DTAI Thesis Topics Dept. Computer Science KU Leuven 2020-2021 - - PowerPoint PPT Presentation
DTAI Thesis Topics Dept. Computer Science KU Leuven 2020-2021 http://people.cs.kuleuven.be/~luc.deraedt/dtaithesis20-21.pdf Luc De Raedt Lab for Declarative Languages and Artificial Intelligence Machine Learning 3 ZAP , 1 res. manager
KU Leuven 2020-2021
http://people.cs.kuleuven.be/~luc.deraedt/dtaithesis20-21.pdf Luc De Raedt
2
Machine Learning
Declarative Languages and Systems
3 ZAP , 1 res. manager ± 5 post-docs ± 25 Ph.D. students 4 ZAP ± 3 post-docs ±12 Ph.D. students
Bruynooghe & De Schreye retired Demoen retired still interested in education in informatics
Self-driving cars - Eve (the robot scientist) Siri IBM Watson in Jeopardy and “Machine Reading” AlphaGo — (Deep) learning …
3
4
Typically associated with deep/ probabilistic learning. Focus on patterns and data. Involves multi-step, multi-modal “reasoning”. Focus on knowledge and logical inference Machine Learning Reasoning System 1: instinct, reflexes Fast Thinking System 2: deliberate, logical Slow Thinking Associations: Seeing, observing What if I see …? Interventions: Doing, intervening Counterfactuals: Retrospection, understanding What if I do or had done …? Great results but only reaches 90% Required to be actionable, trustworthy, … “Is it a stop sign?” “Do you stop at a stop sign?” One of the grand challenges in AI: Combine reasoning with machine learning.
5
Henry Kautz, Former president of Association for the Advancement of Artificial Intelligence: “Violent agreement on the need to bring together the neural and symbolic traditions” Daniel Kahneman, Nobel prize laureate: “We need System I and System II with a representation of the world” Yann LeCun, Turing Award winner: “Our next challenge for Deep Learning is learning to reason.” February 2020: Yoshua Bengio, Turing Award winner: “We need to expand Deep Learning from System I to System II” January 2020: Holger Hoos & Philipp Slusallek, CLAIRE: “European Researchers look beyond deep learning” AI For Europe — COM(2018) 237 ICT-48-2020 “European network of AI excellence centres”: “Necessary competencies are: learning and reasoning, XAI, unbiased AI, safety, reliability and verifiability.” July 2019: Minister Muyters / Crevits, Flemish AI Action Plan: “Hybrid AI to support reasoning […] and complex decision making” Ursula von der Leyen, President of the Commission: “Combining symbolic reasoning with deep neural networks may help us improve explainability
6
Machine Learning & Data Mining how to extract knowledge from data Uncertainty reasoning how to represent and reason about uncertainty Knowledge Representation how to represent and reason about knowledge
7
Declarative = specify the what rather than the how Different types of languages Logic Functional Constraints Probabilistic
Explainable / Understandable AI
8
Thesis can focus on one or more aspects, depending on interests student This presentation does not go in depth about techniques but every thesis does
Overview of research illustrations of possible thesis topics. List of contact persons for topics Full information — see online (needs update)
(dtai.cs.kuleuven.be/research) iOwn topic should be aligned with interests professor
9
11
“Standard” machine learning develop new algorithms for machine learning Decision Trees Predictive Clustering Probabilistic Graphical Models PU Learning evaluation of machine learning (ROC etc.)
Predictive learning and clustering
Contact: Hendrik Blockeel, Jesse Davis
12
A B C D A B C D ? ? ? ? A B C D ! ? ? ?
learning online model ABD→C learner “fill in the missing values”
Contact: Hendrik Blockeel
X1 X2 X3 X4 X5 X6
Predictive learning and clustering
13
Automated Data Science
Contact: Luc De Raedt
Can we (partly) automate data science ? Can we automatically derive the right features ? the right representations ? Can we automatically discover what we can learn / predict ? Can we learn constraints ? Can we automatically wrangle the data ? (programming by example) Example database about students, professors, courses, and marks … we use a SpreadSheet Context The SYNTH project — https://synth.cs.kuleuven.be/ the democratisation of Data Science the automation of Data Science
One example : learning constraints
AI: Can we automate X ? (where X requires intelligence) X = Science -> X = Data Science Would be pretty useful It is about automating the whole process ! <>AutoML
14 Selection and Preprocessing Data Mining
Interpretation and Evaluation
Data Consolidation
Knowledge
Pattern Prepared Consolid
KDD Process [Fayyad] SYNTH Project
Contact: Luc De Raedt
Automated Data Science
15
Key open question in AI — integrate
Probabilistic reasoning Logical or relational representations Machine learning
Contact: Luc De Raedt, Hendrik Blockeel, Jesse Davis
statistical relational learning
Probabilistic Programming and Statistical Relational Learning
probabilistic programming
16
E.g. ProbLog: a probabilistic Prolog P( hears_alarm(john) | burglary = true) ? Challenges on inference, learning, implementation, application, ...
i
0.05 :: burglary. 0.01 :: earthquake. 0.7 :: hears_alarm(john). 0.6 :: hears_alarm(mary). alarm :- burglary. alarm :- earthquake. calls(Pers) :- alarm, hears_alarm(Pers).
Probabilistic Programming and Statistical Relational Learning
Contact: Luc De Raedt
DeepProbLog
17
[Manhaeve NeurIPS 2018]
+ = 16 + = 3 + = 4 + = ?
Data Query Answer
+ = ?
Query Answer
Logic + Probability + Neural Networks
Contact: Hendrik Blockeel, Luc De Raedt
18
Travian: A massively multiplayer real-time strategy game Commercial game run by TravianGames GmbH ~3.000.000 players spread over different “worlds”
[Thon et al. ECML 08]
Can we build a model of this world ? Can we use it for playing better ?
Probabilistic Programming and Statistical Relational Learning
Contact: Luc De Raedt
Robotics (and Vision)
Put the blue pyramid on the block in the box Bring me the tea pot and the sugar
Winograd’s SHRDLU
The CLEVR Dataset and Variations
20
Contact: Luc De Raedt, Hendrik Blockeel, Jesse Davis, & Wannes Meert
Verification of software has a long tradition (eg model checking techniques) How to verify systems that learn ? that use AI ? Our approach — combined principles of probabilistic logics with verification Topics inductive synthesis of specifications Markov Decision Processes (& reinforcement leanring) Derive properties of learned systems …
Verifying AI & ML systems
Contact: Marc Denecker, Gerda Janssens
IDP Advanced KBS system developed by group FO(.) language rooted in predicate logic and logic programming separation of domain knowledge and problem solving Language extensions to increase expressivity E.g. design patterns for FO(.) (past thesis) Better solvers and more inference methods E.g. a solver for rational numbers (past thesis)
21
Knowledge-Base Systems
Contact: Marc Denecker, Gerda Janssens
Three themes for students : logical modeling of interesting AI problem + expressing AI knowledge domains logical analysis and implementation of software systems and tasks + software by applying inference on specifications Advanced algorithmics and implementation + extending/optimising the IDP software package.
22
Knowledge-Base Systems
Analysing medieval manuscripts
vocabulary Vms { extern vocabulary V IsSource(Manuscript ) } theory Tms : Vms { { ! x : IsSource(x) <- ~ ? y : CopiedBy(y, x) & VariantIn(y) = VariantIn(x). } } term NbOfSources : Vms { #{ x : IsSource(x) } } procedure minSources(feature) { setvocabulary(feature, Vms) return minimize(Tms, feature, NbOfSources)[1] }
23
Applications of the Knowledge Base System Paradigm
Contact: Marc Denecker, Gerda Janssens
Software = Knowledge Base + Logical Inference + User Interface E.g., An interactive configuration system for an insurance company AIM : Build cheap, correct, reusable, maintainable software from a logical specification
24 Applications of the Knowledge Base System Paradigm
25 Applications of the Knowledge Base System Paradigm
Winning the RuleML Challenge Insurance application Propagation constraints and choices Fill out necessary values
Contact: Marc Denecker, Gerda Janssens
Advanced algorithmics and implementation + extending/
help us win the next CP or ASP competition + E.g., structuring search space as a hierarchy of search problems + E.g., linear programming techniques in IDP + E.g., improved computation of definitions + E.g., algorithms for revision inference (updating solutions)
26
Knowledge-Base Systems
Contact: Tom Schrijvers, Marc Denecker, & Luc De Raedt
27
Constraints
and optimization problems — formalisation
28
Functional Programming
Haskell
★ Explicit Side-Effects
★ Advanced Type Systems
★ Domain-Specific Languages
★ Much more…
Monads Effect Handlers Transformers Type Classes Polymorphism Kinds Design Infrastructure Applications
Op onderzoeksgebied werken we rond alle aspecten van functionele talen, en Haskell in het bijzonder. Actuele onderwerpen zijn:
29 Functional Programming
λ calculus 1936 Alonzo Church 1958 Lisp John McCarthy 1973 ML Robin Milner 1987 Haskell Haskell Committee 2014 Java 8 Swift 2011 C++11
Functional Languages Mainstream
2007 C#
FP now mainstream
Haskell Language + GHC Compiler Finance Many Others Telecom
Haskell in industry
UITLEG: Heel wat interessante uitdagingen komen voort uit de groeiende mainstream adoptie van Functional Programming. Hoe langer hoe meer bedrijven gaan aan de slag met functionele talen zoals Haskell en F# (F-sharp), en mainstream talen zoals Java en C# adopteren functionele concepten.
30 Functional Programming
GHC compiler abs x | x >= 0 = x | x < 0 = -x your oracle
UITLEG:
guards in Haskell-programma’s alle gevallen dekken
31 Declarative Programming Languages
★ Type Checking ★ Termination Analysis ★ Reasoning about Coroutines
UITLEG: Je kent de Declaratieve Taal Prolog uit het vak Declaratieve Talen. Op onderzoeksgebied werken we rond de automatische analyse van Prolog- programma’s. Actuele onderwerpen zijn:
32 Declarative Programming Languages
append([],L,L). append([X|Xs],Ys,[X|Zs]) :- append(Xs,Ys,Zs).
powerful dynamic flexible
correctness termination
UITLEG: Delcaratieve talen zoals Prolog zijn heel krachtig, dynamisch en flexibel. De uitdaging bestaat erin om automatisch belangrijke eigenschappen af te leiden van Prolog programma’s om na te gaan of ze correct zijn, altijd eindigen en hoe je ze efficient kan compileren.
bugs
Delcarative Programming Languages
33
Prosyn Expert System 1 MegaLoC Prolog
Case Study: Industrial Partner
Prolog Program Types
+
your type checker
UITLEG: Prolog is een ongetypeerde taal. Hierdoor is het makkelijke om via schrijffouten moeilijk op te sporen bugs te introduceren. In deze thesis ontwikkel je een type systeem voor Prolog: De programmeur schrijft type-signaturen voor zijn predikaten, en jouw type checker gebruikt die om bugs op te sporen. Je evalueert je type checker op het Prosyn expert systeem van onze
35
Contact: Wannes Meert
Theses with:
Boeing Jetairfly EuroMillions Basketball League 3E Sirris Thomson-Reuters Xenit Pepite Melexis Flanders Make imec Cern …
36
Machine Learning for sports Soccer & basketball E-sports
Sports Analytics
Contact: Jesse Davis
Strategy detection Performance analysis & prediction Scouting
37
Sports Analytics
Soccer analytics
Model flow of a game Quantify team performance Learn aging curves of players
Basketball analytics
Detect surprising events
38
Sports Analytics
Continuous monitoring Injury risk profiles
39
Performance management and Injury prevention Sensor fusion for surface detection and skill detection in runners Kinect monitoring for qualitative feedback during rehabilitation
40
Contact: Jesse Davis, Hendrik Blockeel, Wannes Meert
Anomalies are behaviors that do not conform to what is expected Anomalies typical entail significant costs such as fraudulent credit card transaction, excess usage, etc. Topics: Design new algorithms to detect anomalies, Applications, e.g., airplanes, CERN, resources
Typically, no usage at night, Except for sporadic maintenance
Contact: Wannes Meert, Jesse Davis, Hendrik Blockeel, Luc De Raedt
Large Hadron Collider maintenance (CERN)
Analysing data from airplanes
Anomaly Detection
Spreadsheets
http://dtai.cs.kuleuven.be
Example use case: Automatic Engineer Goal: Learn constraints and programs over heterogeneous knowledge sources to assist engineers in proposing new designs, finding similar designs, and verifying designs.
Technical drawings Standards Measurements Active learning Probabilistic programming Constraint programming
The automatic Engineer
Contact: Wannes Meert
Algoritmic perspective on creative behaviour (Help) generate e.g. humor, music, …
44
Contact: Luc De Raedt
Thesis Thomas Winters
I like my men like I like my graves: nameless. I like my coffee like I like my country: cold.
45 Luc De Raedt
Artificial intelligence, reasoning about uncertainty, action- and activity learning, machine learning, data mining, constraint programming, probabilistic programming (ProbLog), automated data science, language for mining and learning. Applications in natural language, vision, robotics, automatic programming. Verification of AI and ML. Computational Creativity.
Hendrik Blockeel
Machine learning, data mining, anomaly detection, tree ensembles, probabilistic logics, declarative approaches to data mining. Application domains include engineering, AI, fintech, linguistics.
Jesse Davis
Machine learning, data mining for personalized medicine. Artificial intelligence, statistical relational learning, transfer learning, anomaly detection Applications in healthcare (e.g., clinical practice, physical therapy, medical and biological texts, etc.). Applications to sport (e.g., football and basketball)
Wannes Meert
Probabilistic programming and methods. Data Science Applications. Applications in
46 Gerda Janssens
Performant probabilistic ILP data mining systems, integration of logic programming techniques in the knowledge representation language FO(.), program analysis and abstract interpretation, implementations of logic programs, verification of functional equivalence of C programs
Bart Demoen
Schools onderwijs in de informatica / Education in informatics
Marc Denecker
Constraint programming, Knowledge Base Systems, SAT solving, declarative languages (formal modelling languages), Applications in configuration, scheduling, optimization, security, business rule systems, executable formal software specifications, logical workflow languages.
Tom Schrijvers
functional programming, constraint and logic programming, type systems, programming language theory, programming language design and implementation, program analysis
Check out dtai-web for more details (needs an update)
Advisable to contact promotors or daily advisors before selecting a topic Also, attend thesis info market after Easter Holidays