Deep CNN sparse coding analysis: Towards average case
Deep convolutional sparse coding (D-CSC) is a framework reminiscent of deep convolutional neural nets (DCNN), but by omitting the learning of the dictionaries one can more transparently analyse the role of the activation function and its ability to recover activation paths through the layers. Papyan...
Päätekijät: | Murray, M, Tanner, J |
---|---|
Aineistotyyppi: | Conference item |
Julkaistu: |
Institute of Electrical and Electronics
2018
|
Samankaltaisia teoksia
-
Deep CNN-LSTM supervised model and CNN self-supervised model for human activity recognition
Tekijä: Liao, Zixin
Julkaistu: (2023) -
Toward efficient deep learning with sparse neural networks
Tekijä: Lee, N
Julkaistu: (2020) -
Smart sleep monitoring: sparse sensor-based spatiotemporal CNN for sleep posture detection
Tekijä: Hu, Dikun, et al.
Julkaistu: (2024) -
Dynamic sparse no training: training-free fine-tuning for sparse llms
Tekijä: Tanner, J
Julkaistu: (2024) -
Deformation-invariant sparse coding
Tekijä: Chen, George H
Julkaistu: (2012)