Stephen Downes

Knowledge, Learning, Community

The answer to the question posed in the title is "yes, mostly" (and I would quibble with the places where the paper says they don't mesh) but the real value of the paper is a step-by-step examination of different types of neural networks used in machine learning and (especially) deep learning. "the only hope is to use unsupervised learning model in which  a learner should extract the pattern from given examples without explicit feedback. The repetition and relative similarity between objects in given examples may help a learner to cluster and combine different ideas together to come up with new object. And that is where connectivist's theory lies."

[Direct link]


Stephen Downes Stephen Downes, Casselman, Canada

Creative Commons License.

Copyright 2020
Last Updated: Nov 28, 2020 3:11 p.m.