We introduce the neural echo as a tool for understanding the behavior of neural networks. It generalizes the model-based concepts of impulse responses, diffusion echoes, and filter echoes to learning-based methods.
arXiv:2608. 04864v1 Announce Type: cross Abstract: We introduce the neural echo as a tool for understanding the behavior of neural networks.
arXiv:2607. 15693v1 Announce Type: cross Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.
arXiv:2503. 22223v2 Announce Type: replace Abstract: The semi-airborne transient electromagnetic method (SATEM) is capable of conducting rapid surveys over large-scale and hard-to-reach areas.
arXiv:2506. 14202v4 Announce Type: replace-cross Abstract: End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability.
arXiv:2606. 08309v1 Announce Type: new Abstract: Score-based generative models have had remarkable success over the last decade in generating a diverse set of visually plausible images.
arXiv:2606. 26204v1 Announce Type: new Abstract: Floods frequently impact regions around the world.
arXiv:2607. 11533v1 Announce Type: cross Abstract: Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma.
arXiv:2508. 21172v3 Announce Type: replace-cross Abstract: Echo State Networks (ESNs) are a particular type of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) framework, popular for their fast and efficient learning.
arXiv:2509. 24122v3 Announce Type: replace Abstract: At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences?
arXiv:2607. 16295v1 Announce Type: cross Abstract: Mechanistic interpretability has made significant strides in understanding neural network representations, with sparse dictionary learning (SDL) methods, most prominently sparse autoencoders, as a central paradigm.
arXiv:2607. 08406v1 Announce Type: new Abstract: Backpropagation (BP) dominates deep learning training, but its reliance on gradients brings inherent troubles -- vanishing and exploding gradients.
arXiv:2606. 18303v1 Announce Type: cross Abstract: We develop a mathematically explicit link between shock-wave theory and the symmetry-quotiented learning dynamics of stochastic gradient descent, drawing on differential geometry, Lie group theory, and fluid mechanics.