AI4EU’s project partners will organise a workshop on "Integrative Machine Learning” as an additional activity of the on-going event: International Conference on Machine Learning, Optimisation, and Data Science (LOD2020) tomorrow from 14:40-18:10 on the 23rd July 2020.
Machine learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns.
Addressing the challenges, the workshop covers topics in “Integrative Machine Learning”, where Machine Learning is augmented with knowledge representation and logic reasoning.
In particular, the organisers will discuss the different trade-offs on the application of constraint-based vs probabilistic solutions to represent the knowledge. Other open research problems will be discussed like: are directed or undirected models more suitable for Integrative ML?
How to allow a flexible reasoning process without limiting the scalability of machine learning solutions? How to get the advantage of modern tensor-based computational frameworks within integrative ML? Is an induction/deduction loop possible in machine learning like it happens in the development of human cognition?
The Workshop will be streamed from the following google meet room:
https://meet.google.com/rga-yvtm-dkb
or at the following live stream
https://stream.meet.google.com/stream/cdba0b85-2ba6-4c34-a594-770a772feff7
The workshop is open, so feel free to forward the links to anyone that might be interested.
For details programme and schedule, please visit the LINK.
In the background, Machine Learning solutions tend to be vertical, in the sense that they can well solve the specific task they are trained for, but the lack of emergence of general and portable intelligence is nowadays seen as a major limitation.
Furthermore, machine learning is still limited when there is a need for consistent and robust decisions in complex environments, where the learning data can inevitably cover a small portion of all possible variants.
The integration of machine learning and logical reasoning is an open-research problem, which could overtake these fundamental limitations, leading to the development of real intelligent agents.
The Sixth International Conference on Machine Learning, Optimisation, and Data Science is going on from July 19-23, 2020 in Certosa di Pontignano, Siena – Tuscany, Italy, online as the workshop does.
The 6th Annual Conference on Machine Learning, Optimisation and Data science (LOD) is an international conference on machine learning, computational optimisation, data science that includes invited talks, tutorial talks, special sessions, industrial tracks, demonstrations and oral and poster presentations of refereed papers.
The International Conference on Machine Learning, Optimisation, and Data Science (LOD) has established itself as a premier interdisciplinary conference in machine learning, computational optimisation, and data science. It provides an international forum for presentations of original multidisciplinary research results, as well as exchange and dissemination of innovative and practical development experiences.
From 2015, the LOD Conference brings academics, researchers and industrial researchers together in a unique multidisciplinary community to discuss the state of the art and the latest advances in the integration of machine learning, optimisation and data science to provide the scientific and technological foundations for interpretable, explainable and trustworthy AI adopting, from 2017, the Asilomar AI Principles.