Zobrazeno 1 - 10
of 399
pro vyhledávání: '"Feng, Zhili"'
Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more
Externí odkaz:
http://arxiv.org/abs/2404.15146
Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships
Externí odkaz:
http://arxiv.org/abs/2404.09387
Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, pro
Externí odkaz:
http://arxiv.org/abs/2401.06121
Autor:
Feng, Zhili, Kolter, J. Zico
This work studies the neural tangent kernel (NTK) of the deep equilibrium (DEQ) model, a practical ``infinite-depth'' architecture which directly computes the infinite-depth limit of a weight-tied network via root-finding. Even though the NTK of a fu
Externí odkaz:
http://arxiv.org/abs/2310.14062
Deep Boltzmann machines (DBMs), one of the first ``deep'' learning methods ever studied, are multi-layered probabilistic models governed by a pairwise energy function that describes the likelihood of all variables/nodes in the network. In practice, D
Externí odkaz:
http://arxiv.org/abs/2307.04990
Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently, work in vi
Externí odkaz:
http://arxiv.org/abs/2307.04317
Publikováno v:
In Mechanics of Materials September 2024 196
Publikováno v:
In Journal of Manufacturing Processes 30 August 2024 124:119-130
Publikováno v:
In Mechanics of Materials August 2024 195
$k$-means clustering is a well-studied problem due to its wide applicability. Unfortunately, there exist strong theoretical limits on the performance of any algorithm for the $k$-means problem on worst-case inputs. To overcome this barrier, we consid
Externí odkaz:
http://arxiv.org/abs/2110.14094