Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Herrmann, Vincent"'
Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks? While the mec
Externí odkaz:
http://arxiv.org/abs/2403.11998
Current object-centric learning models such as the popular SlotAttention architecture allow for unsupervised visual scene decomposition. Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition
Externí odkaz:
http://arxiv.org/abs/2311.07534
Autor:
Zhuge, Mingchen, Liu, Haozhe, Faccio, Francesco, Ashley, Dylan R., Csordás, Róbert, Gopalakrishnan, Anand, Hamdi, Abdullah, Hammoud, Hasan Abed Al Kader, Herrmann, Vincent, Irie, Kazuki, Kirsch, Louis, Li, Bing, Li, Guohao, Liu, Shuming, Mai, Jinjie, Piękos, Piotr, Ramesh, Aditya, Schlag, Imanol, Shi, Weimin, Stanić, Aleksandar, Wang, Wenyi, Wang, Yuhui, Xu, Mengmeng, Fan, Deng-Ping, Ghanem, Bernard, Schmidhuber, Jürgen
Both Minsky's "society of mind" and Schmidhuber's "learning to think" inspire diverse societies of large multimodal neural networks (NNs) that solve problems by interviewing each other in a "mindstorm." Recent implementations of NN-based societies of
Externí odkaz:
http://arxiv.org/abs/2305.17066
There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given questions, but also continually invent new questions, by proposing hypo
Externí odkaz:
http://arxiv.org/abs/2212.14374
The act of telling stories is a fundamental part of what it means to be human. This work introduces the concept of narrative information, which we define to be the overlap in information space between a story and the items that compose the story. Usi
Externí odkaz:
http://arxiv.org/abs/2211.12423
Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in form of context-specific weight
Externí odkaz:
http://arxiv.org/abs/2207.01570
Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value function
Externí odkaz:
http://arxiv.org/abs/2207.01566
Autor:
Ashley, Dylan R., Herrmann, Vincent, Friggstad, Zachary, Mathewson, Kory W., Schmidhuber, Jürgen
We look at how machine learning techniques that derive properties of items in a collection of independent media can be used to automatically embed stories into such collections. To do so, we use models that extract the tempo of songs to make a music
Externí odkaz:
http://arxiv.org/abs/2111.02216
Autor:
Herrmann, Vincent
Immersions ist eine Performance Elektronischer Musik, die in Echtzeit die inneren Vorgänge eines Neuronalen Netzes sonifiziert. Dabei werden durch ein Optimierungsverfahren Klänge generiert, die bestimmte Bereiche des Netzwerks aktivieren. So wird
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6709f8381d9578dd117947a308a5760
Publikováno v:
LREC Workshop Language Resource and Technology Standards
LREC Workshop Language Resource and Technology Standards, May 2010, La Valetta, Malta
LREC Workshop Language Resource and Technology Standards, May 2010, La Valetta, Malta
International audience; In this paper we describe how multilingual linguistic and lexical information is stored and accessed within the framework of the SEMbySEM project\footnote{SEMbySEM (\url{http://www.sembysem.org}) is a research project within t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::44aeaca56841c2cde69435c3fad12017
https://hal.inria.fr/inria-00509763/file/final.pdf
https://hal.inria.fr/inria-00509763/file/final.pdf