Thanks to the use of GPUs, Microsoft researchers achieved record results on ImageNet, a prestigious image-recognition benchmark.
Compared to last year, Microsoft’s system cut the top-5 error rate by half, correctly classifying images within 1,000 pre-defined categories more than 96 percent of the time. 
Their system uses a 152-layer neural network, which is nearly five times deeper than the state of the art.
The researchers published a paper that provides more information on the deep learning framework used to win the ImageNet benchmark.
Read more on the NVIDIA blog >>
GPUs Help Microsoft Build Record-Breaking Image Recognition System
Dec 15, 2015
0
Discuss (0)
Related resources
- GTC session: Accelerating AI Pipelines: Boosting Visual Search Efficiency
- GTC session: GPU DiskANN and Beyond: Accelerating Microsoft Vector Search with NVIDIA cuVS
- GTC session: Build and Run Next-Generation AI on Azure’s Proven AI Infrastructure Platform (Presented by Microsoft)
- NGC Containers: ASR Parakeet CTC Riva 1.1b
- SDK: MONAI Cloud API
- SDK: RAPIDS Accelerator for Spark
0
About the Authors
