The Machine Learning Revolution in AI Luc De Raedt luc.deraedt@cs.kuleuven.be
What is Machine Learning?
Machine Learning A machine learns when it improves it performance on a specific task with experience Central to Artificial Intelligence There can be no intelligence without learning
AlphaGo Machine = AlphaGo Player Program Task = playing G Performance = % of won games Experience = huge data base of games + self play Lee Sedol
Spam Filter Machine = e-mail program, spamfilter Task = classify e-mails Performance = accuracy Experience = your past input
Automating Science Eve, an artificially-intelligent robot scientist, can make drug discovery faster and much cheaper. [King et al. Nature 04, Science 09] Robot Scientist Automating Data Science
Why is it useful?
Why Machine Learning? It applies to any application where there is (a lot of) data It is very practical some programs too complex to program by hand easier to generate data than to build programs by hand adaptation and personalisation
Why Machine Learning? It applies to any application where there is (a lot of) data It is very practical some programs too complex to program by hand The enabling technology in natural language processing, web search / information retrieval computer vision & speech understanding easier to generate data than to build programs by hand robotics (& self-driving cars) adaptation and personalisation bioinformatics analysing medical EHR & images
How does it work?
How does it work? Machine learning is all about learning functions f(input) => output. different types of functions different types of data (supervised, unsupervised, reinforcement ) different criteria (loss or value function) Different schools in machine learning make different choices
Where does the data come from? learning from examples (supervised / unsupervised) good/bad moves? just moves? learning by imitation (Behavioral cloning) imitate de world champion learning from rewards (Reinforcement learning) just play, reward = board config. / wins / losses the whole AI problem in a nutshell
Donald Michie s Menace Donald Michie (2007) Menace (1961) Machine Educable Noughts And Crosses Engine slides Menace : thanks to Johannes Fürnkranz
s move
s move
s move
s move
s move Choose box on the basis of current position
s move Choose box on the basis of current position
s move Choose box on the basis of current position
s move Choose box on the basis of current position Execute move
s move Choose box on the basis of current position Execute move
Menace Machine = 287 boxes + pearls Encodes probabilistic function P(box, color) = probability of move Learning a function upon loss: retain all used pearls upon winning: put used pearls back + an extra one of the same color Richard Belmann Q (s, a) =R(s, a)+ s P (s s, a) max a Q (s,a )
Menace Machine = 287 boxes + pearls Encodes probabilistic function P(box, color) = probability of move Learning a function upon loss: retain all used pearls Q (s, a) = R(s, a) + s P (s s, a) max a Q (s, a ) upon winning: put used pearls back + an extra one of the same color Richard Belmann Q (s, a) =R(s, a)+ s P (s s, a) max a Q (s,a )
Three important points
Learning AND Reasoning needed System 1 thinking fast can do things like solve 2+2=? and recognise a car System 2 thinking slow can reason about complex logic problems (IQ tests) and reason about priority in traffic Alternative terms: learning vs reasoning, data-driven vs knowledge driven, symbolic vs sub AlphaGo incorporates learning and reasoning Machine learned video games cannot change the rules of the game
There are five schools in ML Tribe rigins Master Algorithm Symbolists Logic, philosophy Inverse deduction Connectionists Neuroscience Backpropagation Evolutionaries Evolutionary biology Genetic programming Bayesians Statistics Probabilistic inference Analogizers Psychology Kernel machines Pedro Domingos found it both exciting and scary to see that president i Jinping of China reads his book
There are many remaining challenges Getting the right data bias, fairness, privacy, etc. (ethical concerns) Combining learning and reasoning Providing explanations and interpretable models beyond the deep neural network black-boxes Providing guarantees for software verification and validation Akhtar & Mian, IEEE Access
What to expect?
What does this imply? AI is the new electricity (Andrew Ng) Much like the rise of electricity, which started about 100 years ago; AI will revolutionize every major industry. (Industry 4.0) We will see many intelligent assistants for specific (routine) tasks; There is a really high potential, AI can bring a lot of good to society; there are also some caveats
What does this imply? AI as the magic wand There is a lot of hype; the expectations are often unrealistic The press (and the GAFA companies doing AI) create sensational stories on purpose (?) Abuse of the term AI: everything is AI and everybody is jumping on the wagon AI summers and winters cf. Gartner hype cycle for emerging technologies
Take away Insight into the nature of AI and ML AI & ML have a lot of potential, they are here to stay Go for a broad view on AI, we need all schools of ML, we need learning and reasoning, there are remaining challenges Beware of the hype & learn from the past!