Our algorithms result in a significant speedup for sparse coding, allowing us to learn larger sparse codes than possible with previously described algorithms. We apply these algorithms to natural ...

The hardware discussed by Sheridan et al. implements a particular sparse coding algorithm called a locally competitive algorithm 7, which has a straightforward mapping onto a recurrent neural network.

Numenta compared sparse and dense networks by running its algorithms on Xilinx FPGAs (Field Programmable Gate Array) for a speech recognition task using the Google Speech Commands (GSC) dataset.

The alternative, sparse coding, tends to be used for memory recall and sensory representations. Here, a single neuron only conveys a limited amount of information (i.e., ...

The sparse identification of nonlinear dynamics (SINDy) algorithm is one approach to discover dynamical systems models from data. Although extensions have been developed to identify implicit dynamics, ...