# brain: learning on the fly (in D. melanogaster and mammals)

AA << have developed a new computational model that demonstrates a long sought after link between insect and mammalian learning (..)   Incorporating anatomical and functional data from recent experiments, Dr James Bennett and colleagues modelled how the anatomy and physiology of the fruit fly's brain can support learning according to the reward prediction error (RPE) hypothesis. >>️

<< The computational model indicates how dopamine neurons in an area of a fruit fly's brain, known as the mushroom body, can produce similar signals to dopamine neurons in mammals, and how these dopamine signals can reliably instruct learning. >>️

Learning on the fly. University of Sussex. May 7, 2021. 

https://www.sciencedaily.com/releases/2021/05/210507093941.htm

Bennett, J.E.M., Philippides, A.,  Nowotny, T. Learning with reinforcement prediction errors in a model of the Drosophila mushroom body. Nat Commun 12, 2569. doi: 10.1038/ s41467-021-22592-4. May 7,  2021. 

https://www.nature.com/articles/s41467-021-22592-4   

Also

(+) keyword 'melanogaster' in FonT

https://flashontrack.blogspot.com/search?q=melanogaster

(+) Voli a casaccio. Notes. Oct 01, 2006. (quasi-stochastic poetry)

https://inkpi.blogspot.com/2006/10/2066-voli-casaccio.html

# 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 ...