SlideShare a Scribd company logo
1 of 30
Download to read offline
Recurrent Neural Networks
Sang Jun Lee
Ph.D. candidate, POSTECH
Email: lsj4u0208@postech.ac.kr
EECE695J 전자전기공학특론J(딥러닝기초및철강공정에의활용) – LECTURE 7 (2017. 11. 10)
2
▣ Lecture 6: Convolutional Neural Network
1-page Review
Convolution layer Pooling layer
32x32x3 image
5x5x3 filter
Convolve (slide)
over all spatial
locations
Activation maps
Depth slice
Max pool with
2x2 filters and
stride 2
“Parameters are shared on
spatial domain”
3
Introduction to recurrent neural network
Vanilla neural network
h
𝑥
𝑦
𝑥𝑥
𝑥 : concatenated data of 𝑥 , 𝑥 , 𝑥 , ⋯
h
𝑥
y
𝑊
𝑊𝑊𝑊
𝑊 𝑊 ; 𝑊 ; 𝑊 ; ⋯
A naive idea for handling sequential data
 We usually want to predict a vector at a time step for a time domain data 𝑥
4
Introduction to recurrent neural network
ℎ
𝑥
𝑦
𝑥𝑥
ℎℎ
𝑊𝑊𝑊
𝑊𝑊𝑊
Recurrent neural network (RNN)
 Assume that
the relation between 𝑥 and 𝑥 is similar to the relation between 𝑥 and 𝑥
→ Parameter sharing for 𝑊
 Identical feature extraction from inputs
→ Parameter sharing for 𝑊
5
Introduction to recurrent neural network
ℎ
𝑥
𝑦
𝑥𝑥
ℎℎ
𝑊𝑊𝑊
𝑊𝑊
Recurrent neural network (RNN)
 Multiple copies of a same network (same function and same paramters)
 ℎ : a hidden state that consists of a vector
ℎ 𝑓 ℎ , 𝑥
ℎ tanh 𝑊 ⋅ ℎ 𝑊 ⋅ 𝑥
𝑦 𝑊 ⋅ ℎ
ℎ
Usually set to 0
Fully-
connected
layer
RNN cell
Input layer
Output layer
(RNN feature)
6
Introduction to recurrent neural network
Various architectures of RNN
 Flexibility for handling various types of data
Vanilla neural network
7
Introduction to recurrent neural network
Various architectures of RNN
 Flexibility for handling various types of data
e.g. machine translation
(sequence of words
→ sequence of words)
8
Introduction to recurrent neural network
Limitations of vanilla RNN
 Vanilla RNN works well for a small time step
 However, the sensitivity of the input values decays over time in a standard RNN
“the clouds are in the sky”
“I grew up in France
…
I speak fluent French.”
9
LSTM (long short-term memory)
 A standard RNN contains a single layer in the repeating module
10
LSTM (long short-term memory)
 A special kind of RNN for learning long-term dependencies
 Introduced by Hochreiter & Schmidhuber (1997)
11
LSTM (long short-term memory)
The key idea of LSTMs : cell state
 The cell state is kind of like a conveyor belt
12
LSTM (long short-term memory)
Forget gate
 LSTM have the ability to remove or add information to the cell state, carefully regulated by
structures call gates
 The decision what information we’re going to throw away from the cell state is made by a
sigmoid layer called forget gate layer
13
LSTM (long short-term memory)
Input gate layer
 Decide what new information we’re going to store in the cell state
 First, input gate layer decide which values we’ll update
 Next, tanh layer creates a vector of new candidate values
 Finally, combine two to create an update to the state
14
LSTM (long short-term memory)
Update
Output
Forget previous information
Add new information
Output is based on the cell state
15
LSTM (long short-term memory)
16
Variants of RNN
Gated Recurrent Unit (GRU)
 Combine the forget and input gates into a single update gate
 Merge the cell state and hidden state
17
Implementation of RNN
Manipulation of time series data
Split raw data into train, validation, and test dataset
def split_data(data, val_size=0.2, test_size=0.2):
ntest = int(round(len(data) * (1 ‐ test_size)))
nval = int(round(len(data.iloc[:ntest]) * (1 ‐ val_size)))
df_train, df_val, df_test = data.iloc[:nval], data.iloc[nval:ntest], 
data.iloc[ntest:]
return df_train, df_val, df_test
train, val, test = split_data(raw_data, val_size=0.2, test_size=0.2)
Raw data
(100%)
Train
(80%)
Validation
(20%)
Test
(20%)
18
Implementation of RNN
Manipulation of time series data
Generate sequence pair (x, y)
def rnn_data(data, time_steps, labels=False):
"""
creates new data frame based on previous observation
* example:
l = [1, 2, 3, 4, 5]
time_steps = 2
‐> labels == False [[1, 2], [2, 3], [3, 4]]
‐> labels == True [3, 4, 5]
"""
rnn_df = []
for i in range(len(data) ‐ time_steps):
if labels:
try:
rnn_df.append(data.iloc[i + time_steps].as_matrix())
except AttributeError:
rnn_df.append(data.iloc[i + time_steps])
else:
data_ = data.iloc[i: i + time_steps].as_matrix()
rnn_df.append(data_ if len(data_.shape) > 1 else [[i] for i in data_])
return np.array(rnn_df)
19
Implementation of RNN
Manipulation of time series data
Generate sequence pair (x, y)
time_steps = 10
train_x = rnn_data(df_train, time_steps, labels=false)
train_y = rnn_data(df_train, time_steps, labels=true)
Training data [1:10000]
x #01
[1, 2, 3, …,10]
y #01
11
…
…
x #02
[2, 3, 4, …,11]
y #02
12
x #9990
[9990, 9991, 9992, …,9999]
y #9990
10000
train_x
train_y
20
Implementation of RNN
Manipulation of time series data
Split each sample data
time_step = 10
x_split = tf.unpack(x_data, time_steps,1)
tf.unpack
1 2 3 10
𝑥 𝑥 𝑥 … 𝑥
…
x #01
[1, 2, 3, …,10]
Placeholder
21
Implementation of RNN
Choose a RNN cell
Connect input and recurrent layer
rnn_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units)
output, state = tf.nn.rnn(rnn_cell, x_split)
Import tensorflow as tf
num_units = 100
rnn_cell = tf.nn.rnn_cell.BasicRNNCell(num_units)
rnn_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units)
rnn_cell = tf.nn.rnn_cell.GRUCell(num_units)
22
Case study 1: MNIST classification
Hyper parameters for implementing a RNN
 Learning rate, training iteration, batch size, etc.
 Time step, the number of RNN neurons
Placeholder and variable tensor preparation
One-hot encoding 된 라벨
“Sequential processing of
non-sequence data”
23
Case study 1: MNIST classification
RNN cell 구성
28x28 sample을 28개의 28-dimensional vector로 split
Vanilla RNN: rnn.rnn_cell.BasicRNNCell
Output layer 구성
RNN cell의 neuron 개수
각 category에 속할 추정 확률
24
Case study 1: MNIST classification
Define loss and training operation
tf.Session()
Session을 열고 train_op run!
25
Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)
 예측 전략
• 일별 최대전력 수요 예측을 통한 하계 최대전력수요 예측
 알고리즘 개요
• 특별시 및 광역시의 평균 온도를 전력수요 비율로 weighted sum하여 일별 우리나라의 대표 기온 데이터 구성
• 과거 전력/기온데이터를 활용한 RNN/CNN 복합모델 기반의 일별 최대전력수요/기온 예측
• 전력수요 데이터의 특징인 요일과 계절에 따른 주기성을 반영하기 위한 딥러닝 알고리즘 개발
26
Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)
 RNN 구조의 학습을 위한 학습 데이터 구성
• 과거 28일간의 전력/온도데이터를 이용하여 향후 28일간의 전력/온도 예측
 Vanilla RNN model
Electricity (E)
Temperature (T)
Training data Test data
A training sample A label data
Time step Output dimension
Fully-connected layer
RNN cell
Input layer
𝑊
𝑊
𝑊
𝑊
𝐸
𝑇
𝑡𝑡 1
Output layer (→ RNN feature)
27
Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)
 Seasonal data
• 계절성을 학습에 반영하기 위한 데이터 구성
 계절성을 반영하기 위한 CNN model
Electricity (E)
Temperature (T)
1st sample of the training data
Time step (𝑡𝑠) Output dimension
𝑡𝑡 𝑇
𝑡 2𝑇
𝑡 3𝑇
𝑘 x 𝑡𝑠
𝑋
𝑋
𝑋
𝑋
𝑋
𝑋
2𝑘 x 𝑡𝑠
Convolution layer
(2 x 𝑡𝑠 x 1 x 𝐶𝑁𝑁 𝑑𝑒𝑝𝑡ℎ)
𝑘 x 𝐶𝑁𝑁 𝑑𝑒𝑝𝑡ℎ
Fully-connected layer
CNN feature
28
Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)
 RNN과 CNN의 복합 모델
 Training
• Total loss Loss Loss
• Backpropagation via Adam optimizer
CNN feature
(50)
RNN feature
(200)
Fully-connectedlayer
(100)
Outputlayer
Predicted electricity
Outputlayer
Predicted temperature
𝐿𝑜𝑠𝑠
𝐿𝑜𝑠𝑠
RNN cell
(200
Convolutionlayer
(2x28x1x200)
Convolutionlayer
(5x1x200x50)
(100)
Electricity &
Temperature
Seasonal data
29
Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)
 2017년 하계 최대 전력 수요 예측 결과: 86,477MW
(2017년도 하계 최대 전력 수요: 86,298MW, 오차: 0.21%)
 Back testing
• 2016.5.31 이전 데이터로 학습하여 2016.6.1 이후 데이터에 대하여 테스트
• Averaged error rate : 2.37%/2.81% (28-day/56-day prediction)
Introduction to recurrent neural network
- Properties of RNN: parameter sharing
- Various architectures
- Limitation
LSTM (long short-term memory)
- Components of LSTM
- Forget gate, input gate, update, output
Implementation of RNN
Case studies
- MNIST classification
- 2017 하계 최대전력수요 예측
30
Summary

More Related Content

What's hot

Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...
Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...
Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...Universitat Politècnica de Catalunya
 
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
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...Universitat Politècnica de Catalunya
 
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...Universitat Politècnica de Catalunya
 
RNN and its applications
RNN and its applicationsRNN and its applications
RNN and its applicationsSungjoon Choi
 
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
 
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlowLearning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlowAltoros
 
RNN & LSTM: Neural Network for Sequential Data
RNN & LSTM: Neural Network for Sequential DataRNN & LSTM: Neural Network for Sequential Data
RNN & LSTM: Neural Network for Sequential DataYao-Chieh Hu
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term MemoryYan Xu
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM健程 杨
 
Recent Progress in RNN and NLP
Recent Progress in RNN and NLPRecent Progress in RNN and NLP
Recent Progress in RNN and NLPhytae
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep LearningOswald Campesato
 
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)Universitat Politècnica de Catalunya
 

What's hot (20)

Rnn & Lstm
Rnn & LstmRnn & Lstm
Rnn & Lstm
 
Multidimensional RNN
Multidimensional RNNMultidimensional RNN
Multidimensional RNN
 
Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...
Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...
Recurrent Neural Networks I (D2L2 Deep Learning for Speech and Language UPC 2...
 
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)
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...
Recurrent Neural Networks (DLAI D7L1 2017 UPC Deep Learning for Artificial In...
 
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...
Recurrent Neural Networks II (D2L3 Deep Learning for Speech and Language UPC ...
 
RNN and its applications
RNN and its applicationsRNN and its applications
RNN and its applications
 
Lstm
LstmLstm
Lstm
 
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...
 
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
 
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlowLearning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
 
RNN & LSTM: Neural Network for Sequential Data
RNN & LSTM: Neural Network for Sequential DataRNN & LSTM: Neural Network for Sequential Data
RNN & LSTM: Neural Network for Sequential Data
 
LSTM
LSTMLSTM
LSTM
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term Memory
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM
 
Recent Progress in RNN and NLP
Recent Progress in RNN and NLPRecent Progress in RNN and NLP
Recent Progress in RNN and NLP
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep Learning
 
LSTM Tutorial
LSTM TutorialLSTM Tutorial
LSTM Tutorial
 
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)
Unsupervised Learning (D2L6 2017 UPC Deep Learning for Computer Vision)
 

Similar to Lecture 7: Recurrent Neural Networks

Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningJunaid Bhat
 
Multi-Layer Perceptrons
Multi-Layer PerceptronsMulti-Layer Perceptrons
Multi-Layer PerceptronsESCOM
 
Artificial Intelligence Applications in Petroleum Engineering - Part I
Artificial Intelligence Applications in Petroleum Engineering - Part IArtificial Intelligence Applications in Petroleum Engineering - Part I
Artificial Intelligence Applications in Petroleum Engineering - Part IRamez Abdalla, M.Sc
 
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020Universitat Politècnica de Catalunya
 
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience hirokazutanaka
 
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...iosrjce
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningCastLabKAIST
 
Anomaly detection using deep one class classifier
Anomaly detection using deep one class classifierAnomaly detection using deep one class classifier
Anomaly detection using deep one class classifier홍배 김
 
14889574 dl ml RNN Deeplearning MMMm.ppt
14889574 dl ml RNN Deeplearning MMMm.ppt14889574 dl ml RNN Deeplearning MMMm.ppt
14889574 dl ml RNN Deeplearning MMMm.pptManiMaran230751
 
A Hybrid Deep Neural Network Model For Time Series Forecasting
A Hybrid Deep Neural Network Model For Time Series ForecastingA Hybrid Deep Neural Network Model For Time Series Forecasting
A Hybrid Deep Neural Network Model For Time Series ForecastingMartha Brown
 
RNN and LSTM model description and working advantages and disadvantages
RNN and LSTM model description and working advantages and disadvantagesRNN and LSTM model description and working advantages and disadvantages
RNN and LSTM model description and working advantages and disadvantagesAbhijitVenkatesh1
 
Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3TOMMYLINK1
 
Machine Learning Algorithms (Part 1)
Machine Learning Algorithms (Part 1)Machine Learning Algorithms (Part 1)
Machine Learning Algorithms (Part 1)Zihui Li
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningRADO7900
 
Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...SungminYou
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & OpportunityiTrain
 
ANN based STLF of Power System
ANN based STLF of Power SystemANN based STLF of Power System
ANN based STLF of Power SystemYousuf Khan
 

Similar to Lecture 7: Recurrent Neural Networks (20)

Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Multi-Layer Perceptrons
Multi-Layer PerceptronsMulti-Layer Perceptrons
Multi-Layer Perceptrons
 
Artificial Intelligence Applications in Petroleum Engineering - Part I
Artificial Intelligence Applications in Petroleum Engineering - Part IArtificial Intelligence Applications in Petroleum Engineering - Part I
Artificial Intelligence Applications in Petroleum Engineering - Part I
 
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
 
tutorial.ppt
tutorial.ppttutorial.ppt
tutorial.ppt
 
H017376369
H017376369H017376369
H017376369
 
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
Nn devs
Nn devsNn devs
Nn devs
 
Anomaly detection using deep one class classifier
Anomaly detection using deep one class classifierAnomaly detection using deep one class classifier
Anomaly detection using deep one class classifier
 
14889574 dl ml RNN Deeplearning MMMm.ppt
14889574 dl ml RNN Deeplearning MMMm.ppt14889574 dl ml RNN Deeplearning MMMm.ppt
14889574 dl ml RNN Deeplearning MMMm.ppt
 
A Hybrid Deep Neural Network Model For Time Series Forecasting
A Hybrid Deep Neural Network Model For Time Series ForecastingA Hybrid Deep Neural Network Model For Time Series Forecasting
A Hybrid Deep Neural Network Model For Time Series Forecasting
 
RNN and LSTM model description and working advantages and disadvantages
RNN and LSTM model description and working advantages and disadvantagesRNN and LSTM model description and working advantages and disadvantages
RNN and LSTM model description and working advantages and disadvantages
 
Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3
 
Machine Learning Algorithms (Part 1)
Machine Learning Algorithms (Part 1)Machine Learning Algorithms (Part 1)
Machine Learning Algorithms (Part 1)
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & Opportunity
 
ANN based STLF of Power System
ANN based STLF of Power SystemANN based STLF of Power System
ANN based STLF of Power System
 

More from Sang Jun Lee

[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation
[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation
[5분 논문요약] Structured Knowledge Distillation for Semantic SegmentationSang Jun Lee
 
Lecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksLecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksSang Jun Lee
 
Lecture 5: Neural Networks II
Lecture 5: Neural Networks IILecture 5: Neural Networks II
Lecture 5: Neural Networks IISang Jun Lee
 
Lecture 4: Neural Networks I
Lecture 4: Neural Networks ILecture 4: Neural Networks I
Lecture 4: Neural Networks ISang Jun Lee
 
Lecture 3: Unsupervised Learning
Lecture 3: Unsupervised LearningLecture 3: Unsupervised Learning
Lecture 3: Unsupervised LearningSang Jun Lee
 
Lecture 2: Supervised Learning
Lecture 2: Supervised LearningLecture 2: Supervised Learning
Lecture 2: Supervised LearningSang Jun Lee
 
Lecture 1: Introduction to Python and TensorFlow
Lecture 1: Introduction to Python and TensorFlowLecture 1: Introduction to Python and TensorFlow
Lecture 1: Introduction to Python and TensorFlowSang Jun Lee
 

More from Sang Jun Lee (7)

[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation
[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation
[5분 논문요약] Structured Knowledge Distillation for Semantic Segmentation
 
Lecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksLecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural Networks
 
Lecture 5: Neural Networks II
Lecture 5: Neural Networks IILecture 5: Neural Networks II
Lecture 5: Neural Networks II
 
Lecture 4: Neural Networks I
Lecture 4: Neural Networks ILecture 4: Neural Networks I
Lecture 4: Neural Networks I
 
Lecture 3: Unsupervised Learning
Lecture 3: Unsupervised LearningLecture 3: Unsupervised Learning
Lecture 3: Unsupervised Learning
 
Lecture 2: Supervised Learning
Lecture 2: Supervised LearningLecture 2: Supervised Learning
Lecture 2: Supervised Learning
 
Lecture 1: Introduction to Python and TensorFlow
Lecture 1: Introduction to Python and TensorFlowLecture 1: Introduction to Python and TensorFlow
Lecture 1: Introduction to Python and TensorFlow
 

Recently uploaded

Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girlsssuser7cb4ff
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort servicejennyeacort
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .Satyam Kumar
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxbritheesh05
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidNikhilNagaraju
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile servicerehmti665
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineeringmalavadedarshan25
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVRajaP95
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfAsst.prof M.Gokilavani
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
Heart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxHeart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxPoojaBan
 

Recently uploaded (20)

young call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Serviceyoung call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Service
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girls
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptx
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfid
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile service
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineering
 
Design and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdfDesign and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdf
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
Heart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxHeart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptx
 

Lecture 7: Recurrent Neural Networks

  • 1. Recurrent Neural Networks Sang Jun Lee Ph.D. candidate, POSTECH Email: lsj4u0208@postech.ac.kr EECE695J 전자전기공학특론J(딥러닝기초및철강공정에의활용) – LECTURE 7 (2017. 11. 10)
  • 2. 2 ▣ Lecture 6: Convolutional Neural Network 1-page Review Convolution layer Pooling layer 32x32x3 image 5x5x3 filter Convolve (slide) over all spatial locations Activation maps Depth slice Max pool with 2x2 filters and stride 2 “Parameters are shared on spatial domain”
  • 3. 3 Introduction to recurrent neural network Vanilla neural network h 𝑥 𝑦 𝑥𝑥 𝑥 : concatenated data of 𝑥 , 𝑥 , 𝑥 , ⋯ h 𝑥 y 𝑊 𝑊𝑊𝑊 𝑊 𝑊 ; 𝑊 ; 𝑊 ; ⋯ A naive idea for handling sequential data  We usually want to predict a vector at a time step for a time domain data 𝑥
  • 4. 4 Introduction to recurrent neural network ℎ 𝑥 𝑦 𝑥𝑥 ℎℎ 𝑊𝑊𝑊 𝑊𝑊𝑊 Recurrent neural network (RNN)  Assume that the relation between 𝑥 and 𝑥 is similar to the relation between 𝑥 and 𝑥 → Parameter sharing for 𝑊  Identical feature extraction from inputs → Parameter sharing for 𝑊
  • 5. 5 Introduction to recurrent neural network ℎ 𝑥 𝑦 𝑥𝑥 ℎℎ 𝑊𝑊𝑊 𝑊𝑊 Recurrent neural network (RNN)  Multiple copies of a same network (same function and same paramters)  ℎ : a hidden state that consists of a vector ℎ 𝑓 ℎ , 𝑥 ℎ tanh 𝑊 ⋅ ℎ 𝑊 ⋅ 𝑥 𝑦 𝑊 ⋅ ℎ ℎ Usually set to 0 Fully- connected layer RNN cell Input layer Output layer (RNN feature)
  • 6. 6 Introduction to recurrent neural network Various architectures of RNN  Flexibility for handling various types of data Vanilla neural network
  • 7. 7 Introduction to recurrent neural network Various architectures of RNN  Flexibility for handling various types of data e.g. machine translation (sequence of words → sequence of words)
  • 8. 8 Introduction to recurrent neural network Limitations of vanilla RNN  Vanilla RNN works well for a small time step  However, the sensitivity of the input values decays over time in a standard RNN “the clouds are in the sky” “I grew up in France … I speak fluent French.”
  • 9. 9 LSTM (long short-term memory)  A standard RNN contains a single layer in the repeating module
  • 10. 10 LSTM (long short-term memory)  A special kind of RNN for learning long-term dependencies  Introduced by Hochreiter & Schmidhuber (1997)
  • 11. 11 LSTM (long short-term memory) The key idea of LSTMs : cell state  The cell state is kind of like a conveyor belt
  • 12. 12 LSTM (long short-term memory) Forget gate  LSTM have the ability to remove or add information to the cell state, carefully regulated by structures call gates  The decision what information we’re going to throw away from the cell state is made by a sigmoid layer called forget gate layer
  • 13. 13 LSTM (long short-term memory) Input gate layer  Decide what new information we’re going to store in the cell state  First, input gate layer decide which values we’ll update  Next, tanh layer creates a vector of new candidate values  Finally, combine two to create an update to the state
  • 14. 14 LSTM (long short-term memory) Update Output Forget previous information Add new information Output is based on the cell state
  • 16. 16 Variants of RNN Gated Recurrent Unit (GRU)  Combine the forget and input gates into a single update gate  Merge the cell state and hidden state
  • 17. 17 Implementation of RNN Manipulation of time series data Split raw data into train, validation, and test dataset def split_data(data, val_size=0.2, test_size=0.2): ntest = int(round(len(data) * (1 ‐ test_size))) nval = int(round(len(data.iloc[:ntest]) * (1 ‐ val_size))) df_train, df_val, df_test = data.iloc[:nval], data.iloc[nval:ntest],  data.iloc[ntest:] return df_train, df_val, df_test train, val, test = split_data(raw_data, val_size=0.2, test_size=0.2) Raw data (100%) Train (80%) Validation (20%) Test (20%)
  • 18. 18 Implementation of RNN Manipulation of time series data Generate sequence pair (x, y) def rnn_data(data, time_steps, labels=False): """ creates new data frame based on previous observation * example: l = [1, 2, 3, 4, 5] time_steps = 2 ‐> labels == False [[1, 2], [2, 3], [3, 4]] ‐> labels == True [3, 4, 5] """ rnn_df = [] for i in range(len(data) ‐ time_steps): if labels: try: rnn_df.append(data.iloc[i + time_steps].as_matrix()) except AttributeError: rnn_df.append(data.iloc[i + time_steps]) else: data_ = data.iloc[i: i + time_steps].as_matrix() rnn_df.append(data_ if len(data_.shape) > 1 else [[i] for i in data_]) return np.array(rnn_df)
  • 19. 19 Implementation of RNN Manipulation of time series data Generate sequence pair (x, y) time_steps = 10 train_x = rnn_data(df_train, time_steps, labels=false) train_y = rnn_data(df_train, time_steps, labels=true) Training data [1:10000] x #01 [1, 2, 3, …,10] y #01 11 … … x #02 [2, 3, 4, …,11] y #02 12 x #9990 [9990, 9991, 9992, …,9999] y #9990 10000 train_x train_y
  • 20. 20 Implementation of RNN Manipulation of time series data Split each sample data time_step = 10 x_split = tf.unpack(x_data, time_steps,1) tf.unpack 1 2 3 10 𝑥 𝑥 𝑥 … 𝑥 … x #01 [1, 2, 3, …,10] Placeholder
  • 21. 21 Implementation of RNN Choose a RNN cell Connect input and recurrent layer rnn_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units) output, state = tf.nn.rnn(rnn_cell, x_split) Import tensorflow as tf num_units = 100 rnn_cell = tf.nn.rnn_cell.BasicRNNCell(num_units) rnn_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units) rnn_cell = tf.nn.rnn_cell.GRUCell(num_units)
  • 22. 22 Case study 1: MNIST classification Hyper parameters for implementing a RNN  Learning rate, training iteration, batch size, etc.  Time step, the number of RNN neurons Placeholder and variable tensor preparation One-hot encoding 된 라벨 “Sequential processing of non-sequence data”
  • 23. 23 Case study 1: MNIST classification RNN cell 구성 28x28 sample을 28개의 28-dimensional vector로 split Vanilla RNN: rnn.rnn_cell.BasicRNNCell Output layer 구성 RNN cell의 neuron 개수 각 category에 속할 추정 확률
  • 24. 24 Case study 1: MNIST classification Define loss and training operation tf.Session() Session을 열고 train_op run!
  • 25. 25 Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)  예측 전략 • 일별 최대전력 수요 예측을 통한 하계 최대전력수요 예측  알고리즘 개요 • 특별시 및 광역시의 평균 온도를 전력수요 비율로 weighted sum하여 일별 우리나라의 대표 기온 데이터 구성 • 과거 전력/기온데이터를 활용한 RNN/CNN 복합모델 기반의 일별 최대전력수요/기온 예측 • 전력수요 데이터의 특징인 요일과 계절에 따른 주기성을 반영하기 위한 딥러닝 알고리즘 개발
  • 26. 26 Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)  RNN 구조의 학습을 위한 학습 데이터 구성 • 과거 28일간의 전력/온도데이터를 이용하여 향후 28일간의 전력/온도 예측  Vanilla RNN model Electricity (E) Temperature (T) Training data Test data A training sample A label data Time step Output dimension Fully-connected layer RNN cell Input layer 𝑊 𝑊 𝑊 𝑊 𝐸 𝑇 𝑡𝑡 1 Output layer (→ RNN feature)
  • 27. 27 Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)  Seasonal data • 계절성을 학습에 반영하기 위한 데이터 구성  계절성을 반영하기 위한 CNN model Electricity (E) Temperature (T) 1st sample of the training data Time step (𝑡𝑠) Output dimension 𝑡𝑡 𝑇 𝑡 2𝑇 𝑡 3𝑇 𝑘 x 𝑡𝑠 𝑋 𝑋 𝑋 𝑋 𝑋 𝑋 2𝑘 x 𝑡𝑠 Convolution layer (2 x 𝑡𝑠 x 1 x 𝐶𝑁𝑁 𝑑𝑒𝑝𝑡ℎ) 𝑘 x 𝐶𝑁𝑁 𝑑𝑒𝑝𝑡ℎ Fully-connected layer CNN feature
  • 28. 28 Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)  RNN과 CNN의 복합 모델  Training • Total loss Loss Loss • Backpropagation via Adam optimizer CNN feature (50) RNN feature (200) Fully-connectedlayer (100) Outputlayer Predicted electricity Outputlayer Predicted temperature 𝐿𝑜𝑠𝑠 𝐿𝑜𝑠𝑠 RNN cell (200 Convolutionlayer (2x28x1x200) Convolutionlayer (5x1x200x50) (100) Electricity & Temperature Seasonal data
  • 29. 29 Case study 2 (2017년도 하계 최대전력수요 예측, 대한전기학회)  2017년 하계 최대 전력 수요 예측 결과: 86,477MW (2017년도 하계 최대 전력 수요: 86,298MW, 오차: 0.21%)  Back testing • 2016.5.31 이전 데이터로 학습하여 2016.6.1 이후 데이터에 대하여 테스트 • Averaged error rate : 2.37%/2.81% (28-day/56-day prediction)
  • 30. Introduction to recurrent neural network - Properties of RNN: parameter sharing - Various architectures - Limitation LSTM (long short-term memory) - Components of LSTM - Forget gate, input gate, update, output Implementation of RNN Case studies - MNIST classification - 2017 하계 최대전력수요 예측 30 Summary