Google MorphNet makes your neural net faster and smaller MorphNet is a Google Model to Build Faster and Smaller Neural Networks Towards...

Ensemble deep learning: A review arXiv paper abstract https://arxiv.org/abs/2104.02395 arXiv PDF paper https://arxiv.org/pdf/2104.02395.p...

NVIDIA, Stanford, Microsoft Efficient Trillion-Parameter Model Training on GPU Clusters NVIDIA, Stanford & Microsoft Propose Efficient...

Microsoft DeepSpeed lets 1 GPU train 40 billion parameter neural net Microsoft Releases AI Training Library ZeRO-3 Offload InfoQ article...

CPU beats GPU by 15x for neural net training with Rice Univ method CPU algorithm trains deep neural nets up to 15 times faster than top...

Top 10 AI and Machine Learning Papers in 2020 2020's Top AI & Machine Learning Research Papers TOPBOTS https://www.topbots.com/ai-machine...

Facebook AI's MADGRAD optimizer improves neural network training Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged...

Google's MoViNets: Mobile Video Networks for Efficient Video Recognition arXiv abstract https://arxiv.org/abs/2103.11511v1 . . . 3D...

Top 10 Computer Vision Papers in 2020 KDnuggets article https://www.kdnuggets.com/2021/01/top-10-computer-vision-papers-2020.html The top...

GPT-3 AI can write a passing college paper in 20 minutes ZDNet article https://www.zdnet.com/article/ai-can-write-a-passing-college-paper...

Georgia Tech and Facebook AI Researchers Devise a New Tensor Train Approach to Reduce the Size of Deep Learning Recommendation Models up...

Google Model Search AutoML automatically optimizes and identifies AI models VentureBeat article https://venturebeat.com/2021/02/19/google...

Google trained a trillion-parameter AI language model VentureBeat article https://venturebeat.com/2021/01/12/google-trained-a-trillion-pa...

Machine learning with less than one example per class TechTalks article https://bdtechtalks.com/2020/10/01/less-than-one-shot-machine-lea...

Google's Snorkel replaces slow hand labeling to train AI with functions that automatically assign labels https://lnkd.in/et8szyy See also...

Amazon SageMaker JumpStart for AutoML trains neural models with just 100+ images and lets you choose from 150+ models from TensorFlow and...

AI scientists focusing on higher-level tasks like bringing domain expertise to AI rather than hyper-parameter tuning...

MuZero algorithm masters Go, chess, shogi and Atari WITHOUT being told the rules https://lnkd.in/ejnevj6 AlphaZero - learned from scratch...

M.I.T. MCUNet brings deep learning to Internet of Things (IoT) by using $8 microcontroller chips with 0.5 MB SRAM and 2 MB FLASH...