# ai-bot: use of soft labels with 'less than one'-shot task in AI learning models

<< Deep neural networks require large training sets but suffer from high computational cost and long training times. Training on much smaller training sets while maintaining nearly the same accuracy would be very beneficial. In the few-shot learning setting, a model must learn a new class given only a small number of samples from that class. One-shot learning is an extreme form of few-shot learning where the model must learn a new class from a single example. (AA)  propose the 'less than one'-shot learning task where models must learn N new classes given only M<N examples and (they) show that this is achievable with the help of soft labels. >>

Ilia Sucholutsky, Matthias Schonlau. 'Less Than One'-Shot Learning: Learning N Classes From M<N Samples. arXiv:2009.08449v1. Sep 17, 2020

https://arxiv.org/abs/2009.08449   

Karen Hao. A radical new technique lets AI learn with practically no data. Oct 16, 2020.  

https://www.technologyreview.com/2020/10/16/1010566/ai-machine-learning-with-tiny-data

FonT: sara' verosimilmente intrigante osservare come una 'macchina AI' sapra' esercitare sugli umani il potere di cooptazione ...