Social Computing and Big Data Analytics 社群運算與大數據分析

Slides:



Advertisements
Similar presentations
Social Media Marketing Research 社會媒體行銷研究 SMMR08 TMIXM1A Thu 7,8 (14:10-16:00) L511 Exploratory Factor Analysis Min-Yuh Day 戴敏育 Assistant Professor.
Advertisements

Case Study for Information Management 資訊管理個案
Social Media Marketing Analytics 社群網路行銷分析 SMMA02 TLMXJ1A (MIS EMBA) Fri 12,13,14 (19:20-22:10) D326 社群網路行銷分析 (Social Media Marketing Analytics) Min-Yuh.
FGU LDT. FGU EIS 96 ‧ 8 ‧ 25 FGU LDT 佛光大學學習與數位科技學系.
大華技術學院九十五學年度 資工系計算機概論教學大綱 吳弘翔. Wu Hung-Hsiang2 科目名稱:計算機概論與實習 授課老師:吳弘翔 學分數: 4 修別:必修 老師信箱:
報告人:陳錦生 校長 日 期: 99 年 10 月 21 日. 自我評鑑報告內容簡介 校務評鑑五大項目 自我評鑑過程 簡述自我評鑑過程 學校現況 校地、教職員生數、圖書冊數、院系所學位學程.
商業智慧實務 Practices of Business Intelligence BI04 MI4 Wed, 9,10 (16:10-18:00) (B113) 資料倉儲 (Data Warehousing) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授.
Case Study for Information Management 資訊管理個案
Social Media Marketing Research 社會媒體行銷研究 SMMR01 TMIXM1A Thu 7,8 (14:10-16:00) U505 Course Orientation for Social Media Marketing Research Min-Yuh.
Social Media Marketing Research 社會媒體行銷研究 SMMR06 TMIXM1A Thu 7,8 (14:10-16:00) L511 Measuring the Construct Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授.
企業網路系統研究 (Enterprise Networking Systems Research) (VMware vSphere) VM01 MI4 Thu 9,10 (16:10-18:00) (B310) Course Introduction ( 課程介紹 ) Min-Yuh Day.
社會媒體服務專題 Special Topics in Social Media Services 淡江大學 淡江大學 資訊管理學系 資訊管理學系 Dept. of Information ManagementDept. of Information Management, Tamkang UniversityTamkang.
Social Media Marketing 社群網路行銷 SMM09 TLMXJ1A (MIS EMBA) Mon 12,13,14 (19:20-22:10) D504 行動 APP 行銷 (Mobile Apps Marketing) Min-Yuh Day 戴敏育 Assistant.
Web Mining ( 網路探勘 ) WM12 TLMXM1A Wed 8,9 (15:10-17:00) U705 Web Usage Mining ( 網路使用挖掘 ) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information.
Social Media Marketing Management 社會媒體行銷管理 SMMM06 TLMXJ1A Tue 12,13,14 (19:20-22:10) D325 行銷理論 (Marketing Theories) Min-Yuh Day 戴敏育 Assistant Professor.
Business Intelligence Trends 商業智慧趨勢 BIT08 MIS MBA Mon 6, 7 (13:10-15:00) Q407 商業智慧導入與趨勢 (Business Intelligence Implementation and Trends) Min-Yuh.
Social Media Management 社會媒體管理 SMM06 TMIXM1A Fri. 7,8 (14:10-16:00) L215 Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information Management,
Social Media Management 社會媒體管理 SMM01 TMIXM1A Fri. 7,8 (14:10-16:00) L215 Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information Management,
Social Media Marketing Management 社會媒體行銷管理
Social Media Marketing 社群網路行銷 SMM05 TLMXJ1A (MIS EMBA) Mon 12,13,14 (19:20-22:10) D504 社群網路行銷蜻蜓效應 (The Dragonfly Effect of Social Media Marketing)
Case Study for Information Management 資訊管理個案 CSIM4B07 TLMXB4B (M1824) Tue 2, 3, 4 (9:10-12:00) B502 Telecommunications, the Internet, and Wireless.
Social Media Marketing 社群網路行銷 SMM08 TLMXJ1A (MIS EMBA) Mon 12,13,14 (19:20-22:10) D504 社群網路行銷計劃 (Social Media Marketing Plan) Min-Yuh Day 戴敏育 Assistant.
Special Topics in Social Media Services 社會媒體服務專題 1 992SMS07 TMIXJ1A Sat. 6,7,8 (13:10-16:00) D502 Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information.
Data Mining 資料探勘 Introduction to Data Mining 資料探勘導論 Min-Yuh Day 戴敏育
商業智慧實務 Practices of Business Intelligence BI01 MI4 Wed, 9,10 (16:10-18:00) (B113) 商業智慧導論 (Introduction to Business Intelligence) Min-Yuh Day 戴敏育.
Social Media Marketing Management 社會媒體行銷管理 SMMM12 TLMXJ1A Tue 12,13,14 (19:20-22:10) D325 確認性因素分析 (Confirmatory Factor Analysis) Min-Yuh Day 戴敏育.
Social Media Marketing Analytics 社群網路行銷分析 SMMA04 TLMXJ1A (MIS EMBA) Fri 12,13,14 (19:20-22:10) D326 測量構念 (Measuring the Construct) Min-Yuh Day 戴敏育.
Case Study for Information Management 資訊管理個案 CSIM4C02 TLMXB4C (M1824) Tue 2, 3, 4 (9:10-12:00) B425 Information Systems in Global Business: UPS (Chap.
商業智慧實務 Practices of Business Intelligence BI06 MI4 Wed, 9,10 (16:10-18:00) (B130) 資料科學與巨量資料分析 (Data Science and Big Data Analytics) Min-Yuh Day 戴敏育.
Social Media Marketing Research 社會媒體行銷研究 SMMR09 TMIXM1A Thu 7,8 (14:10-16:00) L511 Confirmatory Factor Analysis Min-Yuh Day 戴敏育 Assistant Professor.
Data Mining 資料探勘 DM04 MI4 Thu 9, 10 (16:10-18:00) B216 分群分析 (Cluster Analysis) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information Management,
Case Study for Information Management 資訊管理個案 CSIM4B08 TLMXB4B Thu 8, 9, 10 (15:10-18:00) B508 Securing Information System: 1. Facebook, 2. European.
Case Study for Information Management 資訊管理個案 CSIM4B03 TLMXB4B (M1824) Tue 3,4 (10:10-12:00) L212 Thu 9 (16:10-17:00) B601 Global E-Business and Collaboration:
Case Study for Information Management 資訊管理個案
商業智慧實務 Practices of Business Intelligence BI01 MI4 Wed, 9,10 (16:10-18:00) (B130) 商業智慧導論 (Introduction to Business Intelligence) Min-Yuh Day 戴敏育.
Social Media Marketing Management 社會媒體行銷管理
Social Media Marketing 社群網路行銷 SMM02 TLMXJ1A (MIS EMBA) Mon 12,13,14 (19:20-22:10) D504 社群網路商業模式 (Business Models of Social Media) Min-Yuh Day 戴敏育.
商業智慧實務 Practices of Business Intelligence
Business Intelligence Trends 商業智慧趨勢 BIT01 MIS MBA Mon 6, 7 (13:10-15:00) Q407 Course Orientation for Business Intelligence Trends 商業智慧趨勢課程介紹 Min-Yuh.
Data Mining 資料探勘 DM04 MI4 Wed, 6,7 (13:10-15:00) (B216) 分群分析 (Cluster Analysis) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information Management,
Social Media Marketing Management 社會媒體行銷管理 SMMM01 TLMXJ1A Tue 12,13,14 (19:20-22:10) D325 Course Orientation of Social Media Marketing Management.
Web Mining ( 網路探勘 ) WM06 TLMXM1A Wed 8,9 (15:10-17:00) U705 Information Retrieval and Web Search ( 資訊檢索與網路搜尋 ) Min-Yuh Day 戴敏育 Assistant Professor.
Social Media Marketing Research 社會媒體行銷研究 SMMR04 TMIXM1A Thu 7,8 (14:10-16:00) L511 Marketing Research Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授.
Data Mining 資料探勘 DM01 MI4 Wed, 6,7 (13:10-15:00) (B216) Introduction to Data Mining ( 資料探勘導論 ) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of.
Data Mining 資料探勘 Introduction to Data Mining (資料探勘導論) Min-Yuh Day 戴敏育
Case Study for Information Management 資訊管理個案
Big Data Mining 巨量資料探勘 DM01 MI4 (M2244) (3094) Tue, 3, 4 (10:10-12:00) (B216) Course Orientation for Big Data Mining ( 巨量資料探勘課程介紹 ) Min-Yuh Day 戴敏育.
Social Computing and Big Data Analytics 社群運算與大數據分析
巨量資料基礎: MapReduce典範、Hadoop與Spark生態系統
社群網路行銷管理 Social Media Marketing Management SMMM01 MIS EMBA (M2200) (8615) Thu, 12,13,14 (19:20-22:10) (D309) 社群網路行銷管理課程介紹 (Course Orientation for.
Social Computing and Big Data Analytics 社群運算與大數據分析
Social Computing and Big Data Analytics 社群運算與大數據分析 SCBDA02 MIS MBA (M2226) (8628) Wed, 8,9, (15:10-17:00) (Q201) Data Science and Big Data Analytics:
Social Computing and Big Data Analytics 社群運算與大數據分析 SCBDA06 MIS MBA (M2226) (8628) Wed, 8,9, (15:10-17:00) (B309) Finance Big Data Analytics with.
社群網路行銷管理 Social Media Marketing Management SMMM02 MIS EMBA (M2200) (8615) Thu, 12,13,14 (19:20-22:10) (D309) 社群網路商業模式 (Business Models of Social.
Social Computing and Big Data Analytics 社群運算與大數據分析 SCBDA10 MIS MBA (M2226) (8628) Wed, 8,9, (15:10-17:00) (B309) Deep Learning with Google TensorFlow.
Social Computing and Big Data Analytics 社群運算與大數據分析 SCBDA05 MIS MBA (M2226) (8628) Wed, 8,9, (15:10-17:00) (B309) Big Data Analytics with Numpy in.
社群網路行銷管理 Social Media Marketing Management SMMM03 MIS EMBA (M2200) (8615) Thu, 12,13,14 (19:20-22:10) (D309) 顧客價值與品牌 (Customer Value and Branding)
Social Computing and Big Data Analytics 社群運算與大數據分析
Big Data Mining 巨量資料探勘 DM05 MI4 (M2244) (3094) Tue, 3, 4 (10:10-12:00) (B216) 分群分析 (Cluster Analysis) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授.
巨量資料基礎: MapReduce典範、Hadoop與Spark生態系統
Social Computing and Big Data Analytics 社群運算與大數據分析
Social Computing and Big Data Analytics 社群運算與大數據分析
Social Computing and Big Data Analytics 社群運算與大數據分析
Social Computing and Big Data Analytics 社群運算與大數據分析
Course Orientation for Big Data Mining (巨量資料探勘課程介紹)
Case Study for Information Management 資訊管理個案
分群分析 (Cluster Analysis)
大數據行銷研究 Big Data Marketing Research
商業智慧實務 Practices of Business Intelligence
Case Study for Information Management 資訊管理個案
Presentation transcript:

Social Computing and Big Data Analytics 社群運算與大數據分析 Tamkang University Social Computing and Big Data Analytics 社群運算與大數據分析 Tamkang University Deep Learning with Theano and Keras in Python (Python Theano 和 Keras 深度學習) 1042SCBDA09 MIS MBA (M2226) (8628) Wed, 8,9, (15:10-17:00) (B309) Min-Yuh Day 戴敏育 Assistant Professor 專任助理教授 Dept. of Information Management, Tamkang University 淡江大學 資訊管理學系 http://mail. tku.edu.tw/myday/ 2016-04-27

課程大綱 (Syllabus) 週次 (Week) 日期 (Date) 內容 (Subject/Topics) 1 2016/02/17 Course Orientation for Social Computing and Big Data Analytics (社群運算與大數據分析課程介紹) 2 2016/02/24 Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data (資料科學與大數據分析: 探索、分析、視覺化與呈現資料) 3 2016/03/02 Fundamental Big Data: MapReduce Paradigm, Hadoop and Spark Ecosystem (大數據基礎:MapReduce典範、 Hadoop與Spark生態系統)

課程大綱 (Syllabus) 週次 (Week) 日期 (Date) 內容 (Subject/Topics) 4 2016/03/09 Big Data Processing Platforms with SMACK: Spark, Mesos, Akka, Cassandra and Kafka (大數據處理平台SMACK: Spark, Mesos, Akka, Cassandra, Kafka) 5 2016/03/16 Big Data Analytics with Numpy in Python (Python Numpy 大數據分析) 6 2016/03/23 Finance Big Data Analytics with Pandas in Python (Python Pandas 財務大數據分析) 7 2016/03/30 Text Mining Techniques and Natural Language Processing (文字探勘分析技術與自然語言處理) 8 2016/04/06 Off-campus study (教學行政觀摩日)

課程大綱 (Syllabus) 週次 (Week) 日期 (Date) 內容 (Subject/Topics) 9 2016/04/13 Social Media Marketing Analytics (社群媒體行銷分析) 10 2016/04/20 期中報告 (Midterm Project Report) 11 2016/04/27 Deep Learning with Theano and Keras in Python (Python Theano 和 Keras 深度學習) 12 2016/05/04 Deep Learning with Google TensorFlow (Google TensorFlow 深度學習) 13 2016/05/11 Sentiment Analysis on Social Media with Deep Learning (深度學習社群媒體情感分析)

課程大綱 (Syllabus) 週次 (Week) 日期 (Date) 內容 (Subject/Topics) 14 2016/05/18 Social Network Analysis (社會網絡分析) 15 2016/05/25 Measurements of Social Network (社會網絡量測) 16 2016/06/01 Tools of Social Network Analysis (社會網絡分析工具) 17 2016/06/08 Final Project Presentation I (期末報告 I) 18 2016/06/15 Final Project Presentation II (期末報告 II)

Deep Learning with Theano and Keras in Python

LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Sebastian Raschka (2015), Python Machine Learning, Packt Publishing Source: Sebastian Raschka (2015), Python Machine Learning, Packt Publishing Source: http://www.amazon.com/Python-Machine-Learning-Sebastian-Raschka/dp/1783555130 Source: http://www.amazon.com/Python-Machine-Learning-Sebastian-Raschka/dp/1783555130

Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing Source: http://www.amazon.com/Practical-Machine-Learning-Sunila-Gollapudi/dp/178439968X Source: http://www.amazon.com/Practical-Machine-Learning-Sunila-Gollapudi/dp/178439968X

Machine Learning Models Deep Learning Kernel Association rules Ensemble Decision tree Dimensionality reduction Clustering Regression Analysis Bayesian Instance based Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Neural networks (NN) 1960 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Multilayer Perceptrons (MLP) 1985 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Restricted Boltzmann Machine (RBM) 1986 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Support Vector Machine (SVM) 1995 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Hinton presents the Deep Belief Network (DBN) New interests in deep learning and RBM State of the art MNIST 2005 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Deep Recurrent Neural Network (RNN) 2009 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Convolutional DBN 2010 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Max-Pooling CDBN 2011 Source: Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing

Neural Networks Input Layer (X) Hidden Layer (H) Output Layer (Y) X1 Y Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Deep Learning Geoffrey Hinton Yann LeCun Yoshua Bengio Andrew Y. Ng

Geoffrey Hinton Google University of Toronto Source: https://en.wikipedia.org/wiki/Geoffrey_Hinton

LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Deep Learning Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Deep Learning Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Deep Learning Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Deep Learning Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

Recurrent Neural Network (RNN) Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

From image to text Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

From image to text Image: deep convolution neural network (CNN) Text: recurrent neural network (RNN) Source: LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444.

CS224d: Deep Learning for Natural Language Processing http://cs224d.stanford.edu/

Recurrent Neural Networks (RNNs) Source: http://cs224d.stanford.edu/lectures/CS224d-Lecture8.pdf

X Y 3 5 75 5 1 82 10 2 93 8 3 ? Hours Sleep Hours Study Score 3 5 75 5 1 82 10 2 93 8 3 ? Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

X Y 3 5 75 5 1 82 10 2 93 8 3 ? Hours Sleep Hours Study Score Training 3 5 75 Training 5 1 82 10 2 93 8 3 ? Testing Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Training a Network = Minimize the Cost Function Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Neural Networks Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Neural Networks Input Layer (X) Hidden Layer (H) Output Layer (Y) X1 Y Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Neural Networks Input Layer (X) Hidden Layers (H) Output Layer (Y) Deep Neural Networks Deep Learning Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Neural Networks Neuron Neuron Input Layer (X) Hidden Layer (H) Output Layer (Y) Neuron Synapse Synapse Neuron X1 Y X2 Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Source: https://en.wikipedia.org/wiki/Neuron Neuron and Synapse Source: https://en.wikipedia.org/wiki/Neuron

Neurons 2 Bipolar neuron 1 Unipolar neuron 3 Multipolar neuron 4 Pseudounipolar neuron Source: https://en.wikipedia.org/wiki/Neuron

Neural Networks Input Layer (X) Hidden Layer (H) Output Layer (Y) Hours Sleep Score Hours Study Source: https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU

Neural Networks Input Layer (X) Hidden Layer (H) Output Layer (Y) Source: https://www.youtube.com/watch?v=P2HPcj8lRJE&list=PLjJh1vlSEYgvGod9wWiydumYl8hOXixNu&index=2

Convolutional Neural Networks (CNNs / ConvNets) http://cs231n.github.io/convolutional-networks/

A regular 3-layer Neural Network http://cs231n.github.io/convolutional-networks/

A ConvNet arranges its neurons in three dimensions (width, height, depth) http://cs231n.github.io/convolutional-networks/

The activations of an example ConvNet architecture. http://cs231n.github.io/convolutional-networks/

ConvNets http://cs231n.github.io/convolutional-networks/

ConvNets http://cs231n.github.io/convolutional-networks/

ConvNets http://cs231n.github.io/convolutional-networks/

ConvNets max pooling http://cs231n.github.io/convolutional-networks/

Convolutional Neural Networks (CNN) (LeNet) Sparse Connectivity Source: http://deeplearning.net/tutorial/lenet.html

Convolutional Neural Networks (CNN) (LeNet) Shared Weights Source: http://deeplearning.net/tutorial/lenet.html

Convolutional Neural Networks (CNN) (LeNet) example of a convolutional layer Source: http://deeplearning.net/tutorial/lenet.html

Convolutional Neural Networks (CNN) (LeNet) Source: http://deeplearning.net/tutorial/lenet.html

show flights from Boston to New York today Source: http://deeplearning.net/tutorial/rnnslu.html

Source: http://deeplearning.net/tutorial/rnnslu.html Recurrent Neural Networks with Word Embeddings Semantic Parsing / Slot-Filling (Spoken Language Understanding) Input (words) show flights from Boston to New York today Output (labels) O B-dept B-arr I-arr B-date Source: http://deeplearning.net/tutorial/rnnslu.html

show flights from Boston to New York today Input (words) show flights from Boston to New York today Output (labels) O B-dept B-arr I-arr B-date Source: http://deeplearning.net/tutorial/rnnslu.html

Deep Learning Software Theano CPU/GPU symbolic expression compiler in python (from MILA lab at University of Montreal) Keras A theano based deep learning library. Tensorflow TensorFlow™ is an open source software library for numerical computation using data flow graphs. Source: http://deeplearning.net/software_links/

Theano http://deeplearning.net/software/theano/

https://mila.umontreal.ca/en/

Keras http://keras.io/

Source: http://deeplearning.net/software/theano/install.html#anaconda pip install Theano Source: http://deeplearning.net/software/theano/install.html#anaconda

Source: http://deeplearning.net/software/theano/install.html#anaconda conda install pydot Source: http://deeplearning.net/software/theano/install.html#anaconda

sudo pip install keras pip install keras Source: http://keras.io/

New Deep Learning in Jupyter Notebook Source: http://deeplearning.net/software/theano/tutorial/adding.html http://deeplearning.net/software/theano/tutorial/

Source: https://github.com/Newmu/Theano-Tutorials Theano Example import theano from theano import tensor as T a = T.scalar() b = T.scalar() y = a * b multiply = theano.function(inputs=[a, b], outputs=y) print(multiply(2, 3)) #6 print(multiply(4, 5)) #20 Source: https://github.com/Newmu/Theano-Tutorials

Source: https://github.com/Newmu/Theano-Tutorials Theano Example Source: https://github.com/Newmu/Theano-Tutorials

Keras Example: imdb.lstm.py Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py from __future__ import print_function import numpy as np np.random.seed(1337) # for reproducibility from keras.preprocessing import sequence from keras.utils import np_utils from keras.models import Sequential from keras.layers.core import Dense, Dropout, Activation from keras.layers.embeddings import Embedding from keras.layers.recurrent import LSTM, SimpleRNN, GRU from keras.datasets import imdb max_features = 20000 maxlen = 80 # cut texts after this number of words (among top max_features most common words) batch_size = 32 print('Loading data...') (X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features, test_split=0.2) print(len(X_train), 'train sequences') print(len(X_test), 'test sequences') print('Pad sequences (samples x time)') X_train = sequence.pad_sequences(X_train, maxlen=maxlen) X_test = sequence.pad_sequences(X_test, maxlen=maxlen) print('X_train shape:', X_train.shape) print('X_test shape:', X_test.shape) print('Build model...') model = Sequential() model.add(Embedding(max_features, 128, input_length=maxlen, dropout=0.2)) model.add(LSTM(128, dropout_W=0.2, dropout_U=0.2)) # try using a GRU instead, for fun model.add(Dense(1)) model.add(Activation('sigmoid')) # try using different optimizers and different optimizer configs model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) print('Train...') print(X_train.shape) print(y_train.shape) model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=15, validation_data=(X_test, y_test)) score, acc = model.evaluate(X_test, y_test, batch_size=batch_size) print('Test score:', score) print('Test accuracy:', acc) Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py Deep Learning (Training…) Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras Example: imdb.lstm.py Deep Learning (Training…) Source: https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py

Keras LSTM recurrent neural network Source: https://github.com/Vict0rSch/deep_learning/tree/master/keras/recurrent

TensorFlow Playground http://playground.tensorflow.org/

References Sunila Gollapudi (2016), Practical Machine Learning, Packt Publishing Sebastian Raschka (2015), Python Machine Learning, Packt Publishing Theano: http://deeplearning.net/software/theano/ Keras: http://keras.io/ Deep Learning Basics: Neural Networks Demystified, https://www.youtube.com/playlist?list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU Deep Learning SIMPLIFIED, https://www.youtube.com/playlist?list=PLjJh1vlSEYgvGod9wWiydumYl8hOXixNu Deep Learning for NLP - Lecture 6 - Recurrent Neural Network, https://www.youtube.com/watch?v=an9x3vXQYYQ