A survey on federated learning systems: Vision, hype and reality for data privacy and protection
As data privacy increasingly becomes a critical societal concern, federated learning has
been a hot research topic in enabling the collaborative training of machine learning models …
been a hot research topic in enabling the collaborative training of machine learning models …
Recent advances in open set recognition: A survey
In real-world recognition/classification tasks, limited by various objective factors, it is usually
difficult to collect training samples to exhaust all classes when training a recognizer or …
difficult to collect training samples to exhaust all classes when training a recognizer or …
[PDF][PDF] 网络大数据: 现状与展望
王元卓, 靳小龙, 程学旗 - 2013 - 159.226.43.17
摘要网络大数据是指“人, 机, 物” 三元世界在网络空间(Cyberspace) 中交互,
融合所产生并在互联网上可获得的的大数据. 网络大数据的规模和复杂度的增长超出了硬件能力 …
融合所产生并在互联网上可获得的的大数据. 网络大数据的规模和复杂度的增长超出了硬件能力 …
Gaia Data Release 3-Analysis of RVS spectra using the General Stellar Parametriser from spectroscopy
A Recio-Blanco, P De Laverny, PA Palicio… - Astronomy & …, 2023 - aanda.org
Context. The chemo-physical parametrisation of stellar spectra is essential for
understanding the nature and evolution of stars and of Galactic stellar populations. A …
understanding the nature and evolution of stars and of Galactic stellar populations. A …
A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions
This tutorial introduces the reader to Gaussian process regression as an expressive tool to
model, actively explore and exploit unknown functions. Gaussian process regression is a …
model, actively explore and exploit unknown functions. Gaussian process regression is a …
Towards a neuroscience of active sampling and curiosity
J Gottlieb, PY Oudeyer - Nature Reviews Neuroscience, 2018 - nature.com
In natural behaviour, animals actively interrogate their environments using endogenously
generated 'question-and-answer'strategies. However, in laboratory settings participants …
generated 'question-and-answer'strategies. However, in laboratory settings participants …
Deep unsupervised learning using nonequilibrium thermodynamics
J Sohl-Dickstein, E Weiss… - International …, 2015 - proceedings.mlr.press
A central problem in machine learning involves modeling complex data-sets using highly
flexible families of probability distributions in which learning, sampling, inference, and …
flexible families of probability distributions in which learning, sampling, inference, and …
[PDF][PDF] Stochastic variational inference
We develop stochastic variational inference, a scalable algorithm for approximating
posterior distributions. We develop this technique for a large class of probabilistic models …
posterior distributions. We develop this technique for a large class of probabilistic models …
World model learning and inference
Understanding information processing in the brain—and creating general-purpose artificial
intelligence—are long-standing aspirations of scientists and engineers worldwide. The …
intelligence—are long-standing aspirations of scientists and engineers worldwide. The …
Susceptibility mapping of soil water erosion using machine learning models
Soil erosion is a serious threat to sustainable agriculture, food production, and
environmental security. The advancement of accurate models for soil erosion susceptibility …
environmental security. The advancement of accurate models for soil erosion susceptibility …