e-G2C: A 0.14-to-8.31 µJ/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM.
Yang ZhaoYongan ZhangYonggan FuXu OuyangCheng WanShang WuAnton BantaMathews M. JohnAllison PostMehdi RazaviJoseph R. CavallaroBehnaam AazhangYingyan LinPublished in: VLSI Technology and Circuits (2022)
Keyphrases
- anomaly detection
- high speed
- single chip
- neural network
- anomalous behavior
- intrusion detection
- detecting anomalies
- network intrusion detection
- ibm power processor
- processor core
- network traffic
- unsupervised anomaly detection
- knn
- intrusion detection system
- network anomaly detection
- artificial neural networks
- computer security
- detecting anomalous
- ecg signals
- bayesian networks
- ibm zenterprise
- network intrusion
- one class support vector machines
- malware detection
- behavior analysis
- cumulative sum
- detect anomalies
- instruction set
- negative selection algorithm
- unsupervised learning
- high dimensional
- connectionist systems
- network security
- genetic algorithm