Semiconductor Engineering

Low-Power Heterogeneous Compute Cluster For TinyML DNN Inference And On-Chip Training

A new technical paper titled “DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training” was published by researchers at University of Bologna and ETH Zurich ...
EurekAlert!

Early Bird uses 10 times less energy to train deep neural networks

HOUSTON -- (May 18, 2020) -- Rice University's Early Bird could care less about the worm; it's looking for megatons of greenhouse gas emissions. Early Bird is an energy-efficient method for training ...
Science Daily

Supercomputing speeds up deep learning training

Researchers used Stampede2 to complete a 100-epoch ImageNet deep neural network training in 11 minutes -- the fastest time recorded to date. Using 1600 Skylake processors they also bested Facebook's ...
Electronic Design

Lifelong-DNN Takes a Different Machine-Learning Path

Machine learning (ML) is a broad topic within the realm of artificial intelligence (AI). One of the more popular ML technologies is deep neural networks (DNNs), which have driven FPGA and GPGPU ...
TechNode

Briefing: Chinese researchers propose new, more efficient DNN training method

51001614 - robotic hand, accessing on laptop, the virtual world of information. concept of artificial intelligence and replacement of humans by machines. Every Wednesday and Friday, TechNode’s ...
Semiconductor Engineering

Enabling Training of Neural Networks on Noisy Hardware

“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 ...
Science Daily

Early Bird uses 10 times less energy to train deep neural networks

"This means you can train a DNN to achieve the same or even better accuracy for a given task in about 10% or less of the time needed for traditional training, which can lead to more than one order ...