SlideShare a Scribd company logo
1 of 55
Deep Learning
Supervised by prof.asst. Dr.mohammad najem
by: Huda hamdan ali
contents
 Introduction and overveiw
 Deep learning challenges
 Deep N.N
 Unsupervised Preprocessing Networks
 Deep Belief Networks
 Denoising auto encoder
 Stacked Auto Encoders
 Deep Boltzmann Machines
 CNN – Convolutional Neural Networks
 Recurrent N.N
 Long Short-Term Memory RNN (LSTM)
 Generative Adversarial Neural
 Deep Reinforcement Learning
 Applications.
2
introduction
 Deep learning (also known as deep structured
learning or hierarchical learning) is part of a broader family
of machine learning methods based on learning data
representations, as opposed to task-specific algorithms.
Learning can be supervised, semi-
supervised or unsupervised.
 use a cascade of multiple layers of nonlinear
processing units for feature extraction and transformation.
Each successive layer uses the output from the previous layer
as input
 Deep learning architectures such as deep neural
networks, deep belief networks and recurrent neural
networks have been applied to fields including computer
vision, speech recognition, natural language processing,
Introduction cont..
 Deep learning algorithms can be applied to unsupervised learning
tasks.
 This is an important benefit because unlabeled data are more
abundant than labeled data.
Inspired by the Brain
 The first hierarchy of neurons that receives information in the
visual cortex are sensitive to specific edges while brain regions
further down the visual pipeline are sensitive to more complex
structures such as faces.
 Our brain has lots of neurons connected together and the
strength of the connections between neurons represents long
term knowledge.
Deep Learning training
Overview
 Train networks with many layers (Multiple layers work to build an
improved feature space
 First layer learns 1st
order features (e.g. edges…)
 2nd
layer learns higher order features (combinations of first layer
features, combinations of edges, etc.)
 Some models learn in an unsupervised mode and discover general
features of the input space – serving multiple tasks related to the
unsupervised instances (image recognition, etc.)
 Final layer of transformed features are fed into supervised layer(s)
 And entire network is often subsequently tuned using supervised training of
the entire net, using the initial weightings learned in the unsupervised phase
Deep Learning Architecture
A deep neural network consists of a hierarchy of layers, whereby each
layer transforms the input data into more abstract representations (e.g.
edge -> nose -> face). The output layer combines those features to make
predictions
What did it learn?
No more feature engineering
Problems with Back Propagation
 Gradient is progressively getting more dilute
 Below top few layers, correction signal is minimal
 Gets stuck in local minima
 Especially since they start out far from ‘good’ regions
(i.e., random initialization)
DNN challenges
 As with ANNs, many issues can arise with naively trained DNNs. Two
common issues are overfitting and computation time.
 DNNs are prone to overfitting because of the added layers of
abstraction, which allow them to model rare dependencies in the
training data.
 Regularization methods such as Ivakhnenko's unit pruning or
weight decay (regularization) or sparsity (regularization) can be
applied during training to combat overfitting. Alternatively dropout
regularization randomly omits units from the hidden layers during
training.
 This helps to exclude rare dependencies.
 Finally, data can be augmented via methods such as cropping
and rotating such that smaller training sets can be increased in size
to reduce the chances of overfitting.

Challenge cont..
 DNNs must consider many training parameters, such as
the size (number of layers and number of units per layer),
the learning rate and initial weights.
 Sweeping through the parameter space for optimal
parameters may not be feasible due to the cost in time
and computational resources.
 Various tricks such as batching (computing the gradient
on several training examples at once rather than
individual examples) speed up computation.
 The large processing throughput of GPUs has produced
significant speedups in training, because the matrix and
vector computations required are well-suited for GPUs.
Challenge Cont..
 Alternatively, we may need to look for other type of
neural network which has straightforward and
convergent training algorithm.
 CMAC (cerebellar model articulation controller) is such
kind of neural network. For example, there is no need to
adjust learning rates or randomize initial weights for
CMAC. The training process can be guaranteed to
converge in one step with a new batch of data, and the
computational complexity of the training algorithm is
linear with respect to the number of neurons involved
Greedy Layer-Wise Training
1. Train first layer using your data without the labels (unsupervised)
 Since there are no targets at this level, labels don't help.
 Then freeze the first layer parameters and start training the second
layer using the output of the first layer as the unsupervised input to the
second layer
1. Repeat this for as many layers as desired
 This builds the set of robust features
1. Use the outputs of the final layer as inputs to a supervised
layer/model and train the last supervised layer (s) (leave early
weights frozen)
2. Unfreeze all weights and fine tune the full network by training with
a supervised approach, given the pre-training weight settings
15
David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com
These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
Deep Belief Networks(DBNs)
 Unsupervised pre-learning provides a good initialization
of the network
 Probabilistic generative model
 Deep architecture – multiple layers
 Supervised fine-tuning
 Generative: Up-down algorithm
 Discriminative: backpropagation
DBN Greedy training
 First step:
 Construct an RBM with an input layer v and a hidden
layer h
 Train the RBM
 A restricted Boltzmann machine (RBM) is:
a generative stochastic artificial neural network that
can learn a probability distribution over its set of inputs.
Auto-Encoders
 A type of unsupervised learning,
 An autoencoder is typically a feedforward neural network which aims to
learn a compressed, distributed representation (encoding) of a dataset.
 Conceptually, the network is trained to “recreate” the input, i.e., the
input and the target data are the same. In other words: you’re trying to
output the same thing you were input, but compressed in some way.
 In effect, we want a few small nodes in the middle to really learn the
data at a conceptual level, producing a compact representation that in
some way captures the core features of our input.
22
David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com
These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
Denoising Auto-Encoder
Stacked (Denoising) Auto-
Encoders
David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com
These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
Deep Boltzmann Machines
DBMs vs. DBNs
Convolutional Neural Nets
(CNN)
Convolutional Neural Nets (CNN)
Convolution layers a feature detector that automagically learns to filter out
not needed information from an input by using convolution kernel.
Pooling layers compute the max or average value of a particular feature over
a region of the input data (downsizing of input images).Also helps to detect
objects in some unusual places and reduces memory size.
CNN
 High accuracy for image applications – Breaking all records and
doing it using just raw pixel features.
 Special purpose net – Just for images or problems with strong grid-like
local spatial/temporal correlation
 Once trained on one problem (e.g. vision) could use same net (often
tuned) for a new similar problem – general creator of vision features
 Unlike traditional nets, handles variable sized inputs
 Same filters and weights, just convolve across different sized image and
dynamically scale size of pooling regions (not # of nodes), to normalize
 Different sized images, different length speech segments, etc.
 Lots of hand crafting and CV tuning to find the right recipe of
receptive fields, layer interconnections, etc.
 Lots more Hyperparameters than standard nets, and even than other
deep networks, since the structures of CNNs are more handcrafted
 CNNs getting wider and deeper with speed-up techniques (e.g. GPU,
ReLU, etc.) and lots of current research, excitement, and success
31
Recurrent Neural Nets (RNN)
Long Short-Term Memory RNN (LSTM)
Deep Reinforcement
Learning
Generative Adversarial Networks
Deep learning Applications
Deep Learning in Computer
Vision
Image Segmentation
Deep Learning in Computer Vision
Image Captioning
Deep Learning in Computer
Vision
Image Compression
Deep Learning in Computer Vision
Image Localization
Deep Learning in Computer Vision
Image Transformation –Adding
features
Deep Learning in Computer
Vision
Image Colorization
Image Generation –From
Descriptions
Style Transfer –morph images
into paintings
Deep Learning in Audio
Processing Sound Generation
Deep Learning in NLP
Syntax Parsing
Deep Learning in NLP
Generating Text
Deep Learning in Medicine
Skin Cancer Diagnoses
Deep Learning in Medicine
Detection of diabetic eye disease
Deep Learning in Science
Saving Energy
Deep Learning in Cryptography
Learning to encrypt and decrypt
communication
Autonomous drone navigation
with deep learning
Finally ..
 That’s the basic idea..
 There are many types of deep learning,
 different kinds of autoencoder, variations on architectures and
training algorithms, etc…
 Very fast growing area …
Thanks for attention
2017 //H u d a

More Related Content

What's hot

End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...Universitat Politècnica de Catalunya
 
Character Recognition using Artificial Neural Networks
Character Recognition using Artificial Neural NetworksCharacter Recognition using Artificial Neural Networks
Character Recognition using Artificial Neural NetworksJaison Sabu
 
Basics of Deep learning
Basics of Deep learningBasics of Deep learning
Basics of Deep learningRamesh Kumar
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learningPoo Kuan Hoong
 
Deep learning frameworks v0.40
Deep learning frameworks v0.40Deep learning frameworks v0.40
Deep learning frameworks v0.40Jessica Willis
 
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 :김인중datasciencekorea
 
Survey on Deep Neural Network Watermarking techniques
Survey on Deep Neural Network Watermarking techniquesSurvey on Deep Neural Network Watermarking techniques
Survey on Deep Neural Network Watermarking techniquesPrincy Joy
 
Fundamental of deep learning
Fundamental of deep learningFundamental of deep learning
Fundamental of deep learningStanley Wang
 
Deep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsDeep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsPrincy Joy
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKSESCOM
 
Artificial neural network for machine learning
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learninggrinu
 
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...COMPEGENCE
 
Top 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inAmanKumarSingh97
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksstellajoseph
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
From neural networks to deep learning
From neural networks to deep learningFrom neural networks to deep learning
From neural networks to deep learningViet-Trung TRAN
 
Handwritten digits recognition report
Handwritten digits recognition reportHandwritten digits recognition report
Handwritten digits recognition reportSwayamdipta Saha
 

What's hot (20)

End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
 
Character Recognition using Artificial Neural Networks
Character Recognition using Artificial Neural NetworksCharacter Recognition using Artificial Neural Networks
Character Recognition using Artificial Neural Networks
 
Basics of Deep learning
Basics of Deep learningBasics of Deep learning
Basics of Deep learning
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learning
 
Deep learning frameworks v0.40
Deep learning frameworks v0.40Deep learning frameworks v0.40
Deep learning frameworks v0.40
 
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
 
Survey on Deep Neural Network Watermarking techniques
Survey on Deep Neural Network Watermarking techniquesSurvey on Deep Neural Network Watermarking techniques
Survey on Deep Neural Network Watermarking techniques
 
Fundamental of deep learning
Fundamental of deep learningFundamental of deep learning
Fundamental of deep learning
 
Deep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsDeep Semi-supervised Learning methods
Deep Semi-supervised Learning methods
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKS
 
Artificial neural network for machine learning
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learning
 
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
 
Top 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know in
 
Neural
NeuralNeural
Neural
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
 
From neural networks to deep learning
From neural networks to deep learningFrom neural networks to deep learning
From neural networks to deep learning
 
Handwritten digits recognition report
Handwritten digits recognition reportHandwritten digits recognition report
Handwritten digits recognition report
 
Image captioning
Image captioningImage captioning
Image captioning
 

Similar to deeplearning

Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesValue Amplify Consulting
 
BASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxRiteshPandey184067
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
Machine Learning and Deep Learning with R
Machine Learning and Deep Learning with RMachine Learning and Deep Learning with R
Machine Learning and Deep Learning with RPoo Kuan Hoong
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural NetworksIRJET Journal
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101Felipe Prado
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
Speech Processing with deep learning
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learningMohamed Essam
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.pptyang947066
 
Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2EXAMCELLH4
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceLukas Masuch
 

Similar to deeplearning (20)

Deep Learning
Deep Learning Deep Learning
Deep Learning
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
AINL 2016: Filchenkov
AINL 2016: FilchenkovAINL 2016: Filchenkov
AINL 2016: Filchenkov
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
 
BASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptx
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
Machine Learning and Deep Learning with R
Machine Learning and Deep Learning with RMachine Learning and Deep Learning with R
Machine Learning and Deep Learning with R
 
Occurrence Prediction_NLP
Occurrence Prediction_NLPOccurrence Prediction_NLP
Occurrence Prediction_NLP
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Speech Processing with deep learning
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learning
 
Cnn
CnnCnn
Cnn
 
Deep learning
Deep learningDeep learning
Deep learning
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.ppt
 
Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2
 
MaLAI_Hyderabad presentation
MaLAI_Hyderabad presentationMaLAI_Hyderabad presentation
MaLAI_Hyderabad presentation
 
deep CNN vs conventional ML
deep CNN vs conventional MLdeep CNN vs conventional ML
deep CNN vs conventional ML
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial Intelligence
 
Deep learning
Deep learningDeep learning
Deep learning
 

Recently uploaded

NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...Amil Baba Dawood bangali
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Cathrine Wilhelmsen
 
Machine learning classification ppt.ppt
Machine learning classification  ppt.pptMachine learning classification  ppt.ppt
Machine learning classification ppt.pptamreenkhanum0307
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理e4aez8ss
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...ssuserf63bd7
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfBoston Institute of Analytics
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxMike Bennett
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTBoston Institute of Analytics
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxBoston Institute of Analytics
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 

Recently uploaded (20)

NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)
 
Machine learning classification ppt.ppt
Machine learning classification  ppt.pptMachine learning classification  ppt.ppt
Machine learning classification ppt.ppt
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptx
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 

deeplearning

  • 1. Deep Learning Supervised by prof.asst. Dr.mohammad najem by: Huda hamdan ali
  • 2. contents  Introduction and overveiw  Deep learning challenges  Deep N.N  Unsupervised Preprocessing Networks  Deep Belief Networks  Denoising auto encoder  Stacked Auto Encoders  Deep Boltzmann Machines  CNN – Convolutional Neural Networks  Recurrent N.N  Long Short-Term Memory RNN (LSTM)  Generative Adversarial Neural  Deep Reinforcement Learning  Applications. 2
  • 3. introduction  Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi- supervised or unsupervised.  use a cascade of multiple layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input  Deep learning architectures such as deep neural networks, deep belief networks and recurrent neural networks have been applied to fields including computer vision, speech recognition, natural language processing,
  • 4. Introduction cont..  Deep learning algorithms can be applied to unsupervised learning tasks.  This is an important benefit because unlabeled data are more abundant than labeled data.
  • 5. Inspired by the Brain  The first hierarchy of neurons that receives information in the visual cortex are sensitive to specific edges while brain regions further down the visual pipeline are sensitive to more complex structures such as faces.  Our brain has lots of neurons connected together and the strength of the connections between neurons represents long term knowledge.
  • 6. Deep Learning training Overview  Train networks with many layers (Multiple layers work to build an improved feature space  First layer learns 1st order features (e.g. edges…)  2nd layer learns higher order features (combinations of first layer features, combinations of edges, etc.)  Some models learn in an unsupervised mode and discover general features of the input space – serving multiple tasks related to the unsupervised instances (image recognition, etc.)  Final layer of transformed features are fed into supervised layer(s)  And entire network is often subsequently tuned using supervised training of the entire net, using the initial weightings learned in the unsupervised phase
  • 7. Deep Learning Architecture A deep neural network consists of a hierarchy of layers, whereby each layer transforms the input data into more abstract representations (e.g. edge -> nose -> face). The output layer combines those features to make predictions
  • 8. What did it learn?
  • 9. No more feature engineering
  • 10.
  • 11. Problems with Back Propagation  Gradient is progressively getting more dilute  Below top few layers, correction signal is minimal  Gets stuck in local minima  Especially since they start out far from ‘good’ regions (i.e., random initialization)
  • 12. DNN challenges  As with ANNs, many issues can arise with naively trained DNNs. Two common issues are overfitting and computation time.  DNNs are prone to overfitting because of the added layers of abstraction, which allow them to model rare dependencies in the training data.  Regularization methods such as Ivakhnenko's unit pruning or weight decay (regularization) or sparsity (regularization) can be applied during training to combat overfitting. Alternatively dropout regularization randomly omits units from the hidden layers during training.  This helps to exclude rare dependencies.  Finally, data can be augmented via methods such as cropping and rotating such that smaller training sets can be increased in size to reduce the chances of overfitting. 
  • 13. Challenge cont..  DNNs must consider many training parameters, such as the size (number of layers and number of units per layer), the learning rate and initial weights.  Sweeping through the parameter space for optimal parameters may not be feasible due to the cost in time and computational resources.  Various tricks such as batching (computing the gradient on several training examples at once rather than individual examples) speed up computation.  The large processing throughput of GPUs has produced significant speedups in training, because the matrix and vector computations required are well-suited for GPUs.
  • 14. Challenge Cont..  Alternatively, we may need to look for other type of neural network which has straightforward and convergent training algorithm.  CMAC (cerebellar model articulation controller) is such kind of neural network. For example, there is no need to adjust learning rates or randomize initial weights for CMAC. The training process can be guaranteed to converge in one step with a new batch of data, and the computational complexity of the training algorithm is linear with respect to the number of neurons involved
  • 15. Greedy Layer-Wise Training 1. Train first layer using your data without the labels (unsupervised)  Since there are no targets at this level, labels don't help.  Then freeze the first layer parameters and start training the second layer using the output of the first layer as the unsupervised input to the second layer 1. Repeat this for as many layers as desired  This builds the set of robust features 1. Use the outputs of the final layer as inputs to a supervised layer/model and train the last supervised layer (s) (leave early weights frozen) 2. Unfreeze all weights and fine tune the full network by training with a supervised approach, given the pre-training weight settings 15
  • 16. David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
  • 17. Deep Belief Networks(DBNs)  Unsupervised pre-learning provides a good initialization of the network  Probabilistic generative model  Deep architecture – multiple layers  Supervised fine-tuning  Generative: Up-down algorithm  Discriminative: backpropagation
  • 18.
  • 19. DBN Greedy training  First step:  Construct an RBM with an input layer v and a hidden layer h  Train the RBM  A restricted Boltzmann machine (RBM) is: a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs.
  • 20.
  • 21.
  • 22. Auto-Encoders  A type of unsupervised learning,  An autoencoder is typically a feedforward neural network which aims to learn a compressed, distributed representation (encoding) of a dataset.  Conceptually, the network is trained to “recreate” the input, i.e., the input and the target data are the same. In other words: you’re trying to output the same thing you were input, but compressed in some way.  In effect, we want a few small nodes in the middle to really learn the data at a conceptual level, producing a compact representation that in some way captures the core features of our input. 22
  • 23. David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
  • 26. David Corne, and Nick Taylor, Heriot-Watt University - dwcorne@gmail.com These slides and related resources: http://www.macs.hw.ac.uk/~dwcorne/Teaching/dmml.html
  • 30. Convolutional Neural Nets (CNN) Convolution layers a feature detector that automagically learns to filter out not needed information from an input by using convolution kernel. Pooling layers compute the max or average value of a particular feature over a region of the input data (downsizing of input images).Also helps to detect objects in some unusual places and reduces memory size.
  • 31. CNN  High accuracy for image applications – Breaking all records and doing it using just raw pixel features.  Special purpose net – Just for images or problems with strong grid-like local spatial/temporal correlation  Once trained on one problem (e.g. vision) could use same net (often tuned) for a new similar problem – general creator of vision features  Unlike traditional nets, handles variable sized inputs  Same filters and weights, just convolve across different sized image and dynamically scale size of pooling regions (not # of nodes), to normalize  Different sized images, different length speech segments, etc.  Lots of hand crafting and CV tuning to find the right recipe of receptive fields, layer interconnections, etc.  Lots more Hyperparameters than standard nets, and even than other deep networks, since the structures of CNNs are more handcrafted  CNNs getting wider and deeper with speed-up techniques (e.g. GPU, ReLU, etc.) and lots of current research, excitement, and success 31
  • 37. Deep Learning in Computer Vision Image Segmentation
  • 38. Deep Learning in Computer Vision Image Captioning
  • 39. Deep Learning in Computer Vision Image Compression
  • 40. Deep Learning in Computer Vision Image Localization
  • 41. Deep Learning in Computer Vision Image Transformation –Adding features
  • 42. Deep Learning in Computer Vision Image Colorization
  • 44. Style Transfer –morph images into paintings
  • 45. Deep Learning in Audio Processing Sound Generation
  • 46. Deep Learning in NLP Syntax Parsing
  • 47. Deep Learning in NLP Generating Text
  • 48. Deep Learning in Medicine Skin Cancer Diagnoses
  • 49. Deep Learning in Medicine Detection of diabetic eye disease
  • 50. Deep Learning in Science Saving Energy
  • 51. Deep Learning in Cryptography Learning to encrypt and decrypt communication
  • 53.
  • 54. Finally ..  That’s the basic idea..  There are many types of deep learning,  different kinds of autoencoder, variations on architectures and training algorithms, etc…  Very fast growing area …

Editor's Notes

  1. Pre-Traiining
  2. If do full supervised, we may not bet the benefits of building up the incrementally abstracted feature space Steps 1-4 called pre-training as it gets the weights close enough so that standard training in step 5 can be effective Do fine tuning for sure if lots of labeled data, if little labeled data, not as helpful.
  3. Though Deep Nets done first, start with auto-encoders because they are simpler Mention Zipser auotencoder with reverse engineering, then Cottrell compression where unable to reverse engineer If h is smaller than x then “undercomplete” autoencoding – also would use “regularized” autoencoding Can use just new features in the new training set or concatenate both original and new
  4. Dynamic size – Pooling region just sums/maxes over an area with one final weight so no hard changes when we adjust pool region size Simard 2003, Simple consistent CNN structure 5x5 with 2x2 subsampling with number of features 5 in first C-layer, 50 in next, until too small. Don’t actually used pool layer as instead just connect every other node which samples rather than max/average. Each layer reduces feature size by (n-3)/2. Just two layers for mnist. They also use elastic distortions which is a type of jitter to get increased data. 99.6% - best at the time, Distortions also help a lot with standard MLP Thus an approach with less Hyperparameter fiddling Ciresan and Schmidhuber 2012, Multi column DNN. CNN with depth 6-10 (deeper if initial input image is bigger), and wider on fields, 1-2 hidden layers in MLP, columns are CNNs (an ensemble with different parameters, features, etc.) where their output is averaged, jitter inputs, multi-day GPU training, annealed LR (.001 dropping to .00003) 99.76% mnist