18384525. RESOURCE EFFICIENT FEDERATED EDGE LEARNING WITH HYPERDIMENSIONAL COMPUTING simplified abstract (Intel Corporation)
Contents
RESOURCE EFFICIENT FEDERATED EDGE LEARNING WITH HYPERDIMENSIONAL COMPUTING
Organization Name
Inventor(s)
Sergey Andreev of Tampere (FI)
Nageen Himayat of Fremont CA (US)
RESOURCE EFFICIENT FEDERATED EDGE LEARNING WITH HYPERDIMENSIONAL COMPUTING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18384525 titled 'RESOURCE EFFICIENT FEDERATED EDGE LEARNING WITH HYPERDIMENSIONAL COMPUTING
Simplified Explanation
The abstract describes a device for training a hyperdimensional computing (HDC) model, which includes memory and processing circuitry to train independent sub models of the HDC model and transmit them to another computing device.
- The device can be used in edge computing devices, IoT nodes, or similar devices.
- Training the independent sub models involves transforming training data points into hyperdimensional representations, initializing a prototype with these representations, and iteratively training the prototype.
---
- Potential Applications
- Edge computing
- Internet of Things (IoT) devices
- Machine learning and artificial intelligence applications
- Problems Solved
- Efficient training of hyperdimensional computing models
- Transmission of trained models to other devices
- Benefits
- Faster training process
- Improved model accuracy
- Scalability for large datasets
Original Abstract Submitted
A device to train a hyperdimensional computing (HDC) model may include memory and processing circuitry to train one or more independent sub models of the HDC model and transmit the one or more independent sub models to another computing device, such as a server. The device may be one of a plurality of devices, such as edge computing devices, edge or Internet of Things (IoT) nodes, or the like. Training of the one or more independent sub models of the HDC model may include transforming one or more training data points to one or more hyperdimensional representations, initializing a prototype using the hyperdimensional representations of the one or more training data points, and iteratively training the initialized prototype.