SlideShare a Scribd company logo
1 of 52
Bridging the gap
between AI and UI
● Recommendation Systems (RecSys)
● Model Interpretability Technics (MI)
● Using MI for communication
Outline
Recommendation
Systems
Netflix RecSys
What does it mean?
RecSys with Deep Learning
Autoencoders Meet Collaborative Filtering (Sedhain et al. AutoRec 2015)
Session Based Recommendations with RNN (Hidasi et al. ICLR 2016)
Wide & Deep Learning for Recommender Systems (Cheng et al. DLRS @ RecSys 2016)
Matching Engine
Response Suggestions
Not what I wanted to say!
UI for AI
Better UI for AI
Google Apple
Google Apple
Search suggestions (auto-complete) moves to search results
Feedback
- Constructive
- Focused
Understanding
Models
Predictions
How to “understand” a model prediction?
How to explain a model prediction?
Which features contributed to the
model prediction?
And how?
Example: Decision Tree
“Why should I trust you?” - Explaining the Predictions of
Any Classifier
LIME: Local Interpretable Model-Agnostic Explanations
LIME
- Explains the model result
- Enhances User Trust
Supports Multi-class classifications, (example),
text documents, images, etc.
Packages exists for R, Python, etc.
LIME
● Linear approximated model with a subset of the features - O(2n)
● Lowest distance to the original inputs
● Measuring the magnitude of the predictions distance
SHAP - NIPS`17
SHapley Additive exPlanations
“A Unified Approach to Interpreting
Model Predictions” - Lundberg & Lee
“Connects game theory
with local explanations”
SHAP Value - Feature importance as
an impact (effect) on the output
- The marginal value of an agent in a coalition (impact)
- Average marginal contribution over all possible sequences
Cooperative Games:
http://www.lamsade.dauphine.fr/~airiau/Teaching/CoopGames/2011/coopgam
es-7[8up].pdf
Game Theory :: Shapley Values
SHAP - NIPS`17
- Calculates N linear models for a subsets of the features
- Calculates the impact on the result
- How much each feature contribute as part of a ‘coalition’?
SHAP - NIPS`17
Unifies:
- LIME
- Shapley sampling values
- Shapley regression values
- DeepLIFT
.
.
.
Better consistency with
human intuition
Deeper
Understanding
of Deep Learning?
Visualizing Image Classifications
As an interpretability method:
● What features are these networks really using?
● Do individual units have meaning?
● What roles are played by different layers?
● How are high-level concepts built from low-level ones?
Visualizing Image Classifications
Network Dissection: Quantifying Interpretability of Deep Visual Representations
https://arxiv.org/pdf/1704.05796.pdf
http://people.csail.mit.edu/bzhou/ppt/presentation_ICML_workshop.pdf
Deeper
Understanding
Of Deep Learning
for NLP
Why?
< 2014 Rule-based NLP
2014 - DL NLP
Future DL identifies NLP Rules
= Transparent
= Black box
How?
CBOW (Word-vectors)
LSTM / BiLSTM
AutoEncoders
What is encoded / captured in a vector?
Fine-grained Analysis Of Sentence Embeddings Using Auxiliary Prediction Tasks
(Adi et al. ICLR 2017)
● Trained a model to predict: sentence length, word existence, word-order
● 300-D CBOW - most effective (even for word order!)
● LSTM Autoencoder (500 to 750 D)
What is encoded / captured in a vector?
Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive
neural networks process hierarchical structure
(Hypkes et al. NIPS 2016)
● Visualizing activated neurons
● Researching compositional structures (trees)
● “The scientist who wrote the natural language research paper”
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition
Systems
(Belinkov, Glass, NIPS 2017)
● Speech Recognition
● Visualizing layers
● Which layer/neuron is responsible to which phone (sound)
What is encoded / captured in a vector?
What you can cram into a single $&!#* vector:
Probing sentence embeddings for linguistic properties
(Conneau et al, ACL 2018)
● Ray Mooney
● Set of tests:
○ Surface information: word content, sentence length…
○ Syntactic Information: sentence ‘correctness’, hierarchical structure (depth)
○ Semantic Information (tense, word usage)
● Testing the information that is captured in different vectors
● Again CBOW and BiLSTM stars
What is encoded / captured in a vector?
RNN - Debugging Translation
http://seq2seq-vis.io/ (Strobelt, 2018)
Examines the 5 stages (Encoder, Decoder, Attention, Predictions, Beam-search)
Nearest Neighbor
Visualization
- Examine model decisions
- Connect decisions to
previous examples
- Test alternative decisions
More open questions
What linguistic structures can be captured by
RNN?
How does a model reach a decision?
When would a model fail?
What can’t the model do?
http://u.cs.biu.ac.il/~yogo/blackbox2018.pdf
Keep-Current
Activities - Keep-Current Meetup
- Learning by Doing
- Machine Learning Seminar - Monthly in Vienna
- Applied Machine Learning Course
- PyTorch, Fast.AI
Keep-Current
Educational Project
Filter newly released academic papers
Hybrid recommendation system
- Collaborative filtering
- Content Similarity
- User-Feedback (MOT)
- RNN
Methods
Topic extraction (LDA / LSI)
Document Vector Representation
- Citation Correlation Matrix Decomposition
- Paragraph Vectors
- ELMo / BERT - Attention layer
Similarity using Spotify ANNOY (Approximate Nearest Neighbours - Oh Yeah!)
User-Input
Key-words / topics Extraction
Semantic Similarity
Vector distance:
- cosine similarity
- Euclidean Distance
- Word Mover’s Distance
- PIP
NIPS 18
PIP - Pairwise Inner Product
“Augmented Intelligence”
(Simon Stiebellehner)
“Human Teaching”
(Shai Herz)
Human-Machine
Interactions
Human-Machine Interactions - Ofra Amir
PhD, Harvard University
Intelligent Interactive Systems
(advanced topics in information systems)
- Technion, Israel
AAMAS'18:
- HIGHLIGHTS: Summarizing Agent Behavior to
People
- Agent Strategy Summarization
Meh...
Explain results
- Keywords Contribution:
Positive / Negative
- Encourage User Feedback
Model adaptation
- Stronger Engagement
Interpretability & Communication
http://yannickassogba.info/
Explainable AI
- Models are prune to make mistakes
- Interpretability to the rescue!
- Supplies a peek into the features
- Enhance user trust
- Enables a constructive feedback
Explainable AI using UI
- Be Creative: Explainable UI
- Using ‘stronger’ features for personalization
Future Research:
- Effective Agent Strategy Summary
- Expected Behavior under Different Conditions
Thank You
Liad Magen
www.linkedin.com/in/liadmagen
www.github.com/keep-current
Keep-Current Meetup
Liad.magen @ gmail.com

More Related Content

What's hot

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-ersRoelof Pieters
 
Deep Learning for Information Retrieval: Models, Progress, & Opportunities
Deep Learning for Information Retrieval: Models, Progress, & OpportunitiesDeep Learning for Information Retrieval: Models, Progress, & Opportunities
Deep Learning for Information Retrieval: Models, Progress, & OpportunitiesMatthew Lease
 
Rasa NLU and ML Interpretability
Rasa NLU and ML InterpretabilityRasa NLU and ML Interpretability
Rasa NLU and ML Interpretabilityztopol
 
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...[Paper Reading] Supervised Learning of Universal Sentence Representations fro...
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...Hiroki Shimanaka
 
MetaScience: Holistic Approach for Research Modeling and Analysis
MetaScience: Holistic Approach for Research Modeling and AnalysisMetaScience: Holistic Approach for Research Modeling and Analysis
MetaScience: Holistic Approach for Research Modeling and AnalysisJordi Cabot
 
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 EmbeddingsRoelof Pieters
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLPSatyam Saxena
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modellingRiddhi Jain
 
Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)Yuta Niki
 
Word embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMWord embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMDivya Gera
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsRoelof Pieters
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentationSurya Sg
 
Natural language processing techniques transition from machine learning to de...
Natural language processing techniques transition from machine learning to de...Natural language processing techniques transition from machine learning to de...
Natural language processing techniques transition from machine learning to de...Divya Gera
 
Practical Deep Learning for NLP
Practical Deep Learning for NLP Practical Deep Learning for NLP
Practical Deep Learning for NLP Textkernel
 
Multi-modal Neural Machine Translation - Iacer Calixto
Multi-modal Neural Machine Translation - Iacer CalixtoMulti-modal Neural Machine Translation - Iacer Calixto
Multi-modal Neural Machine Translation - Iacer CalixtoSebastian Ruder
 
AINL 2016: Castro, Lopez, Cavalcante, Couto
AINL 2016: Castro, Lopez, Cavalcante, CoutoAINL 2016: Castro, Lopez, Cavalcante, Couto
AINL 2016: Castro, Lopez, Cavalcante, CoutoLidia Pivovarova
 
ODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPindico data
 
Start a deep learning startup - tutorial
Start a deep learning startup - tutorialStart a deep learning startup - tutorial
Start a deep learning startup - tutorialMostapha Benhenda
 

What's hot (20)

010821+presentation+oti.ppt
010821+presentation+oti.ppt010821+presentation+oti.ppt
010821+presentation+oti.ppt
 
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
 
Deep Learning for Information Retrieval: Models, Progress, & Opportunities
Deep Learning for Information Retrieval: Models, Progress, & OpportunitiesDeep Learning for Information Retrieval: Models, Progress, & Opportunities
Deep Learning for Information Retrieval: Models, Progress, & Opportunities
 
Rasa NLU and ML Interpretability
Rasa NLU and ML InterpretabilityRasa NLU and ML Interpretability
Rasa NLU and ML Interpretability
 
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...[Paper Reading] Supervised Learning of Universal Sentence Representations fro...
[Paper Reading] Supervised Learning of Universal Sentence Representations fro...
 
MetaScience: Holistic Approach for Research Modeling and Analysis
MetaScience: Holistic Approach for Research Modeling and AnalysisMetaScience: Holistic Approach for Research Modeling and Analysis
MetaScience: Holistic Approach for Research Modeling and Analysis
 
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
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLP
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modelling
 
Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)
 
Word embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMWord embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTM
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentation
 
AINL 2016: Filchenkov
AINL 2016: FilchenkovAINL 2016: Filchenkov
AINL 2016: Filchenkov
 
Natural language processing techniques transition from machine learning to de...
Natural language processing techniques transition from machine learning to de...Natural language processing techniques transition from machine learning to de...
Natural language processing techniques transition from machine learning to de...
 
Practical Deep Learning for NLP
Practical Deep Learning for NLP Practical Deep Learning for NLP
Practical Deep Learning for NLP
 
Multi-modal Neural Machine Translation - Iacer Calixto
Multi-modal Neural Machine Translation - Iacer CalixtoMulti-modal Neural Machine Translation - Iacer Calixto
Multi-modal Neural Machine Translation - Iacer Calixto
 
AINL 2016: Castro, Lopez, Cavalcante, Couto
AINL 2016: Castro, Lopez, Cavalcante, CoutoAINL 2016: Castro, Lopez, Cavalcante, Couto
AINL 2016: Castro, Lopez, Cavalcante, Couto
 
ODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLP
 
Start a deep learning startup - tutorial
Start a deep learning startup - tutorialStart a deep learning startup - tutorial
Start a deep learning startup - tutorial
 

Similar to Bridging the gap between AI and UI - DSI Vienna - full version

Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)evabl444
 
Requirements-Collector: Automating Requirements Specification from Elicitatio...
Requirements-Collector: Automating Requirements Specification from Elicitatio...Requirements-Collector: Automating Requirements Specification from Elicitatio...
Requirements-Collector: Automating Requirements Specification from Elicitatio...Sebastiano Panichella
 
Tomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPTomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPMachine Learning Prague
 
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...IRJET Journal
 
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...ejaruuday
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
Zeroshot multimodal named entity disambiguation for noisy social media posts
Zeroshot multimodal named entity disambiguation for noisy social media postsZeroshot multimodal named entity disambiguation for noisy social media posts
Zeroshot multimodal named entity disambiguation for noisy social media postsSyo Kyojin
 
Class Diagram Extraction from Textual Requirements Using NLP Techniques
Class Diagram Extraction from Textual Requirements Using NLP TechniquesClass Diagram Extraction from Textual Requirements Using NLP Techniques
Class Diagram Extraction from Textual Requirements Using NLP Techniquesiosrjce
 
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유NAVER Engineering
 
Deep Dialog System Review
Deep Dialog System ReviewDeep Dialog System Review
Deep Dialog System ReviewNguyen Quang
 
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...AgileNetwork
 
How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...Wee Hyong Tok
 
​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!Eindhoven University of Technology / JADS
 
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORK
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORKSENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORK
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORKijnlc
 
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Network
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural NetworkSentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Network
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Networkkevig
 
Multilayered paper prototyping for user concept modeling
Multilayered paper prototyping for user concept modelingMultilayered paper prototyping for user concept modeling
Multilayered paper prototyping for user concept modelingUKOLN (dev), University of Bath
 
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneGDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneJames Anderson
 
Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory acijjournal
 

Similar to Bridging the gap between AI and UI - DSI Vienna - full version (20)

Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)
 
Requirements-Collector: Automating Requirements Specification from Elicitatio...
Requirements-Collector: Automating Requirements Specification from Elicitatio...Requirements-Collector: Automating Requirements Specification from Elicitatio...
Requirements-Collector: Automating Requirements Specification from Elicitatio...
 
Tomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPTomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLP
 
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
 
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...
Prerequisites of AI Techniques Making Robot To Perform Task With Human (autos...
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
Zeroshot multimodal named entity disambiguation for noisy social media posts
Zeroshot multimodal named entity disambiguation for noisy social media postsZeroshot multimodal named entity disambiguation for noisy social media posts
Zeroshot multimodal named entity disambiguation for noisy social media posts
 
Class Diagram Extraction from Textual Requirements Using NLP Techniques
Class Diagram Extraction from Textual Requirements Using NLP TechniquesClass Diagram Extraction from Textual Requirements Using NLP Techniques
Class Diagram Extraction from Textual Requirements Using NLP Techniques
 
D017232729
D017232729D017232729
D017232729
 
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
 
Deep Dialog System Review
Deep Dialog System ReviewDeep Dialog System Review
Deep Dialog System Review
 
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
 
How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...
 
​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!
 
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORK
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORKSENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORK
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORK
 
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Network
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural NetworkSentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Network
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Network
 
Multilayered paper prototyping for user concept modeling
Multilayered paper prototyping for user concept modelingMultilayered paper prototyping for user concept modeling
Multilayered paper prototyping for user concept modeling
 
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneGDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
 
Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory
 

Recently uploaded

VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiSuhani Kapoor
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130Suhani Kapoor
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystSamantha Rae Coolbeth
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...Suhani Kapoor
 

Recently uploaded (20)

VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data Analyst
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
 

Bridging the gap between AI and UI - DSI Vienna - full version

  • 2. ● Recommendation Systems (RecSys) ● Model Interpretability Technics (MI) ● Using MI for communication Outline
  • 5. What does it mean?
  • 6.
  • 7. RecSys with Deep Learning Autoencoders Meet Collaborative Filtering (Sedhain et al. AutoRec 2015) Session Based Recommendations with RNN (Hidasi et al. ICLR 2016) Wide & Deep Learning for Recommender Systems (Cheng et al. DLRS @ RecSys 2016)
  • 9. Response Suggestions Not what I wanted to say!
  • 13. Google Apple Search suggestions (auto-complete) moves to search results
  • 16. How to “understand” a model prediction?
  • 17. How to explain a model prediction? Which features contributed to the model prediction? And how? Example: Decision Tree
  • 18. “Why should I trust you?” - Explaining the Predictions of Any Classifier LIME: Local Interpretable Model-Agnostic Explanations
  • 19. LIME - Explains the model result - Enhances User Trust Supports Multi-class classifications, (example), text documents, images, etc. Packages exists for R, Python, etc.
  • 20. LIME ● Linear approximated model with a subset of the features - O(2n) ● Lowest distance to the original inputs ● Measuring the magnitude of the predictions distance
  • 21. SHAP - NIPS`17 SHapley Additive exPlanations “A Unified Approach to Interpreting Model Predictions” - Lundberg & Lee “Connects game theory with local explanations” SHAP Value - Feature importance as an impact (effect) on the output
  • 22. - The marginal value of an agent in a coalition (impact) - Average marginal contribution over all possible sequences Cooperative Games: http://www.lamsade.dauphine.fr/~airiau/Teaching/CoopGames/2011/coopgam es-7[8up].pdf Game Theory :: Shapley Values
  • 23. SHAP - NIPS`17 - Calculates N linear models for a subsets of the features - Calculates the impact on the result - How much each feature contribute as part of a ‘coalition’?
  • 24. SHAP - NIPS`17 Unifies: - LIME - Shapley sampling values - Shapley regression values - DeepLIFT . . . Better consistency with human intuition
  • 26. Visualizing Image Classifications As an interpretability method: ● What features are these networks really using? ● Do individual units have meaning? ● What roles are played by different layers? ● How are high-level concepts built from low-level ones?
  • 27. Visualizing Image Classifications Network Dissection: Quantifying Interpretability of Deep Visual Representations https://arxiv.org/pdf/1704.05796.pdf http://people.csail.mit.edu/bzhou/ppt/presentation_ICML_workshop.pdf
  • 29. Why? < 2014 Rule-based NLP 2014 - DL NLP Future DL identifies NLP Rules = Transparent = Black box
  • 30. How? CBOW (Word-vectors) LSTM / BiLSTM AutoEncoders
  • 31. What is encoded / captured in a vector? Fine-grained Analysis Of Sentence Embeddings Using Auxiliary Prediction Tasks (Adi et al. ICLR 2017) ● Trained a model to predict: sentence length, word existence, word-order ● 300-D CBOW - most effective (even for word order!) ● LSTM Autoencoder (500 to 750 D)
  • 32. What is encoded / captured in a vector? Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure (Hypkes et al. NIPS 2016) ● Visualizing activated neurons ● Researching compositional structures (trees) ● “The scientist who wrote the natural language research paper”
  • 33. Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems (Belinkov, Glass, NIPS 2017) ● Speech Recognition ● Visualizing layers ● Which layer/neuron is responsible to which phone (sound) What is encoded / captured in a vector?
  • 34. What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties (Conneau et al, ACL 2018) ● Ray Mooney ● Set of tests: ○ Surface information: word content, sentence length… ○ Syntactic Information: sentence ‘correctness’, hierarchical structure (depth) ○ Semantic Information (tense, word usage) ● Testing the information that is captured in different vectors ● Again CBOW and BiLSTM stars What is encoded / captured in a vector?
  • 35. RNN - Debugging Translation http://seq2seq-vis.io/ (Strobelt, 2018) Examines the 5 stages (Encoder, Decoder, Attention, Predictions, Beam-search) Nearest Neighbor Visualization - Examine model decisions - Connect decisions to previous examples - Test alternative decisions
  • 36. More open questions What linguistic structures can be captured by RNN? How does a model reach a decision? When would a model fail? What can’t the model do? http://u.cs.biu.ac.il/~yogo/blackbox2018.pdf
  • 38. Activities - Keep-Current Meetup - Learning by Doing - Machine Learning Seminar - Monthly in Vienna - Applied Machine Learning Course - PyTorch, Fast.AI
  • 39. Keep-Current Educational Project Filter newly released academic papers Hybrid recommendation system - Collaborative filtering - Content Similarity - User-Feedback (MOT) - RNN
  • 40. Methods Topic extraction (LDA / LSI) Document Vector Representation - Citation Correlation Matrix Decomposition - Paragraph Vectors - ELMo / BERT - Attention layer Similarity using Spotify ANNOY (Approximate Nearest Neighbours - Oh Yeah!)
  • 41. User-Input Key-words / topics Extraction Semantic Similarity Vector distance: - cosine similarity - Euclidean Distance - Word Mover’s Distance - PIP
  • 42. NIPS 18 PIP - Pairwise Inner Product
  • 45. Human-Machine Interactions - Ofra Amir PhD, Harvard University Intelligent Interactive Systems (advanced topics in information systems) - Technion, Israel AAMAS'18: - HIGHLIGHTS: Summarizing Agent Behavior to People - Agent Strategy Summarization
  • 46.
  • 48. Explain results - Keywords Contribution: Positive / Negative - Encourage User Feedback Model adaptation - Stronger Engagement
  • 50. Explainable AI - Models are prune to make mistakes - Interpretability to the rescue! - Supplies a peek into the features - Enhance user trust - Enables a constructive feedback
  • 51. Explainable AI using UI - Be Creative: Explainable UI - Using ‘stronger’ features for personalization Future Research: - Effective Agent Strategy Summary - Expected Behavior under Different Conditions

Editor's Notes

  1. Autonomous Agents and Multiagent Systems