Deep learning enables the best image and audio recognition solutions.
An active area of research with fast advancing innovations.
Silk’s on-device DNN engine processes data locally, not in the cloud.
Increases reliability, reduces network bandwidth, lowers cost, and maintains data privacy.
Intelligent connected devices that understand their environment.
Solve everyday tasks that previously required human involvement.
Using the latest advances in deep neural networks, we empower businesses to build the next generation of intelligent connected devices.
Founded in 2015 by Andreas Gal (former CTO of Mozilla) and Michael Vines (formerly of Qualcomm), Silk is a machine learning company that provides an on-device AI platform enabling real-time visual and audio recognition.
Powered by SILK
We bring next-generation visual and audio intelligence to connected products
The future of connected devices
Edge computing creates opportunities for new use cases that were previously not possible with cloud-based technology
By leveraging the latest advances in deep learning research, Silk offers state-of-the-art image and audio recognition
Accurately detect the presence of a person in a variety of environments. Whether it be in the home, outdoors, or in a store, Silk’s algorithms can detect a person under varying lighting conditions and occlusions.
- Know where people are spending their time in a retail store
- Detect when someone has entered your yard or front porch
- Save power and storage by only recording when a person is seen
Silk’s algorithms can recognize specific faces without a clumsy enrollment or training process. A single image is enough to identify the same individual over time.
- Add face recognition as part of multi-factor authentication for access control
- Recognize who’s coming home without training on specific faces
- Instantly search cameras at a shopping mall to find your missing child
- Be alerted when someone else attempts to gain access to your vehicle
Reliably identify any object using Silk’s deep learning-based algorithms. Leverage pre-trained models or use Silk’s tools to easily create your own object detection model.
- Know when your dog is misbehaving and has jumped onto your couch
- Count the vehicles that have entered a parking lot
- Create custom models for your specific application
Audio cues are often just as important as visual indicators. Silk’s algorithm can detect unique audio signals to understand when a specific sound is heard.
- Detect when your baby is crying to trigger a lullaby
- Recognize when someone has broken a glass window in your store or home
- Know when people are yelling to be alerted of commotion