PatchEchoClassifier combines an echo state network with DeiT-style distillation from an MLP-Mixer teacher to reach about 86% accuracy on SHL human activity data at much lower FLOPs, though it falls below 80% on four other public HAR datasets.
Improving deep learning for har with shallow lstms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition
PatchEchoClassifier combines an echo state network with DeiT-style distillation from an MLP-Mixer teacher to reach about 86% accuracy on SHL human activity data at much lower FLOPs, though it falls below 80% on four other public HAR datasets.