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 ...

“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 ...

Neural networks made from photonic chips can be trained using on-chip backpropagation – the most widely used approach to training neural networks, according to a new study.

The most widely used training algorithm of neural networks (NNs) is back propagation (BP), a gradient-based technique that requires significant computational effort. Metaheuristic search techniques ...

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 ...

Scientists at UCL, Google DeepMind and Intrinsic have developed a powerful new AI algorithm that enables large sets of ...

When working with neural networks, their training is the single most resource-demanding and costly process. Scientists at the ETH Zurich have now developed a software that considerably speeds up ...

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