Zobrazeno 1 - 10
of 178
pro vyhledávání: '"Kersting, Kristian"'
Visual reasoning is essential for building intelligent agents that understand the world and perform problem-solving beyond perception. Differentiable forward reasoning has been developed to integrate reasoning with gradient-based machine learning par
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25c1bf736d55bbbc02da4aa9f0a80f81
http://arxiv.org/abs/2307.00928
http://arxiv.org/abs/2307.00928
Autor:
Delfosse, Quentin, Blüml, Jannis, Gregori, Bjarne, Sztwiertnia, Sebastian, Kersting, Kristian
Cognitive science and psychology suggest that object-centric representations of complex scenes are a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep reinforcement learning approaches rel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67d22243619026b4d3e804b0d8493186
http://arxiv.org/abs/2306.08649
http://arxiv.org/abs/2306.08649
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-size
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2d57d63c65fe4cefa8fb53612b78040
http://arxiv.org/abs/2305.18398
http://arxiv.org/abs/2305.18398
Autor:
Bellagente, Marco, Brack, Manuel, Teufel, Hannah, Friedrich, Felix, Deiseroth, Björn, Eichenberg, Constantin, Dai, Andrew, Baldock, Robert, Nanda, Souradeep, Oostermeijer, Koen, Cruz-Salinas, Andres Felipe, Schramowski, Patrick, Kersting, Kristian, Weinbach, Samuel
The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::434dc9968f8ed1b080c5186401e7c54d
http://arxiv.org/abs/2305.15296
http://arxiv.org/abs/2305.15296
In combination with Reinforcement Learning, Monte-Carlo Tree Search has shown to outperform human grandmasters in games such as Chess, Shogi and Go with little to no prior domain knowledge. However, most classical use cases only feature up to two pla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79ec7b95a1ec8274c6df3fe5fd5a12f7
http://arxiv.org/abs/2305.13206
http://arxiv.org/abs/2305.13206
Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the explanatory interactive machine learning (XIL) framework has been pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=arXiv_______::a3f2dcbd131bc0b3be9e9293a40c3074
http://arxiv.org/abs/2304.07136
http://arxiv.org/abs/2304.07136
Autor:
Wainakh, Aidmar, Ventola, Fabrizio, Müßig, Till, Keim, Jens, Cordero, Carlos Garcia, Zimmer, Ephraim, Grube, Tim, Kersting, Kristian, Mühlhäuser, Max
Publikováno v:
Proceedings on Privacy Enhancing Technologies. 2022:227-244
Federated learning enables multiple users to build a joint model by sharing their model updates (gradients), while their raw data remains local on their devices. In contrast to the common belief that this provides privacy benefits, we here add to the
Autor:
Jentzsch, Sophie, Kersting, Kristian
Humor is a central aspect of human communication that has not been solved for artificial agents so far. Large language models (LLMs) are increasingly able to capture implicit and contextual information. Especially, OpenAI's ChatGPT recently gained im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b26fabee6845ea140aa53e49e5de740
While transformers have gained the reputation as the "Swiss army knife of AI", no one has challenged them to master the game of chess, one of the classical AI benchmarks. Simply using vision transformers (ViTs) within AlphaZero does not master the ga
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6058ed25b6c92e704b06123087b9128
The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic Programming Languages (DPPLs) have been developed for probabilistic logic programmi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c894bb3a098348a761019a1cb649c11