SlideShare a Scribd company logo
Brief Overview of Deep Networks
Monireh Ebrahimi
Semantic Cognitive Perceptual Computing Course, July 2016.
Ohio Center of Excellence in Knowledge-enabled Computing(Kno.e.sis),
Wright State University, USA
1
• “Representation-learning methods with
multiple levels of representation, obtained by
composing simple but non-linear modules
that each transform the representation at one
level (starting with the raw input) into a
representation at a higher, slightly more
abstract level. “
What is deep learning?
2
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553
(2015): 436-444.
Successive model layers learn deeper intermediate representations.
Lee, Honglak. "Tutorial on deep learning and applications." NIPS 2010
Workshop on Deep Learning and Unsupervised Feature Learning.
2010.
3
What is deep learning? Learning Hierarchical Representations
Socher, Richard, Yoshua Bengio, and Chris Manning. "Deep learning
for NLP." Tutorial at Association of Computational Logistics (ACL),
2012, and North American Chapter of the Association of
Computational Linguistics (NAACL) (2013).
• Image recognition: Pixel → edge → texton →
motif → part → object
• Text: Character → word → word group →
clause → sentence → story
• Speech: Sample → spectral band → sound →
… phone → phoneme → word
What is deep learning? Learning Hierarchical Representations
4
LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International
Conference on Machine Learning (ICML’13). 2013.
• Does not require any manual Feature
Engineering
• Deep architectures work well (vision, audio,
NLP, etc.)!
– Speech Recognition(2009)
– Computer Vision (2012)
• Early in 2015, a machine was able to beat the human at
an object recognition challenge for the first time in the
history of AI.
– Machine Translation (2014)
Why go deep?
5
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553
(2015): 436-444.
• Loosely inspired by biological neural networks
(the central nervous system of animals),
particularly brain
Biologically inspired: how does the cortex learn perception?
6
• which details are important?
• For airplanes, feathers and wing flapping
weren't crucial
• What is the equivalent of aerodynamics for
understanding intelligence?
“Let's be inspired by nature, but not too much”
7
LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International Conference
on Machine Learning (ICML’13). 2013.
• Retina - LGN - V1 - V2 - V4 - PIT – AIT
• Lots of intermediate representations
Biologically Inspired: The Mammalian Visual Cortex is
Hierarchical.
8
[picture from Simon Thorpe]
LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International
Conference on Machine Learning (ICML’13). 2013.
All models are WRONG, but some are USEFUL.
9
Neural Networks
10
Why now?
11
• Vanishing Gradient Problem
• Lots of data
• GPUs
RBM (Restricted Boltzman Machine)
12
• Solution to Vanishing
Gradient Problem
• Reconstruct the input and
learn the features in this
process.
https://www.youtube.com/channel/UC9OeZkIwhzfv-
_Cb7fCikLQ
Autoencoders
13
https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
• Kind of Autoencoder (Feature
Extractor Neural Net)
• Detects inherent patterns in
data
• Unsupervised
• Good for real-world
problems
• Both Shallow and deep
Deep Learning for NLP
14
• Use of vectors
– dense low-dimensional real-valued vectors
• Continuous Bag of Words
• Skip Gram Model
• Two popular tools: Word2Vec, Glove
– One-hot vector
• Size of the entire vocabulary
• Very large sparse vector
https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
Continuous Bag of Words
15
Context Words Target word
Skip Gram Model
16
Target Word Context Words
Deep Belief Net
17
• Stack of RBMs
• Identical to MLP in terms of network structure
• Different Training:
– Pre-training
– Fine-tuning
• Small labeled dataset
• Reasonable training time
• Very accurate
• Image Recognition
Convolutional Neural Networks
18
1. Convolutional layer
2. ReLU layer
3. Pooling Layer
4. Fully Connected Layer
• Supervised
• Large amount of labeled
data for training
Convolutional Neural Networks
19
– CNN performs quite well on NLP problems.
• Although we do not have the nice intuition that we have for
image recognition
– Text Processing (Sentiment Analysis and Text
Categorization)
• Word-level
• Character-level:
– Very attractive for user-generated contents with typos and new
vocabularies
– Models can be fine-tuned from a task A with large corpus to a
more targeted task with smaller corpus
– Learning directly from character-level input (needs millions of
examples)
– Learning from pre-trained character embeddings
Recurrent Neural Nets
20
http://www.wildml.com/2015/09/recurrent-neural-networks-
tutorial-part-1-introduction-to-rnns/
• Not Feedforward
• Sequence of values as input
• Sequence of values as output
• Stacking RNNs on top of each other
Recurrent Neural Nets
21
• Extremely difficult to train
– Exponential Vanishing Gradient Problem
• RNN with n time steps = n layers MLP
– Solution:
• LSTM/GRU: Helps the net to decide when to forget the current
input and when to remember it for the future time steps.
• Good for:
– Time Series Analysis (Forecasting)
– Machine Translation
– Text Processing (Parsing, NER, Sentiment Analysis)
• Word-level
• Character-level
Recursive Neural Tensor Network
22
• Leave group:
• input
• Root group:
• class and score
Socher, Richard, et al. "Recursive deep models for semantic compositionality
over a sentiment treebank." Proceedings of the conference on empirical
methods in natural language processing (EMNLP). Vol. 1631. 2013.
References
23
1. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature
521.7553 (2015): 436-444.
2. Socher, Richard, Yoshua Bengio, and Chris Manning. "Deep learning for NLP."
Tutorial at Association of Computational Logistics (ACL), 2012, and North American
Chapter of the Association of Computational Linguistics (NAACL) (2013).
3. Lee, Honglak. "Tutorial on deep learning and applications." NIPS 2010 Workshop
on Deep Learning and Unsupervised Feature Learning. 2010.
4. LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International
Conference on Machine Learning (ICML’13). 2013.
5. Socher, Richard, et al. "Recursive deep models for semantic compositionality over
a sentiment treebank." Proceedings of the conference on empirical methods in natural
language processing (EMNLP). Vol. 1631. 2013.
6. https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
7. https://www.udacity.com/course/deep-learning--ud730
8. http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-
introduction-to-rnns/
Thank you 
Thank you, and please visit us at http://knoesis.org
monireh@knoesis.org
24

More Related Content

What's hot

Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
Tadahiro Taniguchi
 
Deep Learning Big Data Meetup @ Trondheim
Deep Learning Big Data Meetup @ TrondheimDeep Learning Big Data Meetup @ Trondheim
Deep Learning Big Data Meetup @ Trondheim
Cyril Banino-Rokkones
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Vincenzo Lomonaco
 
Character recognition project
Character recognition projectCharacter recognition project
Character recognition project
Monsif sakienah
 
(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
君 廖
 
Frontiers of Natural Language Processing
Frontiers of Natural Language ProcessingFrontiers of Natural Language Processing
Frontiers of Natural Language Processing
Sebastian Ruder
 
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
Tadahiro Taniguchi
 
Nonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
Nonparametric Bayesian Word Discovery for Symbol Emergence in RoboticsNonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
Nonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
Tadahiro Taniguchi
 
Technical Paper.doc.doc
Technical Paper.doc.docTechnical Paper.doc.doc
Technical Paper.doc.doc
butest
 
syllabus-IS.doc
syllabus-IS.docsyllabus-IS.doc
syllabus-IS.doc
butest
 
Project report - Bengali digit recongnition using SVM
Project report - Bengali digit recongnition using SVMProject report - Bengali digit recongnition using SVM
Project report - Bengali digit recongnition using SVM
Mohammad Saiful Islam
 
Teachbot teaching robot_using_artificial
Teachbot teaching robot_using_artificialTeachbot teaching robot_using_artificial
Teachbot teaching robot_using_artificial
CamillaTonanzi
 
Study on Different Human Emotions Using Back Propagation Method
Study on Different Human Emotions Using Back Propagation MethodStudy on Different Human Emotions Using Back Propagation Method
Study on Different Human Emotions Using Back Propagation Method
ijiert bestjournal
 
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent SystemTAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
Yi-Shin Chen
 
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATANAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
ijnlc
 
SCTUR: A Sentiment Classification Technique for URDU
SCTUR: A Sentiment Classification Technique for URDUSCTUR: A Sentiment Classification Technique for URDU
SCTUR: A Sentiment Classification Technique for URDU
International Journal of Computer and Communication System Engineering
 
Intro deep learning
Intro deep learningIntro deep learning
Intro deep learning
mravendi
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
National Institute of Technology Durgapur
 
Artificial Neural Network / Hand written character Recognition
Artificial Neural Network / Hand written character RecognitionArtificial Neural Network / Hand written character Recognition
Artificial Neural Network / Hand written character Recognition
Dr. Uday Saikia
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modelling
Riddhi Jain
 

What's hot (20)

Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
Symbol Emergence in Robotics: Language Acquisition via Real-world Sensorimoto...
 
Deep Learning Big Data Meetup @ Trondheim
Deep Learning Big Data Meetup @ TrondheimDeep Learning Big Data Meetup @ Trondheim
Deep Learning Big Data Meetup @ Trondheim
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
 
Character recognition project
Character recognition projectCharacter recognition project
Character recognition project
 
(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
 
Frontiers of Natural Language Processing
Frontiers of Natural Language ProcessingFrontiers of Natural Language Processing
Frontiers of Natural Language Processing
 
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
Semantic Segmentation of Driving Behavior Data: Double Articulation Analyzer ...
 
Nonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
Nonparametric Bayesian Word Discovery for Symbol Emergence in RoboticsNonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
Nonparametric Bayesian Word Discovery for Symbol Emergence in Robotics
 
Technical Paper.doc.doc
Technical Paper.doc.docTechnical Paper.doc.doc
Technical Paper.doc.doc
 
syllabus-IS.doc
syllabus-IS.docsyllabus-IS.doc
syllabus-IS.doc
 
Project report - Bengali digit recongnition using SVM
Project report - Bengali digit recongnition using SVMProject report - Bengali digit recongnition using SVM
Project report - Bengali digit recongnition using SVM
 
Teachbot teaching robot_using_artificial
Teachbot teaching robot_using_artificialTeachbot teaching robot_using_artificial
Teachbot teaching robot_using_artificial
 
Study on Different Human Emotions Using Back Propagation Method
Study on Different Human Emotions Using Back Propagation MethodStudy on Different Human Emotions Using Back Propagation Method
Study on Different Human Emotions Using Back Propagation Method
 
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent SystemTAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
TAAI 2016 Keynote Talk: Intercultural Collaboration as a Multi‐Agent System
 
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATANAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
NAMED ENTITY RECOGNITION FROM BENGALI NEWSPAPER DATA
 
SCTUR: A Sentiment Classification Technique for URDU
SCTUR: A Sentiment Classification Technique for URDUSCTUR: A Sentiment Classification Technique for URDU
SCTUR: A Sentiment Classification Technique for URDU
 
Intro deep learning
Intro deep learningIntro deep learning
Intro deep learning
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
 
Artificial Neural Network / Hand written character Recognition
Artificial Neural Network / Hand written character RecognitionArtificial Neural Network / Hand written character Recognition
Artificial Neural Network / Hand written character Recognition
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modelling
 

Similar to Semantic, Cognitive and Perceptual Computing -Deep learning

Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
Roelof Pieters
 
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
Karthik Murugesan
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Amr Rashed
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
Akshay Hegde
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
Madhu Sanjeevi (Mady)
 
final-day1-july2.pptx
final-day1-july2.pptxfinal-day1-july2.pptx
final-day1-july2.pptx
KartikGulati16
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Roelof Pieters
 
MILA DL & RL summer school highlights
MILA DL & RL summer school highlights MILA DL & RL summer school highlights
MILA DL & RL summer school highlights
Natalia Díaz Rodríguez
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
Manjunatha Sai
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
leopauly
 
Deep learning 1
Deep learning 1Deep learning 1
Deep learning 1
Karthick Thiyagu
 
Deep analytics via learning to reason
Deep analytics via learning to reasonDeep analytics via learning to reason
Deep analytics via learning to reason
Deakin University
 
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher ManningDeep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
BigDataCloud
 
How do we know what we don’t know: Using the Neuroscience Information Framew...
How do we know what we don’t know:  Using the Neuroscience Information Framew...How do we know what we don’t know:  Using the Neuroscience Information Framew...
How do we know what we don’t know: Using the Neuroscience Information Framew...
Maryann Martone
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
Poo Kuan Hoong
 
Looking for Commonsense in the Semantic Web
Looking for Commonsense in the Semantic WebLooking for Commonsense in the Semantic Web
Looking for Commonsense in the Semantic Web
Valentina Presutti
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep Learning
Poo Kuan Hoong
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learning
Charles Deledalle
 
Standards for Smart Learning Environments
Standards for Smart Learning EnvironmentsStandards for Smart Learning Environments
Standards for Smart Learning Environments
Tore Hoel
 
Rise of AI through DL
Rise of AI through DLRise of AI through DL
Rise of AI through DL
Rehan Guha
 

Similar to Semantic, Cognitive and Perceptual Computing -Deep learning (20)

Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
 
final-day1-july2.pptx
final-day1-july2.pptxfinal-day1-july2.pptx
final-day1-july2.pptx
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word Embeddings
 
MILA DL & RL summer school highlights
MILA DL & RL summer school highlights MILA DL & RL summer school highlights
MILA DL & RL summer school highlights
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Deep learning 1
Deep learning 1Deep learning 1
Deep learning 1
 
Deep analytics via learning to reason
Deep analytics via learning to reasonDeep analytics via learning to reason
Deep analytics via learning to reason
 
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher ManningDeep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
 
How do we know what we don’t know: Using the Neuroscience Information Framew...
How do we know what we don’t know:  Using the Neuroscience Information Framew...How do we know what we don’t know:  Using the Neuroscience Information Framew...
How do we know what we don’t know: Using the Neuroscience Information Framew...
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 
Looking for Commonsense in the Semantic Web
Looking for Commonsense in the Semantic WebLooking for Commonsense in the Semantic Web
Looking for Commonsense in the Semantic Web
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep Learning
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learning
 
Standards for Smart Learning Environments
Standards for Smart Learning EnvironmentsStandards for Smart Learning Environments
Standards for Smart Learning Environments
 
Rise of AI through DL
Rise of AI through DLRise of AI through DL
Rise of AI through DL
 

Recently uploaded

Pride Month Slides 2024 David Douglas School District
Pride Month Slides 2024 David Douglas School DistrictPride Month Slides 2024 David Douglas School District
Pride Month Slides 2024 David Douglas School District
David Douglas School District
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
camakaiclarkmusic
 
Azure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHatAzure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHat
Scholarhat
 
Smart-Money for SMC traders good time and ICT
Smart-Money for SMC traders good time and ICTSmart-Money for SMC traders good time and ICT
Smart-Money for SMC traders good time and ICT
simonomuemu
 
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective UpskillingYour Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Excellence Foundation for South Sudan
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
Nguyen Thanh Tu Collection
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Mohd Adib Abd Muin, Senior Lecturer at Universiti Utara Malaysia
 
Digital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental DesignDigital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental Design
amberjdewit93
 
The basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptxThe basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptx
heathfieldcps1
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
TechSoup
 
A Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptxA Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptx
thanhdowork
 
Liberal Approach to the Study of Indian Politics.pdf
Liberal Approach to the Study of Indian Politics.pdfLiberal Approach to the Study of Indian Politics.pdf
Liberal Approach to the Study of Indian Politics.pdf
WaniBasim
 
Digital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments UnitDigital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments Unit
chanes7
 
Hindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdfHindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdf
Dr. Mulla Adam Ali
 
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat  Leveraging AI for Diversity, Equity, and InclusionExecutive Directors Chat  Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
TechSoup
 
clinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdfclinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdf
Priyankaranawat4
 
Types of Herbal Cosmetics its standardization.
Types of Herbal Cosmetics its standardization.Types of Herbal Cosmetics its standardization.
Types of Herbal Cosmetics its standardization.
Ashokrao Mane college of Pharmacy Peth-Vadgaon
 
World environment day ppt For 5 June 2024
World environment day ppt For 5 June 2024World environment day ppt For 5 June 2024
World environment day ppt For 5 June 2024
ak6969907
 
PIMS Job Advertisement 2024.pdf Islamabad
PIMS Job Advertisement 2024.pdf IslamabadPIMS Job Advertisement 2024.pdf Islamabad
PIMS Job Advertisement 2024.pdf Islamabad
AyyanKhan40
 
A Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdfA Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdf
Jean Carlos Nunes Paixão
 

Recently uploaded (20)

Pride Month Slides 2024 David Douglas School District
Pride Month Slides 2024 David Douglas School DistrictPride Month Slides 2024 David Douglas School District
Pride Month Slides 2024 David Douglas School District
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
 
Azure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHatAzure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHat
 
Smart-Money for SMC traders good time and ICT
Smart-Money for SMC traders good time and ICTSmart-Money for SMC traders good time and ICT
Smart-Money for SMC traders good time and ICT
 
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective UpskillingYour Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective Upskilling
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2023-2024 (CÓ FI...
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
 
Digital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental DesignDigital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental Design
 
The basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptxThe basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptx
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
 
A Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptxA Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptx
 
Liberal Approach to the Study of Indian Politics.pdf
Liberal Approach to the Study of Indian Politics.pdfLiberal Approach to the Study of Indian Politics.pdf
Liberal Approach to the Study of Indian Politics.pdf
 
Digital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments UnitDigital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments Unit
 
Hindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdfHindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdf
 
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat  Leveraging AI for Diversity, Equity, and InclusionExecutive Directors Chat  Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
 
clinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdfclinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdf
 
Types of Herbal Cosmetics its standardization.
Types of Herbal Cosmetics its standardization.Types of Herbal Cosmetics its standardization.
Types of Herbal Cosmetics its standardization.
 
World environment day ppt For 5 June 2024
World environment day ppt For 5 June 2024World environment day ppt For 5 June 2024
World environment day ppt For 5 June 2024
 
PIMS Job Advertisement 2024.pdf Islamabad
PIMS Job Advertisement 2024.pdf IslamabadPIMS Job Advertisement 2024.pdf Islamabad
PIMS Job Advertisement 2024.pdf Islamabad
 
A Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdfA Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdf
 

Semantic, Cognitive and Perceptual Computing -Deep learning

  • 1. Brief Overview of Deep Networks Monireh Ebrahimi Semantic Cognitive Perceptual Computing Course, July 2016. Ohio Center of Excellence in Knowledge-enabled Computing(Kno.e.sis), Wright State University, USA 1
  • 2. • “Representation-learning methods with multiple levels of representation, obtained by composing simple but non-linear modules that each transform the representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract level. “ What is deep learning? 2 LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444.
  • 3. Successive model layers learn deeper intermediate representations. Lee, Honglak. "Tutorial on deep learning and applications." NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning. 2010. 3 What is deep learning? Learning Hierarchical Representations Socher, Richard, Yoshua Bengio, and Chris Manning. "Deep learning for NLP." Tutorial at Association of Computational Logistics (ACL), 2012, and North American Chapter of the Association of Computational Linguistics (NAACL) (2013).
  • 4. • Image recognition: Pixel → edge → texton → motif → part → object • Text: Character → word → word group → clause → sentence → story • Speech: Sample → spectral band → sound → … phone → phoneme → word What is deep learning? Learning Hierarchical Representations 4 LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International Conference on Machine Learning (ICML’13). 2013.
  • 5. • Does not require any manual Feature Engineering • Deep architectures work well (vision, audio, NLP, etc.)! – Speech Recognition(2009) – Computer Vision (2012) • Early in 2015, a machine was able to beat the human at an object recognition challenge for the first time in the history of AI. – Machine Translation (2014) Why go deep? 5 LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444.
  • 6. • Loosely inspired by biological neural networks (the central nervous system of animals), particularly brain Biologically inspired: how does the cortex learn perception? 6
  • 7. • which details are important? • For airplanes, feathers and wing flapping weren't crucial • What is the equivalent of aerodynamics for understanding intelligence? “Let's be inspired by nature, but not too much” 7 LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International Conference on Machine Learning (ICML’13). 2013.
  • 8. • Retina - LGN - V1 - V2 - V4 - PIT – AIT • Lots of intermediate representations Biologically Inspired: The Mammalian Visual Cortex is Hierarchical. 8 [picture from Simon Thorpe] LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International Conference on Machine Learning (ICML’13). 2013.
  • 9. All models are WRONG, but some are USEFUL. 9
  • 11. Why now? 11 • Vanishing Gradient Problem • Lots of data • GPUs
  • 12. RBM (Restricted Boltzman Machine) 12 • Solution to Vanishing Gradient Problem • Reconstruct the input and learn the features in this process. https://www.youtube.com/channel/UC9OeZkIwhzfv- _Cb7fCikLQ
  • 13. Autoencoders 13 https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ • Kind of Autoencoder (Feature Extractor Neural Net) • Detects inherent patterns in data • Unsupervised • Good for real-world problems • Both Shallow and deep
  • 14. Deep Learning for NLP 14 • Use of vectors – dense low-dimensional real-valued vectors • Continuous Bag of Words • Skip Gram Model • Two popular tools: Word2Vec, Glove – One-hot vector • Size of the entire vocabulary • Very large sparse vector https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
  • 15. Continuous Bag of Words 15 Context Words Target word
  • 16. Skip Gram Model 16 Target Word Context Words
  • 17. Deep Belief Net 17 • Stack of RBMs • Identical to MLP in terms of network structure • Different Training: – Pre-training – Fine-tuning • Small labeled dataset • Reasonable training time • Very accurate • Image Recognition
  • 18. Convolutional Neural Networks 18 1. Convolutional layer 2. ReLU layer 3. Pooling Layer 4. Fully Connected Layer • Supervised • Large amount of labeled data for training
  • 19. Convolutional Neural Networks 19 – CNN performs quite well on NLP problems. • Although we do not have the nice intuition that we have for image recognition – Text Processing (Sentiment Analysis and Text Categorization) • Word-level • Character-level: – Very attractive for user-generated contents with typos and new vocabularies – Models can be fine-tuned from a task A with large corpus to a more targeted task with smaller corpus – Learning directly from character-level input (needs millions of examples) – Learning from pre-trained character embeddings
  • 20. Recurrent Neural Nets 20 http://www.wildml.com/2015/09/recurrent-neural-networks- tutorial-part-1-introduction-to-rnns/ • Not Feedforward • Sequence of values as input • Sequence of values as output • Stacking RNNs on top of each other
  • 21. Recurrent Neural Nets 21 • Extremely difficult to train – Exponential Vanishing Gradient Problem • RNN with n time steps = n layers MLP – Solution: • LSTM/GRU: Helps the net to decide when to forget the current input and when to remember it for the future time steps. • Good for: – Time Series Analysis (Forecasting) – Machine Translation – Text Processing (Parsing, NER, Sentiment Analysis) • Word-level • Character-level
  • 22. Recursive Neural Tensor Network 22 • Leave group: • input • Root group: • class and score Socher, Richard, et al. "Recursive deep models for semantic compositionality over a sentiment treebank." Proceedings of the conference on empirical methods in natural language processing (EMNLP). Vol. 1631. 2013.
  • 23. References 23 1. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444. 2. Socher, Richard, Yoshua Bengio, and Chris Manning. "Deep learning for NLP." Tutorial at Association of Computational Logistics (ACL), 2012, and North American Chapter of the Association of Computational Linguistics (NAACL) (2013). 3. Lee, Honglak. "Tutorial on deep learning and applications." NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning. 2010. 4. LeCun, Yann, and M. Ranzato. "Deep learning tutorial." Tutorials in International Conference on Machine Learning (ICML’13). 2013. 5. Socher, Richard, et al. "Recursive deep models for semantic compositionality over a sentiment treebank." Proceedings of the conference on empirical methods in natural language processing (EMNLP). Vol. 1631. 2013. 6. https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ 7. https://www.udacity.com/course/deep-learning--ud730 8. http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1- introduction-to-rnns/
  • 24. Thank you  Thank you, and please visit us at http://knoesis.org monireh@knoesis.org 24

Editor's Notes

  1. With the composition of enough such transformations, very complex functions can be learned. For classification tasks, higher layers of representation amplify aspects of the input that are important for discrimination and suppress irrelevant variations.
  2. It's nice imitate nature, Which details are merely the result of evolution, and the constraints of biochemistry?
  3. Vanishing Gradient Problem: One of the reasons that NNs were not that much successful before. Solved in 2006-2007 by Benjio, Le Cun, Hinton papers, 3 papers, breakthrough in deep learning Neural networks, big come back with deep learning
  4. 1- forward: an RBM takes input and translates them into a set of numbers that encode the inputs 2- backward: takes this set of numbers and translates them back to form the reconstructed inputs. 3- At the visible layer, the reconstruction
  5. Deep Autoencoders are extremely useful tools for dimensionality reduction An autoencoder is a neural net that takes a set of typically unlabeled inputs, and after decoding them, tries to reconstruct them as accurately as possible. As result of this, then net must decide which of the data features are the most important, essentially acting as a feature extraction engine.
  6. The fundamental difference between deep learning and traditional NLP methods is the use of dense vectors.
  7. word2vec map a word into a 1D vector whose size is  some fixed size chosen empirically(N), that is the number of nodes in the hidden layer also. Indeed, after training the neural network, for each word in the input layer, all the weights to the hidden layer of dimension N is learned. So for each word you have 1*N vector of weights that is its vector representation (so-called the real-value dense low-dimensional(1*N) vector representation of that word ).  What the neural net takes as input is the one-hot vector of size V*1, so in each iteration only one word in the NN input is 1. What NN does in that iteration is changing all the output vectors (that is updating all the weights between the hidden layer and the output layer (1*N vector for each word)) in a way that all the output words that can co-occur with the input word become more similar to the input word (that is activated by being 1) and all other words in the output that cannot be in the input word context more dissimilar. Similarly the vector for the input (that is activated by being 1) will be updated in a way that the input word will become more similar to its context words in output. What we mean by input vector is the weight between input layer and hidden layer that is 1*N. After running the algorithm many times we have 2 choices: using 1*N  vector of weight from each word from input layer to its hidden layer as its vector representation or choose the 1*N vector of weights from the word form output layer to the hidden layer as the 1*N vector representation of that word. Empirically the use the first choice. So what we use a  vector representation of one word from word2vec is nothing but the 1*N vector of weights from that word in input layer to the hidden layer.
  8. We do not start backpropagation until we already have sensible weights that already do well at the task. – So the initial gradients are sensible and backprop only needs to perform a local search. [https://www.cs.toronto.edu/~hinton/nipstutorial/nipstut3.pdf] https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
  9. ReLU: for the vanishing gradient problem Pooling layer: for dimensionality reduction
  10. Words in the source language: input Words in the target language: output