Zobrazeno 1 - 10
of 226
pro vyhledávání: '"HELLANDER, ANDREAS"'
We present a generative modeling approach based on the variational inference framework for likelihood-free simulation-based inference. The method leverages latent variables within variational autoencoders to efficiently estimate complex posterior dis
Externí odkaz:
http://arxiv.org/abs/2411.14511
Publikováno v:
10 June 2024
Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However,
Externí odkaz:
http://arxiv.org/abs/2309.10367
Chatbots are mainly data-driven and usually based on utterances that might be sensitive. However, training deep learning models on shared data can violate user privacy. Such issues have commonly existed in chatbots since their inception. In the liter
Externí odkaz:
http://arxiv.org/abs/2304.03228
Federated learning is a distributed and privacy-preserving approach to train a statistical model collaboratively from decentralized data of different parties. However, when datasets of participants are not independent and identically distributed (non
Externí odkaz:
http://arxiv.org/abs/2301.09357
Machine reading comprehension (MRC) of text data is one important task in Natural Language Understanding. It is a complex NLP problem with a lot of ongoing research fueled by the release of the Stanford Question Answering Dataset (SQuAD) and Conversa
Externí odkaz:
http://arxiv.org/abs/2202.04742
With the rapid development of big data and cloud computing, data management has become increasingly challenging. Over the years, a number of frameworks for data management and storage with various characteristics and features have become available. M
Externí odkaz:
http://arxiv.org/abs/2201.11668
Publikováno v:
In Artificial Intelligence in the Life Sciences June 2024 5
Autor:
Ekmefjord, Morgan, Ait-Mlouk, Addi, Alawadi, Sadi, Åkesson, Mattias, Singh, Prashant, Spjuth, Ola, Toor, Salman, Hellander, Andreas
Federated machine learning has great promise to overcome the input privacy challenge in machine learning. The appearance of several projects capable of simulating federated learning has led to a corresponding rapid progress on algorithmic aspects of
Externí odkaz:
http://arxiv.org/abs/2103.00148
Autor:
Wrede, Fredrik, Eriksson, Robin, Jiang, Richard, Petzold, Linda, Engblom, Stefan, Hellander, Andreas, Singh, Prashant
State-of-the-art neural network-based methods for learning summary statistics have delivered promising results for simulation-based likelihood-free parameter inference. Existing approaches require density estimation as a post-processing step building
Externí odkaz:
http://arxiv.org/abs/2102.06521
Autor:
Zhang, Tianru, Gupta, Ankit, Rodríguez, María Andreína Francisco, Spjuth, Ola, Hellander, Andreas, Toor, Salman
Publikováno v:
In Expert Systems With Applications 1 March 2024 237 Part B