Machine learning with less than one example per class

Machine learning with less than one example per class

TechTalks article https://bdtechtalks.com/2020/10/01/less-than-one-shot-machine-learning

'Less Than One'-Shot Learning: Learning N Classes From M<N Samples (This is done by using soft labels to partition the space between existing classes.)

Univ. of Waterloo arXiv paper https://arxiv.org/abs/2009.08449

Code for Univ. of Waterloo paper

GitHub https://github.com/ilia10000/SLkNN

Univ. of Waterloo paper has Binder online Jupyter notebook

Click the link below to run the Univ. of Waterloo software in your browser

Binder link https://mybinder.org/v2/gh/ilia10000/SLkNN/master?filepath=%2Fsoft-knn%2Fsoft_knn_vis.ipynb

AI progress depends on us using less data, not more

VentureBeat article https://venturebeat.com/2021/02/13/ai-progress-depends-on-us-using-less-data-not-more

Please like and share this post if you enjoyed it using the buttons at the bottom!

Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact

Web site with my other posts by category https://morrislee1234.wixsite.com/website

#ai #machinelearning #deeplearning #artificialintelligence #neuralnetworks #technology