Mineto Tsukada

Performance and Cost Evaluations of Online Sequential Learning and Unsupervised Anomaly Detection Core

2019

Toward on-device learning on IoT devices, this paper implements an online sequential learning and unsupervised anomaly detection core and explores its design options, such as pipeline structure. They are evaluated in terms of performance and …

An FPGA-Based On-Device Reinforcement Learning Approach using Online Sequential Learning

2020 · arXiv (Cornell University)

DQN (Deep Q-Network) is a method to perform Q-learning for reinforcement learning using deep neural networks. DQNs require a large buffer and batch processing for an experience replay and rely on a backpropagation based iterative …

An Overflow/Underflow-Free Fixed-Point Bit-Width Optimization Method for OS-ELM Digital Circuit

2021 · arXiv (Cornell University)

Currently there has been increasing demand for real-time training on resource-limited IoT devices such as smart sensors, which realizes standalone online adaptation for streaming data without data transfers to remote servers. OS-ELM (Online Sequential Extreme …