If you are developing smart devices, here we will summarise how can you benefit from Artificial Intelligence.
The advancements in hardware, software, algorithms and the abundance of data have made it relatively easy for developers, OEM and manufacturers to bring intelligence to edge devices.
The traditional approach to machine learning and AI has been that execution, inference and training activities all be resident in the cloud for the reasons of available computing power and amounts of data.
The migration of AI workloads to the Edge devices is driven by the number of reasons over the last couples of years. Latency and performance, delivering seamless user experiences are becoming important. Privacy and security, for some customers being able to keep control of the data while still being able to benefit from the same user experiences is a key.
- Computer vision augmented with machine learning
- Audio assistants for keyword detection and natural language processing
- Security, malware detection and malfunction in systems
If you’d like to see an overview of Qualcomm’s AI solutions please follow this link http://kazlouroche.com/artificial-intelligence-on-snapdragon-device.
Subscribe to our updates with the form below to hear about innovation in AI for devices from the likes of Google Research, Nvidia, Intel Nervana, and startups Cerebras, Graphcore, Wave Computing, Horizon Robotics, Cambricon, Mythic, DeePhi.
Qualcomm Snapdragon Neural Processing Engine
Developing for artificial intelligence using the Snapdragon NPE SDK does require a few prerequisites before you can get started creating solutions.
- You need to run a convolutional model in one or multiple verticals, including mobile, automotive, IoT, AR, drones, and robotics
- You know how to design and train a model or already have a pre-trained model file
- Your framework of choice is Caffe/Caffe2 or TensorFlow
- You make JAVA APPs for Android or native applications for Android or Linux
- You have an Ubuntu 14.04 development environment
- You have a supported device to test your application on
Want to develop on-device AI solution – talk to us to explore the options.