Results 1 to 10 of about 16,800,098 (284)
Theoretical Models of Learning to Learn [PDF]
in Learning to Learn (edited by Sebastian Thrun and Lorien Pratt),
159-179 (1998), 2020 A Machine can only learn if it is biased in some way. Typically the bias is supplied by hand, for example through the choice of an appropriate set of features. However, if the learning machine is embedded within an {\em environment} of related tasks, then it can {\em learn} its own bias by learning sufficiently many tasks from the environment.
Sebastian Thrun, Lorien Pratt
arxiv +7 more sources
Technometrics, 2021 A machine learning system, in general, learns from the environment, but statistical machine learning programs (systems) learn from the data. This chapter presents techniques for statistical machine learning using Support Vector Machines (SVM) to ...
Yuhai Wu
semanticscholar +1 more source
Momentum Contrast for Unsupervised Visual Representation Learning [PDF]
Computer Vision and Pattern Recognition, 2019 We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large
Kaiming He +4 more
semanticscholar +1 more source
Advances and Open Problems in Federated Learning [PDF]
Found. Trends Mach. Learn., 2019 Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g.
P. Kairouz +57 more
semanticscholar +1 more source
Acknowledgment to Reviewers of Machine Learning and Knowledge Extraction in 2021
Machine Learning and Knowledge Extraction, 2022 Rigorous peer-reviews are the basis of high-quality academic publishing [...]
Machine Learning and Knowledge Extraction Editorial Office
doaj +1 more source
node2vec: Scalable Feature Learning for Networks [PDF]
Knowledge Discovery and Data Mining, 2016 Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by ...
Aditya Grover, J. Leskovec
semanticscholar +1 more source
Acknowledgment to the Reviewers of Machine Learning and Knowledge Extraction in 2022
Machine Learning and Knowledge Extraction, 2023 High-quality academic publishing is built on rigorous peer review [...]
Machine Learning and Knowledge Extraction Editorial Office
doaj +1 more source
Learning to Compare: Relation Network for Few-Shot Learning [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each.
Flood Sung +5 more
semanticscholar +1 more source
Research and Practice in Technology Enhanced Learning, 2021 An amendment to this paper has been published and can be accessed via the original article.
Research and Practice in Technology Enhanced Learning
doaj +1 more source
Deep Learning with Differential Privacy [PDF]
Conference on Computer and Communications Security, 2016 Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information.
Martín Abadi +6 more
semanticscholar +1 more source