Searching for lottery tickets inside large neural networks

What if behind every modern deep neural network a “lottery ticket” was hidden? A much smaller sub-network that when trained it would achieve the same or even better performance that the entire trained network

In 2019 a paper by Frankle and Carbin[1] appeared with a very intriguing conjecture, based on experimental observation of current large neural networks it seemed that one could grab a small portion of the same network and train it to achieve …

data science deep-neural-networks machine learning networks neural networks