Supervision by observation using inductive programming Jos - - PowerPoint PPT Presentation
Supervision by observation using inductive programming Jos Hernndez-Orallo (project leader: Carlos Monserrat) Departament de Sistemes Informtics i Computaci, Universitat Politcnica de Valncia, Spain. jorallo@dsic.upv.es AAIP2015
1
José Hernández-Orallo (project leader: Carlos Monserrat)
Departament de Sistemes Informàtics i Computació, Universitat Politècnica de València, Spain. jorallo@dsic.upv.es
AAIP’2015 – Approaches and Applications of Inductive Programming, Dagstuhl Seminar 15442, October 25-30
2
3
A significant progress has recently taken place. Many problems still look too challenging for current techniques.
4
5
In principle, there is no need of learning the task completely, just
some key steps that can be traced and identified when a novice or an
Several ways of solving the task are possible. The supervisor
must be able to consider all types of solutions.
Correction and feedback is also a possibility in supervision.
6
education, have addressed this kind of problem
7
a human mistake that deviates from the procedure or the
advice the operator in real time”.
continuous supervision and get meaningful comprehensible feedback”.
by a recollection of how the procedures are performed at a high level and the effect of the feedback over the operators”.
cover all the possible ways of carrying out the task.
8
Box-trainers are much cheaper and tactile feedback is real. Virtual simulators are very expensive. Not enough availability for students. Virtual simulators usually incorporate tasks and low-level supervision.
9
Markov processes String similarity (longest common subsequence algorithm):
“Automatic supervision of gestures to guide novice surgeons during training” C.
Monserrat, A. Lucas, J. Hernández-Orallo, M. José Rupérez, Surgical Endoscopy (2014)
Using a character coding for gestures: This is very low-level. Ignores the high-level description.
10
DESCRIPTION:
VIDEO:
11
Provide start-up declarative knowledge about the domain, Analyse these logs and suggest segmentation, Identify groups and find repetitive structures, Turn them into high-level actions that represent a program, Possibly make them available to the expert, Perform a similar approach for each trainee performing
Producing high-level online feedback for the user.
12
13
Using track dots in the trainer-box when recording. Positions are analysed and recorded for the key objects.
High-level knowledge representation
Event-Action declarative languages, such as event calculus and
Nikos Katzouris, Alexander Artikis, Georgios Paliouras “Incremental
learning of event definitions with Inductive Logic Programming” Machine Learning 100:555–585, 2015.
Uses XHAIL: Ray, O. (2009). Nonmonotonic abductive inductive learning.
Journal of Applied Logic, 7(3), 329–340.
14
lead to larger consortia and projects.
Anyhow, approach me during the coffee break!