EurekAlert!

A federated anti-forgetting representation method based on hybrid model architecture and gradient truncation

Anti-forgetting representation learning method reduces the weight aggregation interference on model memory and augments the representation performance.
insideHPC

RMSprop Optimization Algorithm for Gradient Descent with Neural Networks

A big part of AI and Deep Learning these days is the tuning/optimizing of the algorithms for speed and accuracy. Much of today’s deep learning algorithms involve the use of the gradient descent ...
EurekAlert!

Efficient stochastic parallel gradient descent training for on-chip optical processors

a) Conceptual diagram of the on-chip optical processor used for optical switching and channel decoder in an MDM optical communications system. (b) Integrated reconfigurable optical processor schematic ...
TMCnet

FICO Achieves Massive Speedups in Optimization Using NVIDIA GPUs

FICO Xpress 9.8 features a GPU-accelerated implementation of the hybrid gradient algorithm, yielding up to 50x speedups for very large optimization problems FICO Xpress Optimization has the widest ...