50x Speed Improvements on Deep Learning Networks Using Brain-Derived Algorithms

The end result is a sparse network that more closely "mimics the brain". Is this as significant as it sounds or is there something I am missing here?

Original Paper here - https://numenta.com/assets/pdf/research-publications/papers/...

Seems like Numenta is out of ideas about how the brain works. What happened to them?

In this work they simply took a standard neural network, sparsified weights and activations, trained it with standard gradient descent and backpropagation, and called it a day.

This would have been unthinkable 10 years ago when they were after biological plausibility of their algorithms.