SlideShare a Scribd company logo
1 of 25
Download to read offline
Dr. Susan McKeever
School of Computer Science TU Dublin
Susan.mckeever@tudublin.ie
July 2020
(Some) Developments in
Machine Learning
CeADAR
Where is ML at now?1
What are the key
developments?
2
Developments in Machine Learning
(ML)
Working well
Not so good
A good place to
start to find
trends
ML Timeline1
1950s 1980s 2010s
Expert Systems/ formal logic/
Rigid top down Reasoning
Human generated knowledge
Programming
ML Timeline1
1950s 1980s 2010s
Expert Systems/ formal logic/
Rigid top down Reasoning
Data driven approaches
Human generated knowledge Data Derived knowledge
Programming Training
Growth of Machine learning
Improved
Algorithms
Computers are
extremely good at
spotting patterns in
data – beyond
human capability
More
Data
More
Computing
Power
For well bounded tasks
Supervised learning
From labelled
Unsupervised learning
Unlabelled data
Etc!
Growth of Machine learning
Etc!
Growth of Machine learning
Machine learning is
powerful. And limited.
ML Snags
Machine learning system (trained CNNs) to
identify pneumonia from chest x-rays
dropped in accuracy when used in hospitals
outside of the ones it was trained in
Difficulty identifying the specific variables
driving the predictions
(The machine as able to work out which
hospital a scan had come from by analysing
small metal tokens placed in the corner of
scans, which differed across hospitals)
ML models will find patterns, but not always the ones we think of
or want
Explainability is crucial;
Researchers have already demonstrated how
to fool an AI system into misreading a stop
sign, by carefully positioning stickers on it1.
Self driving model mistakes motorbike for
bobsleigh with parachute
Facial-recognition systems can be deceived by
sticking a printed pattern on glasses or hats
(or painting dots – security issue)
Lack of (top down) reasoning – which humans employ all the time
ML models lack common sense
ML Snags
ML Snags
o 2019 National Institute for Standards and Technology in
US tested 200 facial recognition algorithms, finding that
many were significantly less accurate at identifying
black faces than white ones
o 2017 Amazon abandons its recruitment system which
favours male CVs. Circular problem trained on CVs of
previous successful applications, male etc.
ML models are only as intelligent as the data they are trained on
Bias in the data
ML Snags
ML models are only as intelligent as the data they are trained on
Lack of contextual knowledge; Lack of multi-modal consideration (visual + audio + …)
“Jake’s birthday party, for his fifth birthday; He’s happy, because kids love their
birthday. He’s about to make a wish and blow out the candles”
Hat
Face
Cake
Emotion = Happy
Patterns can be deceptive
Sloth or pastry?
March 13th 2020: Netherlands Court legislate that
SYRI an AI powered system designed to detect tax
and social benefit fraud is unlawful.
Works off big data from various government
departments and detects anomalous fraudulent
patterns.
Protection of right to private and family life:
violates Art 8 of the European Convention on
Human Rights
Ethical and privacy considerations
ML Snags
ML models may be relying on private data
ML Snags
Training data does not cover all cases (and is expensive)
Challenges developing Amazon Go”Stores - “Walk
in, Pick up, Leave”
Sensors/ cameras capture data about what
happening and ML models determine what the
customer has done
Edge cases:
Overlapping people?
Family groups?
Friends?
Pickup and putting down?
+ ……
“Incompleteness” of data should be known - “what valid scenarios are we missing” ?
Companies planning to exploit deep learning need large amounts of data
Companies need to work at process level to plan effective data labelling and ML deployment
ML Snags
Machine learning models lose intelligence over time
Concept Drift: Often incremental - e.g. Email spam, fraud detection mechanism
Sometimes abrupt – e.g.
- DNNs for flight terrorism
with new one way flight
patterns in COVID
- Facial recognition with
masks
Beware of static models - allow for re-training
A common trend across the themes is
- reducing reliance on expensive or hard to get
data
- Re-using knowledge
Trend - hybrid models
Combining two divided AI camps: Machine learning & Logical
reasoning
Combining data driven machine learning with
top down rules based reasoning for more
powerful, wider learning
Example: The neuro symbolic concept learner
From MIT, IBM and DeepMind (2019)
“We propose the Neuro-Symbolic Concept
Learner (NS-CL), a model that learns visual
concepts, words, and semantic parsing of
sentences without explicit supervision on any of
them; instead, our model learns by simply
looking at images and reading paired questions
and answers.!
Trend – Combine with external knowledge
Combining machine learning & pre existing external knowledge
sources
Does your model need to identify unseen new classes?
Instead of having to train for all classes – expand machine models with external knowledge bases
to allow models to identify new unseen classes
Zero Shot ; One Shot ; Few shot
Several active research projects in
Generalised zero shot learning:
Example:
Identifying previously unseen unknown images by using zero shot learning with Word2Vec based
semantic knowledge space
Using zero shot learning for identifying scenes in video
Trend - Ongoing march of Deep learning
Large data needed;
High performance
GPUs/ parallel archs
Dramatic
improvements in
State of the Art in
many domains: e,g
- NLP: speech
recognition, machine
translation,
- self driving cars
- image/ video
processing
- genome/ biological
applications
-
Transfer learning to avoid reinventing the wheel: e.g.
AlexNet/ VGG for re-use in computer vision
Unsupervised language embedding models such as Word2Vec, BERT, Elmo for re-use in NLP
Ongoing
optimisation on
accuracies and
speed
Trend – Greater Reliance on Synthetic Data
Artificially generated data that mimics the real data in terms of essential parameters, univariate and
multivariate distributions, cross-correlations between the variables and so on. Synthetic data can be
created algorithmically
Good for visual /audio data
Amazon Go Stores – Used graphics s/w to create virtual
shoppers and unusual or hard to find scenarios
Self driving cars - trained using high fidelity simulations
Other scenarios:
• Disaster prediction/ recovery models
• Wind farms
• Environmental models
Simulation s/w provides flexible, “free”,
private labels – for hard to acquire data cases
Trend – Greater Reliance on Synthetic Data
Concept: The generative network generates candidates while
the discriminative network evaluates them
Generative Adversarial networks
Invented by Ian Goodfellow in 2014
GANs generate synethetic data that resemble real world
data. They consist of unsupervised learning algorithms
that use a supervised loss as part of the training.
Can be used for a variety of data types- and data
conversions.
Very active area of research
Our use: to generate fake audio
Trend – Mass generation of & reuse of knowledge
Knowledge generation
- Knowledge generation factories – 3rd party data preparation market worth 1.5billion dollars in 2019,
- Third party services – e.g. Mechanical turk
Owning and selling this knowledge will be key
- Amazon Go Stores- now licencing its technology
- Why reinvent the wheel? E.g. ModelPlay host trained ML models for free or paid use
Research examples for core models – e.g. ResNet and VGG for image processing
- Chinese company MadaCode has 10K freelance
employees;
Trend
End of the black box for user-facing systems: Models must
have transparent decision making (and “what if” on feature
input)
LegalUsable
e.g. medical domain
Optimisation
By Data scientists
Explainable AI (XAI) is now a front and centre area of research in
machine learning ; Visualisations/ evaluation methods/ widening out
beyond image models. Particularly important for deep learning models
Two new demonstrators in CeADAR on way:
(1) Explainable AI for a deep learning model for structure data (using
Layer wise relevance propogation (LRP), LIME and SHAP
(2) Explainable AI for text
See SOTA documents!
Ethical
For Trust
Commercial
For end customers
X
Conclusion
A non exhaustive list of developments in a rapidly
changing environment!

More Related Content

What's hot

dell_ml_rm.ppt
dell_ml_rm.pptdell_ml_rm.ppt
dell_ml_rm.ppt
butest
 

What's hot (20)

Cognitive Computing : IBM Watson
Cognitive Computing : IBM WatsonCognitive Computing : IBM Watson
Cognitive Computing : IBM Watson
 
Artificial intelligence uses in productive systems and impacts on the world...
Artificial intelligence   uses in productive systems and impacts on the world...Artificial intelligence   uses in productive systems and impacts on the world...
Artificial intelligence uses in productive systems and impacts on the world...
 
General introduction to AI ML DL DS
General introduction to AI ML DL DSGeneral introduction to AI ML DL DS
General introduction to AI ML DL DS
 
II-SDV 2017: Auto Classification: Can/Should AI replace You?
II-SDV 2017: Auto Classification: Can/Should AI replace You? II-SDV 2017: Auto Classification: Can/Should AI replace You?
II-SDV 2017: Auto Classification: Can/Should AI replace You?
 
Big Data & Artificial Intelligence
Big Data & Artificial IntelligenceBig Data & Artificial Intelligence
Big Data & Artificial Intelligence
 
Deep Neural Networks for Machine Learning
Deep Neural Networks for Machine LearningDeep Neural Networks for Machine Learning
Deep Neural Networks for Machine Learning
 
Artificial Intelligence power point presentation document
Artificial Intelligence power point presentation documentArtificial Intelligence power point presentation document
Artificial Intelligence power point presentation document
 
1 machine learning demystified
1 machine learning demystified1 machine learning demystified
1 machine learning demystified
 
Steve Mills - Your Cognitive Future
Steve Mills - Your Cognitive FutureSteve Mills - Your Cognitive Future
Steve Mills - Your Cognitive Future
 
1 introduction to data science
1 introduction to data science1 introduction to data science
1 introduction to data science
 
Artificial Intelligence And Its Applications
Artificial Intelligence And Its ApplicationsArtificial Intelligence And Its Applications
Artificial Intelligence And Its Applications
 
Deep learning and neural network converted
Deep learning and neural network convertedDeep learning and neural network converted
Deep learning and neural network converted
 
dell_ml_rm.ppt
dell_ml_rm.pptdell_ml_rm.ppt
dell_ml_rm.ppt
 
AI for Science
AI for ScienceAI for Science
AI for Science
 
Artificial intel
Artificial intelArtificial intel
Artificial intel
 
ANALYSIS OF SYSTEM ON CHIP DESIGN USING ARTIFICIAL INTELLIGENCE
ANALYSIS OF SYSTEM ON CHIP DESIGN USING ARTIFICIAL INTELLIGENCEANALYSIS OF SYSTEM ON CHIP DESIGN USING ARTIFICIAL INTELLIGENCE
ANALYSIS OF SYSTEM ON CHIP DESIGN USING ARTIFICIAL INTELLIGENCE
 
Machine Learning for dummies!
Machine Learning for dummies!Machine Learning for dummies!
Machine Learning for dummies!
 
Bioinformatics and Artificial Intelligence (AI) the interrelation between the...
Bioinformatics and Artificial Intelligence (AI) the interrelation between the...Bioinformatics and Artificial Intelligence (AI) the interrelation between the...
Bioinformatics and Artificial Intelligence (AI) the interrelation between the...
 
ML vs AI
ML vs AIML vs AI
ML vs AI
 
20181212 ibm aot
20181212 ibm aot20181212 ibm aot
20181212 ibm aot
 

Similar to Webinar trends in machine learning ce adar july 9 2020 susan mckeever

Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
eswaralaldevadoss
 
11 Insane Machine Learning Myths Debunked for You!
11 Insane Machine Learning Myths Debunked for You!11 Insane Machine Learning Myths Debunked for You!
11 Insane Machine Learning Myths Debunked for You!
Kavika Roy
 
Principles of Artificial Intelligence & Machine Learning
Principles of Artificial Intelligence & Machine LearningPrinciples of Artificial Intelligence & Machine Learning
Principles of Artificial Intelligence & Machine Learning
Jerry Lu
 

Similar to Webinar trends in machine learning ce adar july 9 2020 susan mckeever (20)

Artificial intelligence slides beginners
Artificial intelligence slides beginners Artificial intelligence slides beginners
Artificial intelligence slides beginners
 
Lecture1 introduction to machine learning
Lecture1 introduction to machine learningLecture1 introduction to machine learning
Lecture1 introduction to machine learning
 
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
 
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSISUNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
 
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSISUNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
UNCOVERING FAKE NEWS BY MEANS OF SOCIAL NETWORK ANALYSIS
 
The Future is Here: 8 Emerging Technologies to Watch in 2023
The Future is Here: 8 Emerging Technologies to Watch in 2023The Future is Here: 8 Emerging Technologies to Watch in 2023
The Future is Here: 8 Emerging Technologies to Watch in 2023
 
11 Insane Machine Learning Myths Debunked for You!
11 Insane Machine Learning Myths Debunked for You!11 Insane Machine Learning Myths Debunked for You!
11 Insane Machine Learning Myths Debunked for You!
 
The Ultimate Guide to Machine Learning (ML)
The Ultimate Guide to Machine Learning (ML)The Ultimate Guide to Machine Learning (ML)
The Ultimate Guide to Machine Learning (ML)
 
Modern signal processing is dead without machine learning! 5th july 2020
Modern signal processing is dead without machine learning! 5th july 2020Modern signal processing is dead without machine learning! 5th july 2020
Modern signal processing is dead without machine learning! 5th july 2020
 
Principles of Artificial Intelligence & Machine Learning
Principles of Artificial Intelligence & Machine LearningPrinciples of Artificial Intelligence & Machine Learning
Principles of Artificial Intelligence & Machine Learning
 
State of AI Report 2023 - Air Street Capital
State of AI Report 2023 - Air Street CapitalState of AI Report 2023 - Air Street Capital
State of AI Report 2023 - Air Street Capital
 
AI | Explore Machine Learning
AI | Explore Machine LearningAI | Explore Machine Learning
AI | Explore Machine Learning
 
How to choose the right AI model for your application?
How to choose the right AI model for your application?How to choose the right AI model for your application?
How to choose the right AI model for your application?
 
Artificial intelligence: PwC Top Issues
Artificial intelligence: PwC Top IssuesArtificial intelligence: PwC Top Issues
Artificial intelligence: PwC Top Issues
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
 
Automated machine learning: the new data science challenge
Automated machine learning: the new data science challengeAutomated machine learning: the new data science challenge
Automated machine learning: the new data science challenge
 
Popular Machine Learning Myths
Popular Machine Learning Myths Popular Machine Learning Myths
Popular Machine Learning Myths
 
Deep learning vs ML vs AI vs DS .pdf
Deep learning vs ML vs AI vs DS .pdfDeep learning vs ML vs AI vs DS .pdf
Deep learning vs ML vs AI vs DS .pdf
 
Machine learning - session 1
Machine learning - session 1Machine learning - session 1
Machine learning - session 1
 
Copy of State of AI Report 2023 - ONLINE.pptx
Copy of State of AI Report 2023 - ONLINE.pptxCopy of State of AI Report 2023 - ONLINE.pptx
Copy of State of AI Report 2023 - ONLINE.pptx
 

Recently uploaded

➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
amitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
gajnagarg
 
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
gajnagarg
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
only4webmaster01
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
gajnagarg
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
karishmasinghjnh
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 

Recently uploaded (20)

➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24  Building Real-Time Pipelines With FLaNKDATA SUMMIT 24  Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
 
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning Approach
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 

Webinar trends in machine learning ce adar july 9 2020 susan mckeever

  • 1. Dr. Susan McKeever School of Computer Science TU Dublin Susan.mckeever@tudublin.ie July 2020 (Some) Developments in Machine Learning CeADAR
  • 2. Where is ML at now?1 What are the key developments? 2 Developments in Machine Learning (ML) Working well Not so good A good place to start to find trends
  • 3. ML Timeline1 1950s 1980s 2010s Expert Systems/ formal logic/ Rigid top down Reasoning Human generated knowledge Programming
  • 4. ML Timeline1 1950s 1980s 2010s Expert Systems/ formal logic/ Rigid top down Reasoning Data driven approaches Human generated knowledge Data Derived knowledge Programming Training
  • 5. Growth of Machine learning Improved Algorithms Computers are extremely good at spotting patterns in data – beyond human capability More Data More Computing Power For well bounded tasks Supervised learning From labelled Unsupervised learning Unlabelled data
  • 7. Etc! Growth of Machine learning Machine learning is powerful. And limited.
  • 8. ML Snags Machine learning system (trained CNNs) to identify pneumonia from chest x-rays dropped in accuracy when used in hospitals outside of the ones it was trained in Difficulty identifying the specific variables driving the predictions (The machine as able to work out which hospital a scan had come from by analysing small metal tokens placed in the corner of scans, which differed across hospitals) ML models will find patterns, but not always the ones we think of or want Explainability is crucial;
  • 9. Researchers have already demonstrated how to fool an AI system into misreading a stop sign, by carefully positioning stickers on it1. Self driving model mistakes motorbike for bobsleigh with parachute Facial-recognition systems can be deceived by sticking a printed pattern on glasses or hats (or painting dots – security issue) Lack of (top down) reasoning – which humans employ all the time ML models lack common sense ML Snags
  • 10. ML Snags o 2019 National Institute for Standards and Technology in US tested 200 facial recognition algorithms, finding that many were significantly less accurate at identifying black faces than white ones o 2017 Amazon abandons its recruitment system which favours male CVs. Circular problem trained on CVs of previous successful applications, male etc. ML models are only as intelligent as the data they are trained on Bias in the data
  • 11. ML Snags ML models are only as intelligent as the data they are trained on Lack of contextual knowledge; Lack of multi-modal consideration (visual + audio + …) “Jake’s birthday party, for his fifth birthday; He’s happy, because kids love their birthday. He’s about to make a wish and blow out the candles” Hat Face Cake Emotion = Happy
  • 12. Patterns can be deceptive
  • 14. March 13th 2020: Netherlands Court legislate that SYRI an AI powered system designed to detect tax and social benefit fraud is unlawful. Works off big data from various government departments and detects anomalous fraudulent patterns. Protection of right to private and family life: violates Art 8 of the European Convention on Human Rights Ethical and privacy considerations ML Snags ML models may be relying on private data
  • 15. ML Snags Training data does not cover all cases (and is expensive) Challenges developing Amazon Go”Stores - “Walk in, Pick up, Leave” Sensors/ cameras capture data about what happening and ML models determine what the customer has done Edge cases: Overlapping people? Family groups? Friends? Pickup and putting down? + …… “Incompleteness” of data should be known - “what valid scenarios are we missing” ? Companies planning to exploit deep learning need large amounts of data Companies need to work at process level to plan effective data labelling and ML deployment
  • 16. ML Snags Machine learning models lose intelligence over time Concept Drift: Often incremental - e.g. Email spam, fraud detection mechanism Sometimes abrupt – e.g. - DNNs for flight terrorism with new one way flight patterns in COVID - Facial recognition with masks Beware of static models - allow for re-training
  • 17. A common trend across the themes is - reducing reliance on expensive or hard to get data - Re-using knowledge
  • 18. Trend - hybrid models Combining two divided AI camps: Machine learning & Logical reasoning Combining data driven machine learning with top down rules based reasoning for more powerful, wider learning Example: The neuro symbolic concept learner From MIT, IBM and DeepMind (2019) “We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers.!
  • 19. Trend – Combine with external knowledge Combining machine learning & pre existing external knowledge sources Does your model need to identify unseen new classes? Instead of having to train for all classes – expand machine models with external knowledge bases to allow models to identify new unseen classes Zero Shot ; One Shot ; Few shot Several active research projects in Generalised zero shot learning: Example: Identifying previously unseen unknown images by using zero shot learning with Word2Vec based semantic knowledge space Using zero shot learning for identifying scenes in video
  • 20. Trend - Ongoing march of Deep learning Large data needed; High performance GPUs/ parallel archs Dramatic improvements in State of the Art in many domains: e,g - NLP: speech recognition, machine translation, - self driving cars - image/ video processing - genome/ biological applications - Transfer learning to avoid reinventing the wheel: e.g. AlexNet/ VGG for re-use in computer vision Unsupervised language embedding models such as Word2Vec, BERT, Elmo for re-use in NLP Ongoing optimisation on accuracies and speed
  • 21. Trend – Greater Reliance on Synthetic Data Artificially generated data that mimics the real data in terms of essential parameters, univariate and multivariate distributions, cross-correlations between the variables and so on. Synthetic data can be created algorithmically Good for visual /audio data Amazon Go Stores – Used graphics s/w to create virtual shoppers and unusual or hard to find scenarios Self driving cars - trained using high fidelity simulations Other scenarios: • Disaster prediction/ recovery models • Wind farms • Environmental models Simulation s/w provides flexible, “free”, private labels – for hard to acquire data cases
  • 22. Trend – Greater Reliance on Synthetic Data Concept: The generative network generates candidates while the discriminative network evaluates them Generative Adversarial networks Invented by Ian Goodfellow in 2014 GANs generate synethetic data that resemble real world data. They consist of unsupervised learning algorithms that use a supervised loss as part of the training. Can be used for a variety of data types- and data conversions. Very active area of research Our use: to generate fake audio
  • 23. Trend – Mass generation of & reuse of knowledge Knowledge generation - Knowledge generation factories – 3rd party data preparation market worth 1.5billion dollars in 2019, - Third party services – e.g. Mechanical turk Owning and selling this knowledge will be key - Amazon Go Stores- now licencing its technology - Why reinvent the wheel? E.g. ModelPlay host trained ML models for free or paid use Research examples for core models – e.g. ResNet and VGG for image processing - Chinese company MadaCode has 10K freelance employees;
  • 24. Trend End of the black box for user-facing systems: Models must have transparent decision making (and “what if” on feature input) LegalUsable e.g. medical domain Optimisation By Data scientists Explainable AI (XAI) is now a front and centre area of research in machine learning ; Visualisations/ evaluation methods/ widening out beyond image models. Particularly important for deep learning models Two new demonstrators in CeADAR on way: (1) Explainable AI for a deep learning model for structure data (using Layer wise relevance propogation (LRP), LIME and SHAP (2) Explainable AI for text See SOTA documents! Ethical For Trust Commercial For end customers X
  • 25. Conclusion A non exhaustive list of developments in a rapidly changing environment!