English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Entropy Mastermind: Learning from humans about intelligent systems

Bertram, L., Schulz, E., Hofer, M., & Nelson, J. (2019). Entropy Mastermind: Learning from humans about intelligent systems. In Human-like Computing Machine Intelligence Workshop (MI21-HLC).

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
http://mi21-hlc.doc.ic.ac.uk/programme.html (Publisher version)
Description:
-
OA-Status:
Not specified
Description:
-
OA-Status:
Not specified

Creators

show
hide
 Creators:
Bertram, L, Author           
Schulz, E1, Author           
Hofer, M, Author
Nelson, JD, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Despite the rapidly increasing computational power of to-day’s computers, a key challenge in robotics and artificial intelligenceis successful and smooth interaction with the environment – somethingthat comes naturally for most humans. Which strategies enable humansto learn about and adapt to an environment with such high computa-tional complexity? What can machines learn from human strategies inorder to exploit their computational powers efficiently and be a natural,understandable and manageable part of our everyday lives? We reviewhow a proposed research program, centered around a novel version of thecode-breaking game Mastermind, sets out to address these questions.

Details

show
hide
Language(s):
 Dates: 2019-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Human-like Computing Machine Intelligence Workshop (MI21-HLC)
Place of Event: Windsor, UK
Start-/End Date: 2019-06-30 - 2019-07-03

Legal Case

show

Project information

show

Source 1

show
hide
Title: Human-like Computing Machine Intelligence Workshop (MI21-HLC)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: 3 Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -