Xilinx invests in neural network startup

March 01, 2016 // By Peter Clarke
FPGA vendor Xilinx has invested in TeraDeep Inc. (Santa Clara, Calif.) a developer of convolutional neural network architectures as part of a Data Center Ecosystem development program.

The program is aimed at emerging workload applications such as machine learning, image and video processing, data analytics, storage data base acceleration, and network acceleration. However, the size of the investment by Xilinx Technology Ventures was not disclosed.

TeraDeep was founded in 2013 as a spin off from Purdue University (West Lafayette, Indiana) to commercialize research into multilayer convolutional neural networks as an efficient means of image processing and similar tasks. The company has used Xilinx FPGAs as a platform to run its deep learning technology.

Xilinx said that the investment would assure that TeraDeep would continue to work closely with Xilinx to optimize its technology on Xilinx-based FPGA boards.

Related links and articles:



News articles:

EE Times Silicon 60: 2015's Startups to Watch

Neural network built in plastic

MIT neural network IC aims at mobiles

BrainChip provides details of neural network architecture

Startup plans neural network front-end for sensor systems

Startup's tech is Intel's Quark neural network  

16 analog, MEMS and sensor startups to follow in 2016