information

Type
Séminaire / Conférence
performance location
Ircam (Paris)
duration
30 min
date
March 8, 2018
program note
Ateliers du forum

We observe the success of artificial neural networks in simulating human performance on a number of tasks: such as image recognition, natural language processing, etc. However, there are limits to state-of-the- art AI that separate it from human-like intelligence. Humans can learn a new skill without forgetting what they have already learned and they can improve their activity and gradually become better learners. Today’s AI algorithms are limited in how much previous knowledge they are able to keep through each new training phase and how much they can reuse. In practice, this means that you need to build a new algorithm for each new specific task. There is domain called AGI where will be possible to find solutions for this problem. Artificial general intelligence(AGI) describes research that aims to create machines capable of general intelligent action. “General” means that one AI program realizes number of different tasks and the same code can be used in many applications. We must focus on self-improvement techniques e.g. Reinforcement Learning and integrate it with deep learning, recurrent networks.

speakers

From the same archive

Sonothèque de sons d'ambiance à vocation cinématographiques - Rémi Adjiman

Depuis une dizaine d’années, le département SATIS, puis la laboratoire ASTRAM et maintenant le laboratoire PRISM (Perception Représentation Image Son Musique) développe un projet de sonothèque de sons d’ambiance consultable en ligne intitul

March 8, 2018 33 min

Video

8 mars, la journée de la femme : La compositrice Violeta CRUZ - Décor sonore électroacoustique de l'opéra La Princesse légère - Violeta Cruz, Anne Montaron

Depuis 2011 je travaille sur un projet de recherche et d’écriture basé sur le dialogue musical et scénique entre des instruments symphoniques et des objets sonores électroacoustiques. Après la construction de trois objets (la fontaine élect

March 8, 2018 01 h 16 min

Video

Recent Developments in Deep Learning and Their Possible Applications in Music - Sahin Kureta

The presentation is intended as an introduction to deep learning and its applications in music. The presentation features the use deep auto-encoders for generating novel sounds from a hidden representation of an audio corpus, audio style tr

March 8, 2018 22 min

Video

StreamCaching Hamburg - Follow the satellites, explore the city, find music - Jan Dietrich

StreamCaching est un projet musical qui a débuté en juin 2017 à Hambourg. Il a été lancé au Blurred Edges festival de musique contemporaine: 10 compositions ont été commandées, numérisées, munies de données GPS et localisées à travers la vi

March 8, 2018 33 min

Video

Sound and Shape - Impermanent Architecture Forms - Karolina Kotnour

Within this project, I aim to define a mutual synthesis of sound and position of the borderlines in space. Space, as well as word, has its own shape, meaning, and wording. How it affects our perception of architecture acoustic experience sp

March 8, 2018 26 min

Video

Future Perfect: An immersive 3D audio visual performance and installation work - Garth Paine

Future Perfect will be a concert performance using smart phone virtual reality technologies and ambisonic/ WaveField sound diffusion.Future Perfect explores the seam between virtual reality as a documentation format for environmental resear

March 8, 2018 33 min

Video

MMixte: the package pour la musique mixte - Maurilio Cacciatore

Le nom vient de la définition française “Musique Mixte”, qui indique l’électronique en live (ou même seulement de l’électronique sans interaction en temps réel) avec des instruments acoustiques sur scène. Il fonctionne comme un middleware:

March 8, 2018 26 min

Video

Cross adaptive processing as musical intervention - Exploring radically new modes of musical interaction in live performance - Øyvind Brandtsegg

The project explores cross-adaptive processing as a drastic intervention in the modes of communication between performing musicians. Digital audio analysis methods are used to let features of one sound modulate the electronic processing of

March 8, 2018 24 min

Video

share


Do you notice a mistake?

IRCAM

1, place Igor-Stravinsky
75004 Paris
+33 1 44 78 48 43

opening times

Monday through Friday 9:30am-7pm
Closed Saturday and Sunday

subway access

Hôtel de Ville, Rambuteau, Châtelet, Les Halles

Institut de Recherche et de Coordination Acoustique/Musique

Copyright © 2022 Ircam. All rights reserved.