Download
Machine learning models for edge devices need to have a small footprint in terms of storage, prediction latency, and energy. One instance of where such models are desirable is resource-scarce devices and sensors in the Internet of Things (IoT) setting. Making real-time predictions locally on IoT devices without connecting to the cloud requires models that fit in a few kilobytes.These algorithms can train models for classical supervised learning problems with memory requirements that are orders of magnitude lower than other modern ML algorithms. The trained models can be loaded onto edge devices such as IoT devices/sensors, and used to make fast and accurate predictions completely offline. A tool that adapts models trained by above algorithms to be inferred by fixed point arithmetic.
Features
- Strong and shallow non-linear tree based classifier
- Prototype based k-nearest neighbors (kNN) classifier
- Training routine to recover the critical signature from time series data for faster and accurate RNN predictions
- A meta-architecture for training RNNs that can be applied to streaming data
- Deep Robust One-Class Classfiication for training robust anomaly detectors
- An efficient non-linear pooling operator for RAM constrained inference
