Embedded Machine Learning: Part 2 (Ep. 183)

<p>In Part 2 of Embedded Machine Learning, I speak about one important technique to prune a neural network and perform inference on small devices. Such technique helps preserving most of the accuracy with a model orders of magnitude smaller.</p> <p>Enjoy the show!</p> <p> </p> <p> </p> References <ol><li class="title mathjax"><a href='https://arxiv.org/abs/1803.03635'>The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks </a></li> </ol><p> </p>