Research topic
This topic page groups Naser Ezzati-Jivan research papers related to deep learning systems. Each linked record provides the paper's problem, method, findings, limitations, keywords, and authoritative source links.
Related search terms: deep learning systems
4 papers in this topic, ordered newest first. The detailed paper records contain the evidence-grounded methods, tools, datasets, findings, and citation guidance.
2025 · arXiv / CoRR
DEBA is an architecture-aware adaptive batch scheduler that uses training-stability signals to decide when and how to change batch size.
Keywords: DEBA · adaptive batch size · gradient variance · training speedup · ResNet
2024 · Software Impacts
The paper proposes a two-tier IoT intrusion detector that first separates normal from anomalous flows and then classifies the attack type with a CNN-BiLSTM model.
Keywords: IoT anomaly detection · CNN-BiLSTM · SMOTE · particle swarm optimization · PSO
2023 · ACM/IFIP/USENIX Middleware 2023 Industry Track
The paper applies a CNN-BiLSTM intrusion classifier to RPL/IoT traffic, combining convolutional feature extraction with bidirectional sequence modeling after imbalance-aware flow preprocessing.
Keywords: RPL attacks · IoT smart grid · CNN-BiLSTM · routing attacks · intrusion detection
2022 · ACM/IFIP/USENIX Middleware 2022 Demos/Posters
The poster proposes a hybrid IoT intrusion-detection pipeline with binary anomaly detection followed by multiclass attack classification.
Keywords: IoTID20 · RNN · SMOTE · PSO · binary classification