FPGAs for Artificial Intelligence (AI)
Overview
AI: The Next Data Revolution
- Accelerating the Evolution
- Enabling AI+
- Delivering Real Time AI
Intel® Solutions
Intel® FPGAs offer fast to market, scalable, and customizable solutions. Learn more about Intel® technology for AI.
Learn more
Partner Solutions
Learn about how our partners leverage Intel® FPGAs to enable a variety of applications from smart retail to speech recognition.
Learn more
Resources
Low Precision Networks for Efficient Inference on FPGAs
Low precision quantization is part of the toolbox for achieving application specifications by increasing throughput or decreasing resource usage where moving to a smaller chip is beneficial.
FPGA Vs. GPU for Deep Learning
While there is no single architecture that works best for all machine and deep learning applications, FPGAs can offer distinct advantages over GPUs and other types of hardware.
Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA – White Paper
The Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA offers exceptional performance, flexibility, and scalability for deep learning and computer vision solutions.
Boost Performance of Video Analytics with the Intel® Vision Accelerator Design
Build high performance computing (HPC) vision applications with integrated deep learning inference.
Intel® FPGAs Power AI in Microsoft Azure*
At the Microsoft Build conference, Microsoft debuted Azure* Machine Learning Hardware Accelerated Models powered by Project Brainwave integrated with the Microsoft Azure* Machine Learning SDK for preview.
FPGAs in Deep Learning Inference Today
The unique architecture of FPGAs can be used to optimize system performance metrics for deep learning applications.
Neuromorphic Computing with Intel® FPGAs
A large-scale neuromorphic computer system of Intel® FPGAs aims to enable reverse engineering of the cerebral cortex.
FPGA AI Blogs
FPGA accelerates face recognition while protecting inference model through data encryption.
Myrtle’s recurrent neural network accelerator handles 4000 simultaneous speech-to-text translations with just one FPGA, outperforms GPU in TOPS, latency, and efficiency.
Corerain’s CAISA stream engine transforms FPGA into Deep Learning Neural Network without HDL coding.
Resource Center
Find technical documentation, videos, and training courses for Intel's AI solutions.