance Computing environment needed Possible limitations:
  • 7. 08.09.15 Vincenzo Lomonaco 7 Objectives Proving that taking inspiration from biological learning systems can help again in advancing the field of DL. Proving that, with less data, it is however possible to reach good levels of accuracy.
  • 8. 08.09.15 Vincenzo Lomonaco 8 How We would like to show that, with a lower quantity of available data, HTM can outperfom CNN on these tasks remaining comparable in terms of training times. Comparing two very different deep learning algorithms on object recognition tasks: – CNN: classical approach, state-of-the-art for object recognition – HTM: new biologically inspired approach
  • 9. 08.09.15 Vincenzo Lomonaco 9 NORB-sequences Experiments and Results Conclusions ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations Original NORB dataset New benchmark design Experiments design Results Contents
  • 10. 08.09.15 Vincenzo Lomonaco 10 CNN CNNs are MLP variants where individual neurons are tiled in such a way that they respond to overlapping regions in the visual field. They are architectural inspired by Hubel and Wiesel’s early work on the cat’s visual cortex. ● Python ● Using Theano ● 11 source files, 2550+ lns ● Pure supervised method ● Sparse Connectivity ● Shared Weights Key features: Implementation:
  • 11. 08.09.15 Vincenzo Lomonaco 11 HTM HTM is known as a new emerging paradigm that is more biologically inspired. It tries to incorporate concepts like time, context and attention during the learning process that are typical of the human brain. ● C#, OPENMP version ● Provided by Biometric System Lab (DISI) ● Mainly unsupervised method ● Top down and bottom-up information flow ● Bayesian probabilistic formulation Key features: Implementations:
  • 12. 08.09.15 Vincenzo Lomonaco 12 Experiments and Results Conclusions Original NORB dataset New benchmark design ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations Experiments design Results Contents NORB-sequences
  • 13. 08.09.15 Vincenzo Lomonaco 13 NORB-Sequences Since the computer vision community is starting to investigate object recognition algorithms on videos, we would like to move our comparison to that direction. To this purpose, a new benchmark of a large collection of image sequences starting from the well-know small NORB DATASET has been created. THE original NORB DATASET: ● Stores 48,600 96x96 image (5 categories, 10 instances, 6 lightings, 9 elevations, and 18 azimuths). ● Is well-know and accepted by the research community in the context of object-recognition
  • 14. 08.09.15 Vincenzo Lomonaco 14 original NORB DATASET Training instances Test instances
  • 15. 08.09.15 Vincenzo Lomonaco 15 Java sequencer NORB-sequences is made possible thanks to a Java software that takes in input the small NORB DATASET, and given a number of different tuning parameters, return a number of training and a test image sequences. time ● The sequences are created ad hoc to simulate a camera moving around a specific object including changes in the surround lighting. ● Integrated KNN baseline, GUI, 10 source files, 2600+ lns Key features:
  • 16. 08.09.15 Vincenzo Lomonaco 16 NORB Sequences GUI
  • 17. 08.09.15 Vincenzo Lomonaco 17 NORB-sequences Conclusions ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations Original NORB dataset New benchmark design Experiments design Results Contents Experiments and Results
  • 18. 08.09.15 Vincenzo Lomonaco 18 Experiments design 1) Validate the CNN implementation on the NORB dataset 2) Evaluate the performance of both algorithms on the plain NORB dataset 3) Evaluate the performance of both algorithms on the NORB sequences
  • 19. 08.09.15 Vincenzo Lomonaco 19 CNN validation In order to validate the new implementation,the goal was to reproduce Y. LeCun original results on the plain NORB DATASET.
  • 20. 08.09.15 Vincenzo Lomonaco 20 Plain NORB results Accuracy results comparison between CNN and HTM on the plain NORB dataset.
  • 21. 08.09.15 Vincenzo Lomonaco 21 Training times Training times comparison between CNN and HTM on the NORB sequences. Training size CNN times HTM times 100 + 800jit 10.94 m 21.19 m 250 + 2000jit 31.15 m 23.13 m 500 + 4000jit 38.24 m 22.14 m 1000 + 4000jit 91.26 m 26.04 m 2500 + 4000jit 94.90 m 61.08 m 5000 + 4000jit 124.7 m 89.58 m 10000 + 4000jit 187.7 m 143.5 m 24300 + 4000jit 51.31 m 596.2 m ● CNN: GPU Tesla C2075 Fermi (GPU speedup x3.2) ● HTM: CPU Xeon W3550, 4 cores. Architectures:
  • 22. 08.09.15 Vincenzo Lomonaco 22 NORB sequences results Accuracy results comparison between CNN and HTM on the NORB sequences. Train Test dist. CNN HTM 2x20 1 84.1% 86.36% 2x20 2 82.96% 86.16% 2x20 3 82.26% 86.16% 2x20 4 81.35% 84.20% 3x20 1 89.27% 91.0% 3x20 2 88.46% 89.52% 3x20 3 88.42% 88.68% 3x20 4 88.0% 85.88% 5x20 1 95.11% 92.69% 5x20 2 94.4% 91.62% 5x20 3 93.1% 92.86% 5x20 4 92.13% 91.23% Train Test dist. CNN HTM 2x20 1 37.56% 37.08% 2x20 2 34.38% 37.82% 2x20 3 30.71% 33.17% 2x20 4 25.47% 28.89% 3x20 1 49.89% 43.68% 3x20 2 48.01% 44.08% 3x20 3 40.56% 37.93% 3x20 4 33.77% 34.93% 5x20 1 55.17% 52.57% 5x20 2 52.55% 49.74% 5x20 3 45.86% 45.52% 5x20 4 40.08% 41.30% 5-classes 50-classes
  • 23. 08.09.15 Vincenzo Lomonaco 23 NORB-sequences Experiments and Results Conclusions ContentsBackground & Motivations Objectives Introduction CNN and HTM Key features Implementations Original NORB dataset New benchmark design Experiments design Results Contents
  • 24. 08.09.15 Vincenzo Lomonaco 24 Conclusions In this dissertation three different milestones have been achieved: 1) A LeNet-7 with Theano has been successfully implemented. 2) A new benchmark for object recognition in image sequences has been created. 3) HTM and CNN have been compared on different object recognition tasks. It has been proven that the HTM bio-inspired approach can be highly competitive and could be instrumental for advancing the field of Deep Learning
  • 25. 08.09.15 Vincenzo Lomonaco 25 The End http://vincenzolomonaco.com vincenzo.lomonaco@studio.unibo.it “If we want machines to think, we need to teach them to see” Fei-Fei Li, Stanford Computer Vision Lab Thank you for your attention Vincenzo Lomonaco