A CNN with attention and shared latent space recovers SFHs and metallicities from spectro-photometric data with ~0.12 dex age and ~0.03 dex metallicity dispersion while running thousands of times faster than full spectral fitting.
A guide to convolution arithmetic for deep learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 5representative citing papers
A multi-delay sinc network jointly aligns speech signals with delayed continuous emotion labels and predicts arousal/valence, claiming state-of-the-art speech-only results on RECOLA and SEWA.
LTBs-KAN delivers linear-time B-spline evaluation in KANs plus parameter reduction via product-of-sums factorization, with competitive results on MNIST, Fashion-MNIST, and CIFAR-10.
Compares feedforward, recurrent, sequence-to-sequence and temporal convolutional neural networks for short-term electric load forecasting through experiments on two real datasets.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
citing papers explorer
-
LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks
LTBs-KAN delivers linear-time B-spline evaluation in KANs plus parameter reduction via product-of-sums factorization, with competitive results on MNIST, Fashion-MNIST, and CIFAR-10.