Researchers have developed an algorithm to train an analog neural network just as accurately as a digital one, enabling the development of more efficient alternatives to power-hungry deep learning ...

On a more basic level, [Gigante] did just that, teaching a neural network to play a basic driving game with a genetic algorithm. The game consists of a basic top-down 2D driving game.

James McCaffrey explains the common neural network training technique known as the back-propagation algorithm.

We’re going to talk about backpropagation. We’re going to talk about how neurons in a neural network learn by getting their math adjusted, called backpropagation, and how we can optimize ...

The standard “back-propagation” training technique for deep neural networks requires matrix multiplication, an ideal workload for GPUs. With SLIDE, Shrivastava, Chen and Medini turned neural network ...

“Deep neural networks (DNNs) are typically trained using the conventional stochastic gradient descent (SGD) algorithm. However, SGD performs poorly when applied to train networks on non-ideal analog ...

Machine learning needs to improve adversarial robustness in deep neural networks for robotics without reducing their accuracy and safety.

Dropout training is a relatively new algorithm which appears to be highly effective for improving the quality of neural network predictions. It's not yet widely implemented in neural network API ...