Machine Learning, Cognition and
AI –Some Future Challenges
Eytan Ruppin
Overview
•Embodied Cognition
•Automatic Language Acquisition
•AI & Biology
•Re-exploring the reward of reward..
Embodied Cognition
•Creating a canonical set of world-agent(s)
simulation scenarios
•Studying comparatively the three basic
methodologies (hand-designed, learning
and evolutionary) on equal grounds
•Emphasis on evolutionary agents:
-encodings, encodings and encodings..
-utilizing the environment and ontogenesis
Automatic Language Acquisition
•Awakening –the rise of non-Chomskian
approaches in Linguistics
•A `middle kingdom’between grammar-
based and statistical approaches to NLP
(ADIOS and other distributed grammar
approaches)
•Many important real world applications:
Human-computer interface, VR and IVR,
Textonics..
AI & Biology
•A real necessity and opportunity –Biology is
flooded with data that needs to be distilled to
knowledge..
•Biological texts
-the usual.. data mining, entity extraction
-Annotations, databases
•AI methodologies for biological inference:
-logics for gene regulation networks
-logics for signal transduction networks
Time for some Reward
•Obviously, the basic driving force of operant
conditioning and reinforcement learning
•Recent advances in our understanding of the
neurobiology of reward-driven decision making
systems
•Previous EU projects focused separately on
affordance, anticipation and context-
dependency: reward as a possibly integrative
principle.
Enter the password to open this PDF file:
File name:
-
File size:
-
Title:
-
Author:
-
Subject:
-
Keywords:
-
Creation Date:
-
Modification Date:
-
Creator:
-
PDF Producer:
-
PDF Version:
-
Page Count:
-
Preparing document for printing…
0%
Comments 0
Log in to post a comment