Blogs (61) >>
Wed 18 Jul 2018 14:30 - 15:00 at Bangkok - Session #2 Chair(s): Artem Pelenitsyn

Recent availability of large amounts of sensor data from Internet of Things devices opens up the possibility for software systems to dynamically provide fine-grained adaptations to the observed environment conditions, rather than executing only static hard-coded behaviors. However, in current adaptive systems such adaptations still need to be specified beforehand, making the development process cumbersome as well as restricting the system adaptations only to those situations foreseen by the developers. We propose that adaptations should instead be generated by machine learning techniques at run time. Adaptive systems should incorporate an adaptation engine, which, through a mix of supervised and unsupervised learning, learns adaptive behaviors, and packages them into reusable software adaptations. We illustrate this idea with a simple proof-of-concept example using Context-oriented Programming, and focus on the challenges of implementing such an approach in the development of adaptive systems.

Wed 18 Jul

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

14:00 - 15:30
Session #2ML4PL at Bangkok
Chair(s): Artem Pelenitsyn Czech Technical University in Prague
14:00
30m
Talk
Buffer Overflow Detection for C Programs is Hard to Learn
ML4PL
Cristina Cifuentes Oracle Labs, Yang Zhao Oracle Labs, Xingzhong Du Oracle Labs, Paddy Krishnan
14:30
30m
Talk
Generating Software Adaptations using Machine Learning
ML4PL
Nicolás Cardozo Universidad de los Andes, Ivana Dusparic Trinity College Dublin, Ireland
15:00
30m
Talk
Detecting anomalies in Kotlin code
ML4PL
Timofey Bryksin , Victor Petukhov ITMO University, Kirill Smirenko Saint Petersburg State University, Nikita Povarov JetBrains