We consider the aspect of learning rate (LR-)scheduling in neural networks, which often significantly affects achievable training time and generalization performance.
Switching between different levels of resolution is essential for multiscale modeling, but restoring details at higher resolution remains challenging.
Chemical Physics Computational Physics
In this paper, we apply harmonic distortion analysis to understand the effect of nonlinearities in the spectral domain.
An EMG-based upper limb prosthesis relies on a statistical pattern recognition system to map the EMG signal of residual forearm muscles into the appropriate hand movements.
We demonstrate that our feed-forward network, even though it is trained solely on synthetic data, generalizes to measured data from SPAD sensors and is able to obtain results that are competitive with model-based reconstruction methods.
By focusing computational attention using progressive sampling, we reduce inference costs on ImageNet further by a factor of up to 33% (before network pruning).
We present a Lipreading system, i. e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence.
This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis.
Lipreading, i. e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods.
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.
In this paper, we introduce a new approach to partial, intrinsic isometric matching.