SlideShare une entreprise Scribd logo
1  sur  31
RNN
Recurrent Neural
Network
By: M. Sabouri
ACRRL
Applied Control & Robotics Research Laboratory of
Shiraz University
Department of Power and Control Engineering, Shiraz University, Fars, Iran.
Recurrent Neural Network
A Recurrent Neural Network (RNN) is a class of artificial neural
network that has memory or feedback loops that allow it to better
recognize patterns in data.
• Recurrent neural network (RNN) is a neural network model
proposed in the 80’s for modelling time series.
RNNs are an extension of regular artificial neural networks that add connections
feeding the hidden layers of the neural network back into themselves - these are called
recurrent connections.
Recurrent Neural Network
The structure of the network is similar to feedforward neural network, with t
he distinction that it allows a recurrent hidden state whose activation at each
time is dependent on that of the previous time (cycle).
Recurrent Neural Network
• Recurrent networks, on the other hand, take as their input not just the current input exa
mple they see, but also what they have perceived previously in time.
• This enables RNNs to have improved accuracy compared to MLPs, which only have t
he single input and no memory, RNNs can take several prior input and extrapolate out
with improved accuracy. In other words, RNNs take into consideration what it has lear
ned from prior inputs to classify the current input.
Some Example of Recurrent
Neural Network
The beauty of recurrent neural networks lies in their diversity of applicati
on. When we are dealing with RNNs they have a great ability to deal wit
h various input and output types.
• Sentiment Classification
• Image Captioning
• Language Translation
Some example of Recurrent
Neural Network
Sentiment Classification
This can be a task of simply classifying tweets into positive and negative sentiment. So he
re the input would be a tweet of varying lengths, while output is of a fixed type and size.
Some Example of Recurrent
Neural Network
• Image Captioning
Here, let’s say we have an image for which we need a textual description. So we have a si
ngle input – the image, and a series or sequence of words as output. Here the image might
be of a fixed size, but the output is a description of varying lengths
Some Example of Recurrent
Neural Network
• Language Translation
This basically means that we have some text in a particular language let’s say English, an
d we wish to translate it in French. Each language has it’s own semantics and would have
varying lengths for the same sentence. So here the inputs as well as outputs are of varying
lengths.
Recurrent Neural Network
So RNNs can be used for mapping inputs to outputs of varying types, lengths and are fairly
generalized in their application. Looking at their applications
Where to use a RNN?
• Language Modelling and Generating Text
Given a sequence of word, here we try to predict the likelihood of the next wo
rd. This is useful for translation since the most likely sentence would be the on
e that is correct.
• Machine Translation
Translating text from one language to other uses one or the other form of RN
N. All practical day systems use some advanced version of a RNN.
• Speech Recognition
Predicting phonetic segments based on input sound waves, thus formulating a
word.
Where to use a RNN?
• Generating Image Descriptions
A very big use case is to understand what is happening inside an image, thus
we have a good description. This works in a combination of CNN and RNN. C
NN does the segmentation and RNN then used the segmented data to recreat
e the description. It’s rudimentary but the possibilities are limitless.
• Video Tagging
This can be used for video search where we do image description of a video fr
ame by frame.
RNN VS FNN
Feed-forward Neural Netwo
rk
Multilayer Perceptron (MLP
Recurrent Neural Network (RNN)
Recurrent Neural Network
Recurrent Neural Network (RNN), with additional feed-forward la
yer
Mathematical Formulation
Recurrent neural networks learn from sequences. A sequence is define
d as a list of (xi,yi) pairs, where xi is the input at time i and yi is the d
esired output. Note that that is a single sequence; the entire data set co
nsists of many sequences.
Mathematical Formulation
In addition to the data in our data set, each time step has another input: the hidden state hi−1
from the previous time step. In this way, the recurrent neural network can maintain some int
ernal context as it progresses forward in the sequence. Thus, to summarize, at time i the rec
urren
t network has:
• Input vector xi (data)
• Output vector yi (data)
• Predicted output vector y^i(computed through forward propagation)
• Hidden state hi
Mathematical Formulation
When looking only at a single timestep, the recurrent network looks like a simple one-hidden-
layer feed forward network. It has an input layer for xi, an output layer for yi, and another inp
ut layer for the previous hidden state hi−1. Finally, it has one hidden layer between these. The
only unusual thing is that we have two input layers; both of the input layers are are connected
to the hidden layer as if they were really just a single layer.
Thus, we have three separate matrices of weights:
• Input-to-hidden weights Whx
• Hidden-to-hidden weights Whh
• Hidden-to-output weights Wyh
Mathematical Formulation
There are several things to note here. First of all, note that the predicted outputs are not su
bject to the nonlinearity. We may want to predict things other than the things in the range
of the nonlinearity, so instead we do not apply the nonlinearity. For specific use cases of r
ecurrent nets, this can be amended, and a nonlinearity specific to the problem can be chos
en. Finally, note that these equations are the same as the equations for a single hidden lay
er feed forward network, with the caveat that the input layer is broken into two pieces xi a
nd hi−1.
Expanded figure of Recurrent
Neural Network
Expanded figure of Recurrent
Neural Network
Kind Of RNN
Jordan RNN
Pro: Fast to train because can be parallelized in time
Cons:
• Output transforms hidden state → nonlinear effects, information distorted
• The output dimension may be too small → information in hidden states is t
runcated
Elman RNN
Often referenced as the basic RNN structure and called “Vanilla” RNN
• Should see complete sequence to be trained
• Can not be parallelized by timestamps
• Has some important training difficulties….
Vanilla RNN
The Vanilla RNN Cell and Network
BackPropagation Refresher!
Multiple Laye
rs
Chain Rule for Gradient Computat
RNN Problem
However, conventional RNNs have a few limitations. They are difficult to train and have a
very short-term memory, which limits their functionality. To overcome the memory limitatio
n, a newer form of RNN, known as LSTM or Long Short-term Memory networks are used.
LSTMs extend the memory RNNs to enable them to perform tasks involving longer-term m
emory.
References
https://www.analyticsvidhya.com
https://www.allerin.com/
http://andrew.gibiansky.com/
http://corochann.com/
Thank you
Mohammad Sabouri
You can find me at m.sabouri@shirazu.ac.ir

Contenu connexe

Tendances

Sequence Modelling with Deep Learning
Sequence Modelling with Deep LearningSequence Modelling with Deep Learning
Sequence Modelling with Deep LearningNatasha Latysheva
 
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...Simplilearn
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryAndrii Gakhov
 
Recurrent neural networks rnn
Recurrent neural networks   rnnRecurrent neural networks   rnn
Recurrent neural networks rnnKuppusamy P
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM健程 杨
 
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...Simplilearn
 
RNN and its applications
RNN and its applicationsRNN and its applications
RNN and its applicationsSungjoon Choi
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
INTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUINTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUSri Geetha
 
Deep Belief Networks
Deep Belief NetworksDeep Belief Networks
Deep Belief NetworksHasan H Topcu
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNNAshray Bhandare
 
Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Larry Guo
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural NetworksAshray Bhandare
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 

Tendances (20)

Sequence Modelling with Deep Learning
Sequence Modelling with Deep LearningSequence Modelling with Deep Learning
Sequence Modelling with Deep Learning
 
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: Theory
 
Recurrent neural networks rnn
Recurrent neural networks   rnnRecurrent neural networks   rnn
Recurrent neural networks rnn
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM
 
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
 
RNN and its applications
RNN and its applicationsRNN and its applications
RNN and its applications
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
INTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUINTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRU
 
Deep Belief Networks
Deep Belief NetworksDeep Belief Networks
Deep Belief Networks
 
Lstm
LstmLstm
Lstm
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
 
Neural network
Neural networkNeural network
Neural network
 
Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10)
 
03 Single layer Perception Classifier
03 Single layer Perception Classifier03 Single layer Perception Classifier
03 Single layer Perception Classifier
 
LSTM Tutorial
LSTM TutorialLSTM Tutorial
LSTM Tutorial
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
Multi Layer Network
Multi Layer NetworkMulti Layer Network
Multi Layer Network
 
Hopfield Networks
Hopfield NetworksHopfield Networks
Hopfield Networks
 

Similaire à Recurrent Neural Network

Complete solution for Recurrent neural network.pptx
Complete solution for Recurrent neural network.pptxComplete solution for Recurrent neural network.pptx
Complete solution for Recurrent neural network.pptxArunKumar674066
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningJunaid Bhat
 
Convolutional Neural Network and RNN for OCR problem.
Convolutional Neural Network and RNN for OCR problem.Convolutional Neural Network and RNN for OCR problem.
Convolutional Neural Network and RNN for OCR problem.Vishal Mishra
 
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...Convolutional Neural Networks for Natural Language Processing / Stanford cs22...
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...changedaeoh
 
Engineering Intelligent NLP Applications Using Deep Learning – Part 2
Engineering Intelligent NLP Applications Using Deep Learning – Part 2 Engineering Intelligent NLP Applications Using Deep Learning – Part 2
Engineering Intelligent NLP Applications Using Deep Learning – Part 2 Saurabh Kaushik
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNNPradnya Saval
 
DEEPLEARNING recurrent neural networs.pdf
DEEPLEARNING recurrent neural networs.pdfDEEPLEARNING recurrent neural networs.pdf
DEEPLEARNING recurrent neural networs.pdfAamirMaqsood8
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningRADO7900
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & OpportunityiTrain
 
Lecture on Deep Learning
Lecture on Deep LearningLecture on Deep Learning
Lecture on Deep LearningYasas Senarath
 
Artificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisArtificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisAdityendra Kumar Singh
 
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...csandit
 
lepibwp74jd2rz.pdf
lepibwp74jd2rz.pdflepibwp74jd2rz.pdf
lepibwp74jd2rz.pdfSajalTyagi6
 
Neural networks of artificial intelligence
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligencealldesign
 
Applying Deep Learning Machine Translation to Language Services
Applying Deep Learning Machine Translation to Language ServicesApplying Deep Learning Machine Translation to Language Services
Applying Deep Learning Machine Translation to Language ServicesYannis Flet-Berliac
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
Convolution neural networks
Convolution neural networksConvolution neural networks
Convolution neural networksFares Hasan
 

Similaire à Recurrent Neural Network (20)

Complete solution for Recurrent neural network.pptx
Complete solution for Recurrent neural network.pptxComplete solution for Recurrent neural network.pptx
Complete solution for Recurrent neural network.pptx
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Convolutional Neural Network and RNN for OCR problem.
Convolutional Neural Network and RNN for OCR problem.Convolutional Neural Network and RNN for OCR problem.
Convolutional Neural Network and RNN for OCR problem.
 
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...Convolutional Neural Networks for Natural Language Processing / Stanford cs22...
Convolutional Neural Networks for Natural Language Processing / Stanford cs22...
 
Engineering Intelligent NLP Applications Using Deep Learning – Part 2
Engineering Intelligent NLP Applications Using Deep Learning – Part 2 Engineering Intelligent NLP Applications Using Deep Learning – Part 2
Engineering Intelligent NLP Applications Using Deep Learning – Part 2
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
 
DEEPLEARNING recurrent neural networs.pdf
DEEPLEARNING recurrent neural networs.pdfDEEPLEARNING recurrent neural networs.pdf
DEEPLEARNING recurrent neural networs.pdf
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Advanced Machine Learning
Advanced Machine LearningAdvanced Machine Learning
Advanced Machine Learning
 
Lec10new
Lec10newLec10new
Lec10new
 
lec10new.ppt
lec10new.pptlec10new.ppt
lec10new.ppt
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & Opportunity
 
Lecture on Deep Learning
Lecture on Deep LearningLecture on Deep Learning
Lecture on Deep Learning
 
Artificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisArtificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical Diagnosis
 
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...
EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORKS FOR ENGLISH-HINDI MACHINE ...
 
lepibwp74jd2rz.pdf
lepibwp74jd2rz.pdflepibwp74jd2rz.pdf
lepibwp74jd2rz.pdf
 
Neural networks of artificial intelligence
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligence
 
Applying Deep Learning Machine Translation to Language Services
Applying Deep Learning Machine Translation to Language ServicesApplying Deep Learning Machine Translation to Language Services
Applying Deep Learning Machine Translation to Language Services
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
Convolution neural networks
Convolution neural networksConvolution neural networks
Convolution neural networks
 

Plus de Mohammad Sabouri

Extremely low-cost lower limb prostheses_G12.pptx
Extremely low-cost lower limb prostheses_G12.pptxExtremely low-cost lower limb prostheses_G12.pptx
Extremely low-cost lower limb prostheses_G12.pptxMohammad Sabouri
 
MECHANICAL DESIGN METHODS IN ROBOTICS.pptx
MECHANICAL DESIGN METHODS IN ROBOTICS.pptxMECHANICAL DESIGN METHODS IN ROBOTICS.pptx
MECHANICAL DESIGN METHODS IN ROBOTICS.pptxMohammad Sabouri
 
Human Computer Interaction (HCI).pptx
Human Computer Interaction (HCI).pptxHuman Computer Interaction (HCI).pptx
Human Computer Interaction (HCI).pptxMohammad Sabouri
 
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptx
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptxIntelligent Decision Making Assistant (IDMA) for SAL improvement.pptx
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptxMohammad Sabouri
 
Introducing the services of Iran Patent Center- PDF
Introducing the services of Iran Patent Center- PDFIntroducing the services of Iran Patent Center- PDF
Introducing the services of Iran Patent Center- PDFMohammad Sabouri
 
Introduction to Lens database -in Persian (powerful site for searching)
Introduction to Lens database -in Persian (powerful site for searching)Introduction to Lens database -in Persian (powerful site for searching)
Introduction to Lens database -in Persian (powerful site for searching)Mohammad Sabouri
 
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...Mohammad Sabouri
 
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...Mohammad Sabouri
 
Traffic monitoring using drone_ACRRL_Shiraz University
Traffic monitoring using drone_ACRRL_Shiraz UniversityTraffic monitoring using drone_ACRRL_Shiraz University
Traffic monitoring using drone_ACRRL_Shiraz UniversityMohammad Sabouri
 
Labview2_Computer Applications in Control_ACRRL
Labview2_Computer Applications in Control_ACRRLLabview2_Computer Applications in Control_ACRRL
Labview2_Computer Applications in Control_ACRRLMohammad Sabouri
 
Labview1_ Computer Applications in Control_ACRRL
Labview1_ Computer Applications in Control_ACRRLLabview1_ Computer Applications in Control_ACRRL
Labview1_ Computer Applications in Control_ACRRLMohammad Sabouri
 
Spoofing attack on PMU (Phasor measurement unit)
Spoofing attack on PMU (Phasor measurement unit)Spoofing attack on PMU (Phasor measurement unit)
Spoofing attack on PMU (Phasor measurement unit)Mohammad Sabouri
 

Plus de Mohammad Sabouri (15)

Extremely low-cost lower limb prostheses_G12.pptx
Extremely low-cost lower limb prostheses_G12.pptxExtremely low-cost lower limb prostheses_G12.pptx
Extremely low-cost lower limb prostheses_G12.pptx
 
MECHANICAL DESIGN METHODS IN ROBOTICS.pptx
MECHANICAL DESIGN METHODS IN ROBOTICS.pptxMECHANICAL DESIGN METHODS IN ROBOTICS.pptx
MECHANICAL DESIGN METHODS IN ROBOTICS.pptx
 
Human Computer Interaction (HCI).pptx
Human Computer Interaction (HCI).pptxHuman Computer Interaction (HCI).pptx
Human Computer Interaction (HCI).pptx
 
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptx
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptxIntelligent Decision Making Assistant (IDMA) for SAL improvement.pptx
Intelligent Decision Making Assistant (IDMA) for SAL improvement.pptx
 
Introducing the services of Iran Patent Center- PDF
Introducing the services of Iran Patent Center- PDFIntroducing the services of Iran Patent Center- PDF
Introducing the services of Iran Patent Center- PDF
 
Introduction to Lens database -in Persian (powerful site for searching)
Introduction to Lens database -in Persian (powerful site for searching)Introduction to Lens database -in Persian (powerful site for searching)
Introduction to Lens database -in Persian (powerful site for searching)
 
CV_ nov.2019
CV_ nov.2019CV_ nov.2019
CV_ nov.2019
 
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...
Icbme2020- Use of neural network algorithms to predict arterial blood gas ite...
 
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...
Prediction of Arterial Blood Gases(ABG) by Using Neural Network In Trauma Pat...
 
Traffic monitoring using drone_ACRRL_Shiraz University
Traffic monitoring using drone_ACRRL_Shiraz UniversityTraffic monitoring using drone_ACRRL_Shiraz University
Traffic monitoring using drone_ACRRL_Shiraz University
 
Robotic introduction
Robotic introductionRobotic introduction
Robotic introduction
 
Labview2_Computer Applications in Control_ACRRL
Labview2_Computer Applications in Control_ACRRLLabview2_Computer Applications in Control_ACRRL
Labview2_Computer Applications in Control_ACRRL
 
Labview1_ Computer Applications in Control_ACRRL
Labview1_ Computer Applications in Control_ACRRLLabview1_ Computer Applications in Control_ACRRL
Labview1_ Computer Applications in Control_ACRRL
 
Spoofing attack on PMU (Phasor measurement unit)
Spoofing attack on PMU (Phasor measurement unit)Spoofing attack on PMU (Phasor measurement unit)
Spoofing attack on PMU (Phasor measurement unit)
 
Haptic technology ppt
Haptic technology pptHaptic technology ppt
Haptic technology ppt
 

Dernier

How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxnegromaestrong
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterMateoGardella
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...KokoStevan
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxAreebaZafar22
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Disha Kariya
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxDenish Jangid
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin ClassesCeline George
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfAyushMahapatra5
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 

Dernier (20)

How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
Advance Mobile Application Development class 07
Advance Mobile Application Development class 07Advance Mobile Application Development class 07
Advance Mobile Application Development class 07
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 

Recurrent Neural Network

  • 2. ACRRL Applied Control & Robotics Research Laboratory of Shiraz University Department of Power and Control Engineering, Shiraz University, Fars, Iran.
  • 3. Recurrent Neural Network A Recurrent Neural Network (RNN) is a class of artificial neural network that has memory or feedback loops that allow it to better recognize patterns in data. • Recurrent neural network (RNN) is a neural network model proposed in the 80’s for modelling time series. RNNs are an extension of regular artificial neural networks that add connections feeding the hidden layers of the neural network back into themselves - these are called recurrent connections.
  • 4. Recurrent Neural Network The structure of the network is similar to feedforward neural network, with t he distinction that it allows a recurrent hidden state whose activation at each time is dependent on that of the previous time (cycle).
  • 5. Recurrent Neural Network • Recurrent networks, on the other hand, take as their input not just the current input exa mple they see, but also what they have perceived previously in time. • This enables RNNs to have improved accuracy compared to MLPs, which only have t he single input and no memory, RNNs can take several prior input and extrapolate out with improved accuracy. In other words, RNNs take into consideration what it has lear ned from prior inputs to classify the current input.
  • 6. Some Example of Recurrent Neural Network The beauty of recurrent neural networks lies in their diversity of applicati on. When we are dealing with RNNs they have a great ability to deal wit h various input and output types. • Sentiment Classification • Image Captioning • Language Translation
  • 7. Some example of Recurrent Neural Network Sentiment Classification This can be a task of simply classifying tweets into positive and negative sentiment. So he re the input would be a tweet of varying lengths, while output is of a fixed type and size.
  • 8. Some Example of Recurrent Neural Network • Image Captioning Here, let’s say we have an image for which we need a textual description. So we have a si ngle input – the image, and a series or sequence of words as output. Here the image might be of a fixed size, but the output is a description of varying lengths
  • 9. Some Example of Recurrent Neural Network • Language Translation This basically means that we have some text in a particular language let’s say English, an d we wish to translate it in French. Each language has it’s own semantics and would have varying lengths for the same sentence. So here the inputs as well as outputs are of varying lengths.
  • 10. Recurrent Neural Network So RNNs can be used for mapping inputs to outputs of varying types, lengths and are fairly generalized in their application. Looking at their applications
  • 11. Where to use a RNN? • Language Modelling and Generating Text Given a sequence of word, here we try to predict the likelihood of the next wo rd. This is useful for translation since the most likely sentence would be the on e that is correct. • Machine Translation Translating text from one language to other uses one or the other form of RN N. All practical day systems use some advanced version of a RNN. • Speech Recognition Predicting phonetic segments based on input sound waves, thus formulating a word.
  • 12. Where to use a RNN? • Generating Image Descriptions A very big use case is to understand what is happening inside an image, thus we have a good description. This works in a combination of CNN and RNN. C NN does the segmentation and RNN then used the segmented data to recreat e the description. It’s rudimentary but the possibilities are limitless. • Video Tagging This can be used for video search where we do image description of a video fr ame by frame.
  • 13. RNN VS FNN Feed-forward Neural Netwo rk Multilayer Perceptron (MLP Recurrent Neural Network (RNN)
  • 14. Recurrent Neural Network Recurrent Neural Network (RNN), with additional feed-forward la yer
  • 15. Mathematical Formulation Recurrent neural networks learn from sequences. A sequence is define d as a list of (xi,yi) pairs, where xi is the input at time i and yi is the d esired output. Note that that is a single sequence; the entire data set co nsists of many sequences.
  • 16. Mathematical Formulation In addition to the data in our data set, each time step has another input: the hidden state hi−1 from the previous time step. In this way, the recurrent neural network can maintain some int ernal context as it progresses forward in the sequence. Thus, to summarize, at time i the rec urren t network has: • Input vector xi (data) • Output vector yi (data) • Predicted output vector y^i(computed through forward propagation) • Hidden state hi
  • 17. Mathematical Formulation When looking only at a single timestep, the recurrent network looks like a simple one-hidden- layer feed forward network. It has an input layer for xi, an output layer for yi, and another inp ut layer for the previous hidden state hi−1. Finally, it has one hidden layer between these. The only unusual thing is that we have two input layers; both of the input layers are are connected to the hidden layer as if they were really just a single layer. Thus, we have three separate matrices of weights: • Input-to-hidden weights Whx • Hidden-to-hidden weights Whh • Hidden-to-output weights Wyh
  • 18. Mathematical Formulation There are several things to note here. First of all, note that the predicted outputs are not su bject to the nonlinearity. We may want to predict things other than the things in the range of the nonlinearity, so instead we do not apply the nonlinearity. For specific use cases of r ecurrent nets, this can be amended, and a nonlinearity specific to the problem can be chos en. Finally, note that these equations are the same as the equations for a single hidden lay er feed forward network, with the caveat that the input layer is broken into two pieces xi a nd hi−1.
  • 19. Expanded figure of Recurrent Neural Network
  • 20. Expanded figure of Recurrent Neural Network
  • 22. Jordan RNN Pro: Fast to train because can be parallelized in time Cons: • Output transforms hidden state → nonlinear effects, information distorted • The output dimension may be too small → information in hidden states is t runcated
  • 23. Elman RNN Often referenced as the basic RNN structure and called “Vanilla” RNN • Should see complete sequence to be trained • Can not be parallelized by timestamps • Has some important training difficulties….
  • 25. The Vanilla RNN Cell and Network
  • 27. Multiple Laye rs Chain Rule for Gradient Computat
  • 28. RNN Problem However, conventional RNNs have a few limitations. They are difficult to train and have a very short-term memory, which limits their functionality. To overcome the memory limitatio n, a newer form of RNN, known as LSTM or Long Short-term Memory networks are used. LSTMs extend the memory RNNs to enable them to perform tasks involving longer-term m emory.
  • 31. Mohammad Sabouri You can find me at m.sabouri@shirazu.ac.ir