Results 21 to 30 of about 19,993,772 (359)
e-Learning at the Coimbra Group Universities
Je-LKS: Journal of E-Learning and Knowledge Society, 2012 This document is the result of a Strategic Workshop held in Leuven by the Task Force e-Learning (TF eL) of the Coimbra Group (CG), followed by a series of meetings with the TF members on this issue.
Task Force e-Learning Coimbra Group
doaj +1 more source
iCaRL: Incremental Classifier and Representation Learning [PDF]
Computer Vision and Pattern Recognition, 2016 A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data.
Sylvestre-Alvise Rebuffi +3 more
semanticscholar +1 more source
Learning without Forgetting [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016 When building a unified vision system or gradually adding new apabilities to a system, the usual assumption is that training data for all tasks is always available.
Zhizhong Li, Derek Hoiem
semanticscholar +1 more source
MedEdPORTAL, 2015 Introduction Bloom's Taxonomy has become a gold standard for writing learning objectives. Originally developed in the 1950's by Benjamin Bloom and revised in the 1990's by Lorin Anderson, Bloom's Taxonomy is a hierarchical model for organizing thinking ...
Jeanne Schlesinger +2 more
doaj +1 more source
ONLINE LEARNING – BETWEEN NECESSITY AND OPTION
Journal of Education, Society & Multiculturalism, 2021 The analysis of the educational policy in relation to online education takes into account major decisions that have a direct impact on all those involved in taking these decisions and, of course, on how they become functional.
ONLINE LEARNING – BETWEEN NECESSITY AND OPTION
doaj
Deep Residual Learning for Image Recognition [PDF]
Computer Vision and Pattern Recognition, 2015 Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously.
Kaiming He +3 more
semanticscholar +1 more source
Context Encoders: Feature Learning by Inpainting [PDF]
Computer Vision and Pattern Recognition, 2016 We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the contents of an arbitrary image ...
Deepak Pathak +4 more
semanticscholar +1 more source
A survey on Image Data Augmentation for Deep Learning
Journal of Big Data, 2019 Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very
Connor Shorten, T. Khoshgoftaar
semanticscholar +1 more source
Learning objects, learning objectives and learning design [PDF]
Innovations in Education and Teaching International, 2008 Educational research and development into e-learning mainly focuses on the inclusion of new technological features without taking into account psycho-pedagogical concerns that are likely to improve a learner's cognitive process in this new educational category.
Fernando Alonso +3 more
openaire +2 more sources
Neuromorphic Hardware Learns to Learn [PDF]
Frontiers in Neuroscience, 2019 Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand. In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized through extensive evolutionary and developmental processes for specific ranges of computing and learning tasks ...
Bohnstingl, Thomas +4 more
openaire +4 more sources