國立虎尾科技大學 |

Elements of Intelligence : = Memory, Communication and Intrinsic Motivation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Elements of Intelligence :/
其他題名:	Memory, Communication and Intrinsic Motivation.
作者:	Sukhbaatar, Sainbayar.
面頁冊數:	1 online resource (162 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Contained By:	Dissertation Abstracts International79-12B(E).
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780438171213

Elements of Intelligence : = Memory, Communication and Intrinsic Motivation.
Sukhbaatar, Sainbayar.

Elements of Intelligence :Memory, Communication and Intrinsic Motivation. - 1 online resource (162 pages)

Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.

Thesis (Ph.D.)--New York University, 2018.

Includes bibliographical references

Building an intelligent agent that can learn and adapt to its environment has always been a challenging task. This is because intelligence consists of many different elements such as recognition, memory, and planning. In recent years, deep learning has shown impressive results in recognition tasks. The aim this thesis is to advance the deep learning techniques to other elements of intelligence.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438171213Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Elements of Intelligence : = Memory, Communication and Intrinsic Motivation.
LDR:03136ntm a2200373Ki 4500 001 916871
005 20180928111502.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438171213
035 $a (MiAaPQ)AAI10750686
035 $a (MiAaPQ)nyu:13257
035 $a AAI10750686
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Sukhbaatar, Sainbayar. $3 1190728
245 1 0 $a Elements of Intelligence : $b Memory, Communication and Intrinsic Motivation.
264 0 $c 2018
300 $a 1 online resource (162 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
500 $a Adviser: Rob Fergus.
502 $a Thesis (Ph.D.)--New York University, 2018.
504 $a Includes bibliographical references
520 $a Building an intelligent agent that can learn and adapt to its environment has always been a challenging task. This is because intelligence consists of many different elements such as recognition, memory, and planning. In recent years, deep learning has shown impressive results in recognition tasks. The aim this thesis is to advance the deep learning techniques to other elements of intelligence.
520 $a We start our investigation with memory, an integral part of intelligence that bridges past experience with current decision making. In particular, we focus on the episodic memory, which is responsible for storing our past experiences and recalling them. An agent without such memory will struggle at many tasks such as having a coherent conversation. We show that a neural network with an external memory is better suited to such tasks than traditional recurrent networks with an internal memory.
520 $a Another crucial ingredient of intelligence is the capability to communicate with others. In particular, communication is essential for agents participating in a cooperative task, improving their collaboration and division of labor. We investigate whether agents can learn to communicate from scratch without any external supervision. Our finding is that communication through a continuous vector facilitates faster learning by allowing gradients to flow between agents.
520 $a Lastly, an intelligent agent must have an intrinsic motivation to learn about its environment on its own without any external supervision or rewards. Our investigation led to one such learning strategy where an agent plays a two-role game with itself. The first role proposes a task, and the second role tries to execute it. Since their goal is to make the other fail, their adversarial interplay pushes them to explore increasingly complex tasks, which leads to a better understanding of the environment.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New York University. $b Computer Science. $3 1184382
773 0 $t Dissertation Abstracts International $g 79-12B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10750686 $z click for full text (PQDT)