DataFranca - Contributions [fr]

Calcul bio-inspiré

2018-03-24T21:37:28Z

Pierre5018 : /* Termes privilégiés */

== Domaine ==
[[Category:Vocabulary]]

== Définition ==

== Termes privilégiés ==

=== calcul bio-inspiré ===
Origine:
* Computing sur Termium: http://www.btb.termiumplus.gc.ca/tpv2alpha/alpha-fra.html?lang=fra&i=1&srchtxt=COMPUTING&index=ent&codom2nd_wet=1#resultrecs

* Bio-inspiré sur Termium: http://www.btb.termiumplus.gc.ca/tpv2source?lang=eng&srchtxt=Bio-inspired&i=1&index=enw&src_id=BANMO1996,RECHE1995&rlang=fr&titl=bio-inspir%26eacute%3B&fchrcrdnm=2#resultrecs

=== traitement bio-inspiré ===
Origine:
* Computing sur Termium: http://www.btb.termiumplus.gc.ca/tpv2alpha/alpha-fra.html?lang=fra&i=1&srchtxt=COMPUTING&index=ent&codom2nd_wet=1#resultrecs

* Bio-inspiré sur Termium: http://www.btb.termiumplus.gc.ca/tpv2source?lang=eng&srchtxt=Bio-inspired&i=1&index=enw&src_id=BANMO1996,RECHE1995&rlang=fr&titl=bio-inspir%26eacute%3B&fchrcrdnm=2#resultrecs

== Anglais ==

=== Bio-inspired computing ===
Bio-inspired computing, short for biologically inspired computing, is a field of study that loosely knits together subfields related to the topics of connectionism, social behaviour and emergence. It is often closely related to the field of artificial intelligence, as many of its pursuits can be linked to machine learning. It relies heavily on the fields of biology, computer science and mathematics. Briefly put, it is the use of computers to model the living phenomena, and simultaneously the study of life to improve the usage of computers. Biologically inspired computing is a major subset of natural computation.

Robotique en nuage

2018-03-24T20:36:02Z

Pierre5018 : /* Robotique en nuage */

== Domaine ==
[[Category:Vocabulary]]Vocabulary
[[Category:Cloud robotics]]Cloud robotics

== Définition ==

== Termes privilégiés ==

=== Robotique en nuage ===
* https://patents.google.com/patent/WO2012025014A1/fr
* https://www.robotshop.com/blog/fr/robots/robots-professionnels-recherche/robotique-nuage

=== robotique en tant que service ===
* https://www.silicon.fr/robotique-ia-top-previsions-idc-2017-164800.htmlhttps://www.silicon.fr/robotique-ia-top-previsions-idc-2017-164800.html

=== robotique à la demande ===

* https://www.silicon.fr/robotique-ia-top-previsions-idc-2017-164800.html

== Anglais ==

=== Cloud robotics ===

Cloud robotics is a field of robotics that attempts to invoke cloud technologies such as cloud computing, cloud storage, and other Internet technologies centred on the benefits of converged infrastructure and shared services for robotics. When connected to the cloud, robots can benefit from the powerful computation, storage, and communication resources of modern data center in the cloud, which can process and share information from various robots or agent (other machines, smart objects, humans, etc.). Humans can also delegate tasks to robots remotely through networks. Cloud computing technologies enable robot systems to be endowed with powerful capability whilst reducing costs through cloud technologies. Thus, it is possible to build lightweight, low cost, smarter robots have intelligent "brain" in the cloud. The "brain" consists of data center, knowledge base, task planners, deep learning, information processing, environment models, communication support etc.[1][2][3][4]

Robotique en nuage

2018-03-24T20:14:22Z

Pierre5018 : /* Robotique en nuage */

== Domaine ==
[[Category:Vocabulary]]Vocabulary
[[Category:Cloud robotics]]Cloud robotics

== Définition ==

== Termes privilégiés ==

=== Robotique en nuage ===
* https://patents.google.com/patent/WO2012025014A1/fr
* https://www.robotshop.com/blog/fr/robots/robots-professionnels-recherche/robotique-nuage

== Anglais ==

=== Cloud robotics ===

Cloud robotics is a field of robotics that attempts to invoke cloud technologies such as cloud computing, cloud storage, and other Internet technologies centred on the benefits of converged infrastructure and shared services for robotics. When connected to the cloud, robots can benefit from the powerful computation, storage, and communication resources of modern data center in the cloud, which can process and share information from various robots or agent (other machines, smart objects, humans, etc.). Humans can also delegate tasks to robots remotely through networks. Cloud computing technologies enable robot systems to be endowed with powerful capability whilst reducing costs through cloud technologies. Thus, it is possible to build lightweight, low cost, smarter robots have intelligent "brain" in the cloud. The "brain" consists of data center, knowledge base, task planners, deep learning, information processing, environment models, communication support etc.[1][2][3][4]

Robotique en nuage

2018-03-24T20:07:34Z

Pierre5018 : /* Termes privilégiés */

== Domaine ==
[[Category:Vocabulary]]Vocabulary
[[Category:Cloud robotics]]Cloud robotics

== Définition ==

== Termes privilégiés ==

=== Robotique en nuage ===
* https://patents.google.com/patent/WO2012025014A1/fr

== Anglais ==

=== Cloud robotics ===

Cloud robotics is a field of robotics that attempts to invoke cloud technologies such as cloud computing, cloud storage, and other Internet technologies centred on the benefits of converged infrastructure and shared services for robotics. When connected to the cloud, robots can benefit from the powerful computation, storage, and communication resources of modern data center in the cloud, which can process and share information from various robots or agent (other machines, smart objects, humans, etc.). Humans can also delegate tasks to robots remotely through networks. Cloud computing technologies enable robot systems to be endowed with powerful capability whilst reducing costs through cloud technologies. Thus, it is possible to build lightweight, low cost, smarter robots have intelligent "brain" in the cloud. The "brain" consists of data center, knowledge base, task planners, deep learning, information processing, environment models, communication support etc.[1][2][3][4]

Évanescence du gradient

2018-03-24T18:18:44Z

Pierre5018 : /* Termes privilégiés */

== Domaine ==

[[Category:Vocabulary]] Vocabulary
[[Catégorie:Apprentissage profond]] Apprentissage profond

== Définition ==

== Termes privilégiés ==

=== le problème de la disparition du gradient ===
* Référence : https://openclassrooms.com/courses/utilisez-des-modeles-supervises-non-lineaires/empilez-les-perceptrons

== Anglais ==

'''Vanishing Gradient Problem'''

The vanishing gradient problem arises in very deep Neural Networks, typically Recurrent Neural Networks, that use activation functions whose gradients tend to be small (in the range of 0 from 1). Because these small gradients are multiplied during backpropagation, they tend to “vanish” throughout the layers, preventing the network from learning long-range dependencies. Common ways to counter this problem is to use activation functions like ReLUs that do not suffer from small gradients, or use architectures like LSTMs that explicitly combat vanishing gradients. The opposite of this problem is called the exploding gradient problem.
• On the difficulty of training recurrent neural networks

Explosion du gradient

2018-03-24T18:15:26Z

Pierre5018 : /* Termes privilégiés */ explosion

== Domaine ==
[[Category:Vocabulary]] Vocabulary 

[[Catégorie:Apprentissage profond]] Apprentissage profond

== Définition ==

== Termes privilégiés ==

=== le problème de l'explosion du gradient ===
Référence: https://openclassrooms.com/courses/utilisez-des-modeles-supervises-non-lineaires/empilez-les-perceptrons

== Anglais ==

===Exploding Gradient Problem===

The Exploding Gradient Problem is the opposite of the Vanishing Gradient Problem. In Deep Neural Networks gradients may explode during backpropagation, resulting number overflows. A common technique to deal with exploding gradients is to perform Gradient Clipping.
• On the difficulty of training recurrent neural networks

Logique du premier ordre

2018-03-24T14:19:08Z

Pierre5018 : /* Termes privilégiés */

== Domaine ==
[[Category:Vocabulary]]Vocabulary 

== Définition ==

== Termes privilégiés ==
* Logique du premier ordre.
** [https://www.btb.termiumplus.gc.ca/tpv2source?lang=fra&srchtxt=logique%20premier%20ordre&i=1&index=frt&src_id=IRIA-21984,GOEXP1984,BONINT1984,TESIN1984&rlang=fr&titl=logique%20du%20premier%20ordre&fchrcrdnm=1#resultrecs Termium]
** Mémo : Cours logique - Mémo n˚5, Logique du premier ordre, Emmanuel Coquery, [https://liris.cnrs.fr/~ecoquery/dokuwiki/lib/exe/fetch.php?media=enseignement:logique:logique-memo5.pdf (pdf)]

== Anglais ==

=== First-order logic ===
First-order logic—also known as first-order predicate calculus and predicate logic—is a collection of formal systems used in mathematics, philosophy, linguistics, and computer science. First-order logic uses quantified variables over non-logical objects and allows the use of sentences that contain variables, so that rather than propositions such as Socrates is a man one can have expressions in the form "there exists X such that X is Socrates and X is a man" and there exists is a quantifier while X is a variable.[1] This distinguishes it from propositional logic, which does not use quantifiers or relations.[2]

A theory about a topic is usually a first-order logic together with a specified domain of discourse over which the quantified variables range, finitely many functions from that domain to itself, finitely many predicates defined on that domain, and a set of axioms believed to hold for those things. Sometimes "theory" is understood in a more formal sense, which is just a set of sentences in first-order logic.

The adjective "first-order" distinguishes first-order logic from higher-order logic in which there are predicates having predicates or functions as arguments, or in which one or both of predicate quantifiers or function quantifiers are permitted.[3] In first-order theories, predicates are often associated with sets. In interpreted higher-order theories, predicates may be interpreted as sets of sets.

Logique du premier ordre

2018-03-24T13:50:41Z

Pierre5018 : /* Termes privilégiés */ Termes privilégiés

== Domaine ==
[[Category:Vocabulary]]Vocabulary 

== Définition ==

== Termes privilégiés ==
* Logique du premier ordre.
** [https://www.btb.termiumplus.gc.ca/tpv2source?lang=fra&srchtxt=logique%20premier%20ordre&i=1&index=frt&src_id=IRIA-21984,GOEXP1984,BONINT1984,TESIN1984&rlang=fr&titl=logique%20du%20premier%20ordre&fchrcrdnm=1#resultrecs Termium]
** Mémo : Cours logique - Mémo n˚5
Logique du premier ordre,
Emmanuel Coquery, [https://liris.cnrs.fr/~ecoquery/dokuwiki/lib/exe/fetch.php?media=enseignement:logique:logique-memo5.pdf (pdf)]

== Anglais ==

=== First-order logic ===
First-order logic—also known as first-order predicate calculus and predicate logic—is a collection of formal systems used in mathematics, philosophy, linguistics, and computer science. First-order logic uses quantified variables over non-logical objects and allows the use of sentences that contain variables, so that rather than propositions such as Socrates is a man one can have expressions in the form "there exists X such that X is Socrates and X is a man" and there exists is a quantifier while X is a variable.[1] This distinguishes it from propositional logic, which does not use quantifiers or relations.[2]

A theory about a topic is usually a first-order logic together with a specified domain of discourse over which the quantified variables range, finitely many functions from that domain to itself, finitely many predicates defined on that domain, and a set of axioms believed to hold for those things. Sometimes "theory" is understood in a more formal sense, which is just a set of sentences in first-order logic.

The adjective "first-order" distinguishes first-order logic from higher-order logic in which there are predicates having predicates or functions as arguments, or in which one or both of predicate quantifiers or function quantifiers are permitted.[3] In first-order theories, predicates are often associated with sets. In interpreted higher-order theories, predicates may be interpreted as sets of sets.