deep learning

Hassanein Alwan
Hassanein AlwanPlanning Advisor

Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans

1
Deep Learning
Prepared by
Hassanein Alwan Malik
University Of Technology
Computer Science
Master of Science
2
Introduction
Deeplearning is a machine learning technique that teaches computers
to do what comes naturally to humans: learn by example. Deeplearning
is a key technologybehind driverless cars, enabling them to recognize a
stop sign, or to distinguish a pedestrian from a lamppost. It is the key to
voice control in consumer devices like phones, tablets, TVs, and hands-
free speakers. Deeplearning is getting lots of attention lately and for
goodreason. It’s achieving results that were not possible before
we will overview the neuralnetworks and take a generalview of some of
their types as examples to understand thebasics of neural networks and
then move to a general description of deep education
1.Artificial Neural networks(ANN)
systems that processing information, inspired by biological neural systems.
Neural networks consist of many simple processing elements called
Neurons, nodes, units or cells.
Artificial neural networks have been developed as generalizations of
mathematical models of human cognition or neural biology, based on the
assumptions that:-
1. Information processingoccurs at many simple elements called
neurons.
2. Signals are passed between neurons over connection links.
3. Each connection link has an associated weight which, in a typical
neural net, multiplies the signal transmitted.
3
1.1 Type of architecture
The NN consists of input units, output units, and one hidden unit. Neural
nets are often classified as single layer or multilayer by depending on the
number of layers (hidden unit) and the number of layers in the NN can be
defined to be the numbers of layers of weighted interconnect links between
the neurons.
Single layer
NN has one layer of connection weights.
4
Multilayer NN
A Multilayer net is a net with one or more layers (or levels) of nodes which
is called hidden units, between the input units and the output units.
2 What Is Learning and What Is Generalization in ANNs?
We use the properties of ANN to made a model that can be solve a problems
through learning the model by given it a training data and adjusting the
weights until the output achieved our goal.
Rather than use a single program to solve every single problem we can
generalization our model to solve several problems.
5
There is three type of learning :
a- Supervised learning : The training data comprise input vectors x and the
desired output vectors y. Training is performed until the neural
network "learns" to associate each input vector x to its corresponding
and desired output vector y.
b- Unsupervised: Only input vectors x are supplied; the neural network
learns some internal features of the whole set of all the input vectors
presented to it.
6
c- Self- Organization
sometimes called reward-penalty learning (reinforcement), is a combination
of the above two paradigms; it is based on presenting input vector x to a
neural network and looking at the output vector calculated by the network. If
it is considered "good," then a "reward" is given to the network in the sense
that the existing connection weights are increased; otherwise the network is
"punished", the connection weights, being considered as "not appropriately
set," decrease.
Learning type
 Hebbian Learning Rule
It’s a learning rule that suggested by Hebb in 1949, and it can represented by
the rule: If two neurons on either side of connection are activated
synchronously, then the weight of that connection is increased.
Note: Hebb's rule provide the basis for unsupervised learning.
Features of Hebb rule
1. Unsupervised
2. Fully conncted.
3. Single Layer (with lack of a hidden layer within the network).
The common uses of Hebb is in Character Recognition
By training the net to distinguish between the pattern "X" and the pattern
"0".
7
8
3 Deep learning neural network
How deep learning works?
We will take an Image recognition model as an example to illustration how
is deep learning working
 First stage : learning the model :-
so we feeding the model with a large amount of images (e.g many
various images cats, dogs, wolf, tigers, ….etc.)as a training data and
learning the model to recognize an unlabeled image , the first layer
usually consistof many activation functions that have specific job
which is detection the edges of images, so it will take the input images
and begin learning itself through obtained the features edges images
and gives these features to the second layer. The second layer
activation functions have another job that is detection the objects parts
(nose, mouth, eyes), so it will obtained the features and learning itself.
The third layer activation functions will detecting the object features
and learning itself through the obtained features.
 Second stage : test the model
So, when we input an unlabeled image to the model, for example a
dog image, the first layer will matching the edge of cat image with all
images, and feeds the second layer with only the edges that have
similar features (e.g the cat , wolf, dog and raccoonhave similar edge,
but elephant is different). The second layer will receive the obtained
features with the input image from the first layer and will matching
the object parts of input image with only images that already
determined from the first layer by it features ( it will matching the
nose, mouth, eye, …etc with the images of cat , wolf, dog, and
raccoonand will ignoring the other images) and feeds the third layer
with only the object parts that have similar features (e.g the raccoon
and cat will excluded).
The third layer will receive the obtained features with the input image
from the second layer and will matching the object of the input image
with the images that selected from the previous layer (e.g the wolf,
image with dog image), and the result will be the dog image.
9
Notes:
a. Every layer have an independent function but all layers associated in
hierarchically.
b. In every move from lower layer to the next, the options is decreased
until achieved the goal.
c. The higher layer more complex than the lower layer.
10
E.g. Classify a cat:
 Bottom Layers: Edge detectors, curves, corners straight lines
 Middle Layers: Fur patterns, eyes, ears
 Higher Layers: Body, head, legs
 Top Layer: Cat or Dog
11
4 Deep Leaning Algorithms
Also known as deep structured learning, hierarchical learning or deep
machine learning) is a class of machine learning algorithms that use a cascade
of many layers of nonlinear processing units for feature extraction and
transformation. Each successive layer uses the output from the previous layer
as input. The algorithms may be supervised or unsupervised and applications
include pattern analysis (unsupervised) and classification (supervised).
convolutional neural networks (CNN)
A typical CNN is composed of many layers of hierarchy with some layers
for feature representations (or feature maps) and others as a type of
conventional neural networks for classification. It often starts with two
altering types of layers called convolutional and subsampling layers:
convolutional layers perform convolution operations with several filter maps
of equal size, while subsampling layers reduce the sizes of proceeding layers
by averaging pixels within a small neighborhood (or by max-pooling.
Facebook uses neural nets for their automatic tagging algorithms, Google for
their photo search, Amazon for their product recommendations, and Instagram
for their search infrastructure. Simple ConvNet is a sequence of layers:
Convolutional Layer, Pooling Layer, and Fully-Connected Layer.
12
Figure shows a typical architecture of CNNs. The input is first convoluted
with a set of filters (C layers in Fig). These 2D filtered data are called feature
maps. After a nonlinear transformation, a subsampling is further performed to
reduce the dimensionality (S layers in Figure 2). The sequence of
convolution/subsampling can be repeated many times (predetermined by
users).
1-Convolutional Layer: Also referred to as Conv. layer, it forms the basis of
the CNN and performs the core operations of training and consequently firing
the neurons of the network. It performs the convolution operation over the input
volume and consists of a 3-dimensional arrangement of neurons (a stack of 2-
dimensional layers of neurons, one for each channel depth). That make :
Filters (Convolution Kernels) :A filter (or kernel) is an integral component of
the layered architecture. it refers to an operator applied to the entirety of the
image such that it transforms the information encoded in the pixels
Figure (2) CNN
13
Spatial arrangement. We have explained the connectivity of each neuron in
the Conv Layer to the input volume, but we haven’t yet discussed how many
neurons there are in the output volume or how they are arranged. Three
hyper parameters control the size of the output volume: the depth,
stride and zero-padding. We discuss these next:
1. First, the depth of the output volume is a hyper parameter: it corresponds
to the number of filters we would like to use, each learning to look for
something different in the input. Forexample, if the first Convolutional
Layer takes as input the raw image, then different neurons along the depth
dimension may activate in presence of various oriented edges, or blobs of
color. We will refer to a set of neurons that are all looking at the same
region of the input as a depth column (some people also prefer the
term fibre).
2. Second, we must specify the stride with which we slide the filter. When
the stride is 1 then we move the filters one pixel at a time. When the
stride is 2 (or uncommonly 3 or more, though this is rare in practice) then
the filters jump 2 pixels at a time as we slide them around. This will
producesmaller output volumes spatially.
3. As we will soonsee, sometimes it will be convenient to pad the input
volume with zeros around the border. The size of this zero-padding is a
hyper parameter. The nice feature of zero padding is that it will allow us
to control the spatial size of the output volumes (most commonly as we’ll
see soonwe will use it to exactly preserve the spatial size of the input
volume so the input and output width and height are the same).
We can compute the spatial size of the output volume as a function of the
input volume size (W), the receptive field size of the Conv Layer neurons
(F), the stride with which they are applied (S), and the amount of zero
padding used (P) on the border. You can convince yourself that the correct
formula for calculating how many neurons “fit” is given
by (W−F+2P)/S+1(W−F+2P)/S+1.
14
Illustration of spatial arrangement. In this example there is only one spatial
dimension (x-axis), one neuron with a receptive field size of F = 3, the input
size is W = 5, and there is zero padding of P = 1.
Left: The neuron strided across the input in stride of S = 1, giving output of
size (5 - 3 + 2)/1+1 = 5.
Right: The neuron uses stride of S = 2, giving output of size
(5 - 3 + 2)/2+1 = 3. Notice that stride S = 3 could not be used since it
wouldn't fit neatly across the volume. In terms of the equation, this can be
determined since (5 - 3 + 2) = 4 is not divisible by 3.
The neuron weights are in this example (shown on very right), and its bias is
zero. These weights are shared across all yellow neurons (see parameter
sharing below
2-Pooling layer (subsampling layer): it is between successive Conv layers in
ConvNet architecture. Its function is to progressively reduce the spatial size of
the representation to reduce the amount of parameters and computation in the
network, and hence to also control over fitting. The Pooling Layer operates
independently on every depth slice of the input and resizes it spatially, using the
MAX operation. The most common form is a pooling layer with filters of size
2x2 applied with a stride of 2 down samples every depth slice in the input by 2
along both width and height, discarding 75% of the activations. Every MAX
operation would in this case be taking a max over 4 numbers (little 2x2region in
some depth slice). The depth dimension remains unchanged.
15
3-The Fully Connected layer: is configured exactly the way its name implies: it
is fully connected with the output of the previous layer. Fully-connected layers
are typically used in the last stages of the CNN to connect to the output layer and
construct the desired number of outputs.
16
Advantages
1-Reduces the need for feature engineering, one of the most time-consuming
parts of machine learning practice
2-Is an architecture that can be adapted to new problems relatively easily
Disadvantage
1-Requires a large amount of data.
2-Is extremely computationally expensive to train. The most complex odels
take weeks to train using hundreds of machines equipped with expensive
GPUs.
Deeplearning applications :
1. Natural language processing
2. Computer vision
3. speechrecognition
References
1. Fundamentals of the New Artificial Intelligence Neural, Evolutionary, Fuzzy
and More Second Edition. By Toshinori Munakata, Springer-Verlag London
Limited 2008
2. Foundations of Neural Networks, Fuzzy Systems, and Knowledge
Engineering, by Nikola K. Kasabov, 1996 Massachusetts Institute of Technology
3. Fundamentals Of Neural Networks, by Laurene Fausett, Prentice Hall 1993
4. Deep Learning, by Ian Goodfellow, Yoshua Bengio, Aaron Courville
5. Deep Learning Methods and Applications, by Li Deng and Dong Yu 2014
6. http://cs231n.github.io/convolutional-networks/
7. Predicting Stock Markets with Neural Networks A Comparative Study, by
Torkil Aamodt 2015.

Recomendados

SCREENLESS DISPLAY por
SCREENLESS DISPLAYSCREENLESS DISPLAY
SCREENLESS DISPLAYMahad Mumtaz
10.6K visualizações18 slides
Screenless display technology por
Screenless display technologyScreenless display technology
Screenless display technologyzeelarora
6.7K visualizações17 slides
Mobile TV por
Mobile TV Mobile TV
Mobile TV Sumit Biswas
7.5K visualizações33 slides
Introduction uc por
Introduction ucIntroduction uc
Introduction ucPurvi Sankhe
922 visualizações39 slides
chameleon chip por
chameleon chipchameleon chip
chameleon chipSucharita Bohidar
17.2K visualizações19 slides
Screenless displays ppt por
Screenless displays ppt Screenless displays ppt
Screenless displays ppt Jeevan Kumar D
28K visualizações15 slides

Mais conteúdo relacionado

Mais procurados

Screenless displays seminar report por
Screenless displays seminar reportScreenless displays seminar report
Screenless displays seminar reportJeevan Kumar D
26K visualizações22 slides
Virtual keyboard por
Virtual keyboardVirtual keyboard
Virtual keyboardsiddhantranjan
10.6K visualizações23 slides
Virtual Retinal Display: their falling cost and rising performance por
Virtual Retinal Display: their falling cost and rising performanceVirtual Retinal Display: their falling cost and rising performance
Virtual Retinal Display: their falling cost and rising performanceJeffrey Funk
5.5K visualizações43 slides
BLUE BRAIN TECHNOLOGY por
BLUE BRAIN TECHNOLOGYBLUE BRAIN TECHNOLOGY
BLUE BRAIN TECHNOLOGYShivangi Sinha
2.2K visualizações25 slides
Screenless display por
Screenless displayScreenless display
Screenless displaychnaveed
2.9K visualizações35 slides
E-PAPER TECHNOLOGY por
E-PAPER TECHNOLOGYE-PAPER TECHNOLOGY
E-PAPER TECHNOLOGYPranav Patel
67.9K visualizações25 slides

Mais procurados(20)

Screenless displays seminar report por Jeevan Kumar D
Screenless displays seminar reportScreenless displays seminar report
Screenless displays seminar report
Jeevan Kumar D26K visualizações
Virtual keyboard por siddhantranjan
Virtual keyboardVirtual keyboard
Virtual keyboard
siddhantranjan10.6K visualizações
Virtual Retinal Display: their falling cost and rising performance por Jeffrey Funk
Virtual Retinal Display: their falling cost and rising performanceVirtual Retinal Display: their falling cost and rising performance
Virtual Retinal Display: their falling cost and rising performance
Jeffrey Funk5.5K visualizações
BLUE BRAIN TECHNOLOGY por Shivangi Sinha
BLUE BRAIN TECHNOLOGYBLUE BRAIN TECHNOLOGY
BLUE BRAIN TECHNOLOGY
Shivangi Sinha2.2K visualizações
Screenless display por chnaveed
Screenless displayScreenless display
Screenless display
chnaveed2.9K visualizações
E-PAPER TECHNOLOGY por Pranav Patel
E-PAPER TECHNOLOGYE-PAPER TECHNOLOGY
E-PAPER TECHNOLOGY
Pranav Patel67.9K visualizações
Graphical Password Authenticationimp.docx2 por Raghu Vamsy Sirasala
Graphical Password Authenticationimp.docx2Graphical Password Authenticationimp.docx2
Graphical Password Authenticationimp.docx2
Raghu Vamsy Sirasala6.7K visualizações
Screenless Display PPT por Vikas Kumar
Screenless Display PPTScreenless Display PPT
Screenless Display PPT
Vikas Kumar104.2K visualizações
05012013150050 computerised-paper-evaluation-using-neural-network por nimmajji
05012013150050 computerised-paper-evaluation-using-neural-network05012013150050 computerised-paper-evaluation-using-neural-network
05012013150050 computerised-paper-evaluation-using-neural-network
nimmajji3.5K visualizações
Fog Screen technology por VijayRoyal5
Fog Screen technologyFog Screen technology
Fog Screen technology
VijayRoyal56K visualizações
E-Ball Technology por ashima sood
E-Ball Technology E-Ball Technology
E-Ball Technology
ashima sood849 visualizações
Touchless Touchscreen Technology por Saurabh Tripathi
Touchless Touchscreen TechnologyTouchless Touchscreen Technology
Touchless Touchscreen Technology
Saurabh Tripathi1.8K visualizações
Z force touch screen technology por lokesh naidu
Z force touch screen technologyZ force touch screen technology
Z force touch screen technology
lokesh naidu4.2K visualizações
Automatic Irrigation System Project Report por Er Gupta
Automatic Irrigation System Project ReportAutomatic Irrigation System Project Report
Automatic Irrigation System Project Report
Er Gupta51.1K visualizações
Screenless display report por Vikas Kumar
Screenless display reportScreenless display report
Screenless display report
Vikas Kumar38.1K visualizações
Eye Movement based Human Computer Interaction Technique por Jobin George
Eye Movement based Human Computer Interaction TechniqueEye Movement based Human Computer Interaction Technique
Eye Movement based Human Computer Interaction Technique
Jobin George23.7K visualizações
Jini network technology por Keerthi Thomas
Jini  network   technologyJini  network   technology
Jini network technology
Keerthi Thomas8.3K visualizações
Deaf and Dump Gesture Recognition System por Praveena T
Deaf and Dump Gesture Recognition SystemDeaf and Dump Gesture Recognition System
Deaf and Dump Gesture Recognition System
Praveena T10.3K visualizações
Screenless Display PPT Presentation por Sai Mohith
Screenless Display PPT PresentationScreenless Display PPT Presentation
Screenless Display PPT Presentation
Sai Mohith5.6K visualizações
EBO ROBOT PPT.pptx por KavyasreeKamsani
EBO ROBOT PPT.pptxEBO ROBOT PPT.pptx
EBO ROBOT PPT.pptx
KavyasreeKamsani910 visualizações

Similar a deep learning

Deep Learning Survey por
Deep Learning SurveyDeep Learning Survey
Deep Learning SurveyAnthony Parziale
768 visualizações13 slides
A Study On Deep Learning por
A Study On Deep LearningA Study On Deep Learning
A Study On Deep LearningAbdelrahman Hosny
1.7K visualizações13 slides
Deep learning (2) por
Deep learning (2)Deep learning (2)
Deep learning (2)Muhanad Al-khalisy
169 visualizações35 slides
Speech Processing with deep learning por
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learningMohamed Essam
102 visualizações21 slides
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R por
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RUnderstanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RManish Saraswat
482 visualizações18 slides
Face recognition using artificial neural network por
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural networkSumeet Kakani
29.6K visualizações22 slides

Similar a deep learning(20)

Deep Learning Survey por Anthony Parziale
Deep Learning SurveyDeep Learning Survey
Deep Learning Survey
Anthony Parziale768 visualizações
A Study On Deep Learning por Abdelrahman Hosny
A Study On Deep LearningA Study On Deep Learning
A Study On Deep Learning
Abdelrahman Hosny1.7K visualizações
Deep learning (2) por Muhanad Al-khalisy
Deep learning (2)Deep learning (2)
Deep learning (2)
Muhanad Al-khalisy169 visualizações
Speech Processing with deep learning por Mohamed Essam
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learning
Mohamed Essam102 visualizações
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R por Manish Saraswat
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RUnderstanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Manish Saraswat482 visualizações
Face recognition using artificial neural network por Sumeet Kakani
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural network
Sumeet Kakani29.6K visualizações
Deep Neural Network DNN.docx por jaffarbikat
Deep Neural Network DNN.docxDeep Neural Network DNN.docx
Deep Neural Network DNN.docx
jaffarbikat3 visualizações
let's dive to deep learning por Mohamed Essam
let's dive to deep learninglet's dive to deep learning
let's dive to deep learning
Mohamed Essam76 visualizações
Cnn por rimshailyas1
CnnCnn
Cnn
rimshailyas172 visualizações
Artificial neural network paper por AkashRanjandas1
Artificial neural network paperArtificial neural network paper
Artificial neural network paper
AkashRanjandas160 visualizações
DL.pdf por ssuserd23711
DL.pdfDL.pdf
DL.pdf
ssuserd2371117 visualizações
Convolutional Neural Network and Its Applications por Kasun Chinthaka Piyarathna
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
Kasun Chinthaka Piyarathna4.6K visualizações
BASIC CONCEPT OF DEEP LEARNING.pptx por RiteshPandey184067
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptx
RiteshPandey18406725 visualizações
Automatic Attendace using convolutional neural network Face Recognition por vatsal199567
Automatic Attendace using convolutional neural network Face RecognitionAutomatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face Recognition
vatsal199567532 visualizações
Let_s_Dive_to_Deep_Learning.pptx por Mohamed Essam
Let_s_Dive_to_Deep_Learning.pptxLet_s_Dive_to_Deep_Learning.pptx
Let_s_Dive_to_Deep_Learning.pptx
Mohamed Essam5 visualizações
Som paper1.doc por Abhi Mediratta
Som paper1.docSom paper1.doc
Som paper1.doc
Abhi Mediratta392 visualizações
Intro to Deep learning - Autoencoders por Akash Goel
Intro to Deep learning - Autoencoders Intro to Deep learning - Autoencoders
Intro to Deep learning - Autoencoders
Akash Goel5.8K visualizações
Deep learning algorithms por Revanth Kumar
Deep learning algorithmsDeep learning algorithms
Deep learning algorithms
Revanth Kumar60 visualizações
Artifical Neural Network por mahalakshmimalini
Artifical Neural NetworkArtifical Neural Network
Artifical Neural Network
mahalakshmimalini744 visualizações
Neural networks and deep learning por RADO7900
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
RADO790095 visualizações

Mais de Hassanein Alwan

Feasibility study por
Feasibility studyFeasibility study
Feasibility studyHassanein Alwan
415 visualizações10 slides
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM. por
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.Hassanein Alwan
80 visualizações19 slides
Community Engagement por
Community EngagementCommunity Engagement
Community EngagementHassanein Alwan
52 visualizações32 slides
Data Management por
Data ManagementData Management
Data ManagementHassanein Alwan
137 visualizações9 slides
video comparison por
video comparison video comparison
video comparison Hassanein Alwan
105 visualizações13 slides
Planning for contingencies por
Planning for contingenciesPlanning for contingencies
Planning for contingenciesHassanein Alwan
297 visualizações12 slides

Mais de Hassanein Alwan(9)

Feasibility study por Hassanein Alwan
Feasibility studyFeasibility study
Feasibility study
Hassanein Alwan415 visualizações
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM. por Hassanein Alwan
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.
ARABIC TEXT MINING AND ROUGH SET THEORY FOR DECISION SUPPORT SYSTEM.
Hassanein Alwan80 visualizações
Community Engagement por Hassanein Alwan
Community EngagementCommunity Engagement
Community Engagement
Hassanein Alwan52 visualizações
Data Management por Hassanein Alwan
Data ManagementData Management
Data Management
Hassanein Alwan137 visualizações
video comparison por Hassanein Alwan
video comparison video comparison
video comparison
Hassanein Alwan105 visualizações
Planning for contingencies por Hassanein Alwan
Planning for contingenciesPlanning for contingencies
Planning for contingencies
Hassanein Alwan297 visualizações
Data link layer por Hassanein Alwan
Data link layerData link layer
Data link layer
Hassanein Alwan196 visualizações
data replication por Hassanein Alwan
data replicationdata replication
data replication
Hassanein Alwan945 visualizações
Project Organizations por Hassanein Alwan
Project Organizations Project Organizations
Project Organizations
Hassanein Alwan268 visualizações

Último

Future of Indian ConsumerTech por
Future of Indian ConsumerTechFuture of Indian ConsumerTech
Future of Indian ConsumerTechKapil Khandelwal (KK)
21 visualizações68 slides
virtual reality.pptx por
virtual reality.pptxvirtual reality.pptx
virtual reality.pptxG036GaikwadSnehal
11 visualizações15 slides
Business Analyst Series 2023 - Week 3 Session 5 por
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5DianaGray10
248 visualizações20 slides
STKI Israeli Market Study 2023 corrected forecast 2023_24 v3.pdf por
STKI Israeli Market Study 2023   corrected forecast 2023_24 v3.pdfSTKI Israeli Market Study 2023   corrected forecast 2023_24 v3.pdf
STKI Israeli Market Study 2023 corrected forecast 2023_24 v3.pdfDr. Jimmy Schwarzkopf
19 visualizações29 slides
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院 por
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院IttrainingIttraining
52 visualizações8 slides
Data Integrity for Banking and Financial Services por
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial ServicesPrecisely
21 visualizações26 slides

Último(20)

virtual reality.pptx por G036GaikwadSnehal
virtual reality.pptxvirtual reality.pptx
virtual reality.pptx
G036GaikwadSnehal11 visualizações
Business Analyst Series 2023 - Week 3 Session 5 por DianaGray10
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5
DianaGray10248 visualizações
STKI Israeli Market Study 2023 corrected forecast 2023_24 v3.pdf por Dr. Jimmy Schwarzkopf
STKI Israeli Market Study 2023   corrected forecast 2023_24 v3.pdfSTKI Israeli Market Study 2023   corrected forecast 2023_24 v3.pdf
STKI Israeli Market Study 2023 corrected forecast 2023_24 v3.pdf
Dr. Jimmy Schwarzkopf19 visualizações
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院 por IttrainingIttraining
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
IttrainingIttraining52 visualizações
Data Integrity for Banking and Financial Services por Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely21 visualizações
Future of AR - Facebook Presentation por ssuserb54b561
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
ssuserb54b56114 visualizações
Igniting Next Level Productivity with AI-Infused Data Integration Workflows por Safe Software
Igniting Next Level Productivity with AI-Infused Data Integration Workflows Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Safe Software263 visualizações
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... por TrustArc
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc10 visualizações
Voice Logger - Telephony Integration Solution at Aegis por Nirmal Sharma
Voice Logger - Telephony Integration Solution at AegisVoice Logger - Telephony Integration Solution at Aegis
Voice Logger - Telephony Integration Solution at Aegis
Nirmal Sharma39 visualizações
Mini-Track: Challenges to Network Automation Adoption por Network Automation Forum
Mini-Track: Challenges to Network Automation AdoptionMini-Track: Challenges to Network Automation Adoption
Mini-Track: Challenges to Network Automation Adoption
Network Automation Forum12 visualizações
Piloting & Scaling Successfully With Microsoft Viva por Richard Harbridge
Piloting & Scaling Successfully With Microsoft VivaPiloting & Scaling Successfully With Microsoft Viva
Piloting & Scaling Successfully With Microsoft Viva
Richard Harbridge12 visualizações
Democratising digital commerce in India-Report por Kapil Khandelwal (KK)
Democratising digital commerce in India-ReportDemocratising digital commerce in India-Report
Democratising digital commerce in India-Report
Kapil Khandelwal (KK)15 visualizações
Network Source of Truth and Infrastructure as Code revisited por Network Automation Forum
Network Source of Truth and Infrastructure as Code revisitedNetwork Source of Truth and Infrastructure as Code revisited
Network Source of Truth and Infrastructure as Code revisited
Network Automation Forum26 visualizações
6g - REPORT.pdf por Liveplex
6g - REPORT.pdf6g - REPORT.pdf
6g - REPORT.pdf
Liveplex10 visualizações
Powerful Google developer tools for immediate impact! (2023-24) por wesley chun
Powerful Google developer tools for immediate impact! (2023-24)Powerful Google developer tools for immediate impact! (2023-24)
Powerful Google developer tools for immediate impact! (2023-24)
wesley chun10 visualizações
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... por James Anderson
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
James Anderson85 visualizações
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... por Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker37 visualizações

deep learning

  • 1. 1 Deep Learning Prepared by Hassanein Alwan Malik University Of Technology Computer Science Master of Science
  • 2. 2 Introduction Deeplearning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. Deeplearning is a key technologybehind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, TVs, and hands- free speakers. Deeplearning is getting lots of attention lately and for goodreason. It’s achieving results that were not possible before we will overview the neuralnetworks and take a generalview of some of their types as examples to understand thebasics of neural networks and then move to a general description of deep education 1.Artificial Neural networks(ANN) systems that processing information, inspired by biological neural systems. Neural networks consist of many simple processing elements called Neurons, nodes, units or cells. Artificial neural networks have been developed as generalizations of mathematical models of human cognition or neural biology, based on the assumptions that:- 1. Information processingoccurs at many simple elements called neurons. 2. Signals are passed between neurons over connection links. 3. Each connection link has an associated weight which, in a typical neural net, multiplies the signal transmitted.
  • 3. 3 1.1 Type of architecture The NN consists of input units, output units, and one hidden unit. Neural nets are often classified as single layer or multilayer by depending on the number of layers (hidden unit) and the number of layers in the NN can be defined to be the numbers of layers of weighted interconnect links between the neurons. Single layer NN has one layer of connection weights.
  • 4. 4 Multilayer NN A Multilayer net is a net with one or more layers (or levels) of nodes which is called hidden units, between the input units and the output units. 2 What Is Learning and What Is Generalization in ANNs? We use the properties of ANN to made a model that can be solve a problems through learning the model by given it a training data and adjusting the weights until the output achieved our goal. Rather than use a single program to solve every single problem we can generalization our model to solve several problems.
  • 5. 5 There is three type of learning : a- Supervised learning : The training data comprise input vectors x and the desired output vectors y. Training is performed until the neural network "learns" to associate each input vector x to its corresponding and desired output vector y. b- Unsupervised: Only input vectors x are supplied; the neural network learns some internal features of the whole set of all the input vectors presented to it.
  • 6. 6 c- Self- Organization sometimes called reward-penalty learning (reinforcement), is a combination of the above two paradigms; it is based on presenting input vector x to a neural network and looking at the output vector calculated by the network. If it is considered "good," then a "reward" is given to the network in the sense that the existing connection weights are increased; otherwise the network is "punished", the connection weights, being considered as "not appropriately set," decrease. Learning type  Hebbian Learning Rule It’s a learning rule that suggested by Hebb in 1949, and it can represented by the rule: If two neurons on either side of connection are activated synchronously, then the weight of that connection is increased. Note: Hebb's rule provide the basis for unsupervised learning. Features of Hebb rule 1. Unsupervised 2. Fully conncted. 3. Single Layer (with lack of a hidden layer within the network). The common uses of Hebb is in Character Recognition By training the net to distinguish between the pattern "X" and the pattern "0".
  • 7. 7
  • 8. 8 3 Deep learning neural network How deep learning works? We will take an Image recognition model as an example to illustration how is deep learning working  First stage : learning the model :- so we feeding the model with a large amount of images (e.g many various images cats, dogs, wolf, tigers, ….etc.)as a training data and learning the model to recognize an unlabeled image , the first layer usually consistof many activation functions that have specific job which is detection the edges of images, so it will take the input images and begin learning itself through obtained the features edges images and gives these features to the second layer. The second layer activation functions have another job that is detection the objects parts (nose, mouth, eyes), so it will obtained the features and learning itself. The third layer activation functions will detecting the object features and learning itself through the obtained features.  Second stage : test the model So, when we input an unlabeled image to the model, for example a dog image, the first layer will matching the edge of cat image with all images, and feeds the second layer with only the edges that have similar features (e.g the cat , wolf, dog and raccoonhave similar edge, but elephant is different). The second layer will receive the obtained features with the input image from the first layer and will matching the object parts of input image with only images that already determined from the first layer by it features ( it will matching the nose, mouth, eye, …etc with the images of cat , wolf, dog, and raccoonand will ignoring the other images) and feeds the third layer with only the object parts that have similar features (e.g the raccoon and cat will excluded). The third layer will receive the obtained features with the input image from the second layer and will matching the object of the input image with the images that selected from the previous layer (e.g the wolf, image with dog image), and the result will be the dog image.
  • 9. 9 Notes: a. Every layer have an independent function but all layers associated in hierarchically. b. In every move from lower layer to the next, the options is decreased until achieved the goal. c. The higher layer more complex than the lower layer.
  • 10. 10 E.g. Classify a cat:  Bottom Layers: Edge detectors, curves, corners straight lines  Middle Layers: Fur patterns, eyes, ears  Higher Layers: Body, head, legs  Top Layer: Cat or Dog
  • 11. 11 4 Deep Leaning Algorithms Also known as deep structured learning, hierarchical learning or deep machine learning) is a class of machine learning algorithms that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). convolutional neural networks (CNN) A typical CNN is composed of many layers of hierarchy with some layers for feature representations (or feature maps) and others as a type of conventional neural networks for classification. It often starts with two altering types of layers called convolutional and subsampling layers: convolutional layers perform convolution operations with several filter maps of equal size, while subsampling layers reduce the sizes of proceeding layers by averaging pixels within a small neighborhood (or by max-pooling. Facebook uses neural nets for their automatic tagging algorithms, Google for their photo search, Amazon for their product recommendations, and Instagram for their search infrastructure. Simple ConvNet is a sequence of layers: Convolutional Layer, Pooling Layer, and Fully-Connected Layer.
  • 12. 12 Figure shows a typical architecture of CNNs. The input is first convoluted with a set of filters (C layers in Fig). These 2D filtered data are called feature maps. After a nonlinear transformation, a subsampling is further performed to reduce the dimensionality (S layers in Figure 2). The sequence of convolution/subsampling can be repeated many times (predetermined by users). 1-Convolutional Layer: Also referred to as Conv. layer, it forms the basis of the CNN and performs the core operations of training and consequently firing the neurons of the network. It performs the convolution operation over the input volume and consists of a 3-dimensional arrangement of neurons (a stack of 2- dimensional layers of neurons, one for each channel depth). That make : Filters (Convolution Kernels) :A filter (or kernel) is an integral component of the layered architecture. it refers to an operator applied to the entirety of the image such that it transforms the information encoded in the pixels Figure (2) CNN
  • 13. 13 Spatial arrangement. We have explained the connectivity of each neuron in the Conv Layer to the input volume, but we haven’t yet discussed how many neurons there are in the output volume or how they are arranged. Three hyper parameters control the size of the output volume: the depth, stride and zero-padding. We discuss these next: 1. First, the depth of the output volume is a hyper parameter: it corresponds to the number of filters we would like to use, each learning to look for something different in the input. Forexample, if the first Convolutional Layer takes as input the raw image, then different neurons along the depth dimension may activate in presence of various oriented edges, or blobs of color. We will refer to a set of neurons that are all looking at the same region of the input as a depth column (some people also prefer the term fibre). 2. Second, we must specify the stride with which we slide the filter. When the stride is 1 then we move the filters one pixel at a time. When the stride is 2 (or uncommonly 3 or more, though this is rare in practice) then the filters jump 2 pixels at a time as we slide them around. This will producesmaller output volumes spatially. 3. As we will soonsee, sometimes it will be convenient to pad the input volume with zeros around the border. The size of this zero-padding is a hyper parameter. The nice feature of zero padding is that it will allow us to control the spatial size of the output volumes (most commonly as we’ll see soonwe will use it to exactly preserve the spatial size of the input volume so the input and output width and height are the same). We can compute the spatial size of the output volume as a function of the input volume size (W), the receptive field size of the Conv Layer neurons (F), the stride with which they are applied (S), and the amount of zero padding used (P) on the border. You can convince yourself that the correct formula for calculating how many neurons “fit” is given by (W−F+2P)/S+1(W−F+2P)/S+1.
  • 14. 14 Illustration of spatial arrangement. In this example there is only one spatial dimension (x-axis), one neuron with a receptive field size of F = 3, the input size is W = 5, and there is zero padding of P = 1. Left: The neuron strided across the input in stride of S = 1, giving output of size (5 - 3 + 2)/1+1 = 5. Right: The neuron uses stride of S = 2, giving output of size (5 - 3 + 2)/2+1 = 3. Notice that stride S = 3 could not be used since it wouldn't fit neatly across the volume. In terms of the equation, this can be determined since (5 - 3 + 2) = 4 is not divisible by 3. The neuron weights are in this example (shown on very right), and its bias is zero. These weights are shared across all yellow neurons (see parameter sharing below 2-Pooling layer (subsampling layer): it is between successive Conv layers in ConvNet architecture. Its function is to progressively reduce the spatial size of the representation to reduce the amount of parameters and computation in the network, and hence to also control over fitting. The Pooling Layer operates independently on every depth slice of the input and resizes it spatially, using the MAX operation. The most common form is a pooling layer with filters of size 2x2 applied with a stride of 2 down samples every depth slice in the input by 2 along both width and height, discarding 75% of the activations. Every MAX operation would in this case be taking a max over 4 numbers (little 2x2region in some depth slice). The depth dimension remains unchanged.
  • 15. 15 3-The Fully Connected layer: is configured exactly the way its name implies: it is fully connected with the output of the previous layer. Fully-connected layers are typically used in the last stages of the CNN to connect to the output layer and construct the desired number of outputs.
  • 16. 16 Advantages 1-Reduces the need for feature engineering, one of the most time-consuming parts of machine learning practice 2-Is an architecture that can be adapted to new problems relatively easily Disadvantage 1-Requires a large amount of data. 2-Is extremely computationally expensive to train. The most complex odels take weeks to train using hundreds of machines equipped with expensive GPUs. Deeplearning applications : 1. Natural language processing 2. Computer vision 3. speechrecognition References 1. Fundamentals of the New Artificial Intelligence Neural, Evolutionary, Fuzzy and More Second Edition. By Toshinori Munakata, Springer-Verlag London Limited 2008 2. Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering, by Nikola K. Kasabov, 1996 Massachusetts Institute of Technology 3. Fundamentals Of Neural Networks, by Laurene Fausett, Prentice Hall 1993 4. Deep Learning, by Ian Goodfellow, Yoshua Bengio, Aaron Courville 5. Deep Learning Methods and Applications, by Li Deng and Dong Yu 2014 6. http://cs231n.github.io/convolutional-networks/ 7. Predicting Stock Markets with Neural Networks A Comparative Study, by Torkil Aamodt 2015.