Search Results for author: Michael Wand

Found 14 papers, 4 papers with code

Nonlinearities in Steerable SO(2)-Equivariant CNNs

no code implementations14 Sep 2021 Daniel Franzen, Michael Wand

Invariance under symmetry is an important problem in machine learning.

ActCooLR – High-Level Learning Rate Schedules using Activation Pattern Temperature

no code implementations NeurIPS 2021 David Hartmann, Sebastian Brodehl, Michael Wand

We consider the aspect of learning rate (LR-)scheduling in neural networks, which often significantly affects achievable training time and generalization performance.

Image Classification

Adversarial reverse mapping of condensed-phase molecular structures: Chemical transferability

1 code implementation13 Jan 2021 Marc Stieffenhofer, Tristan Bereau, Michael Wand

Switching between different levels of resolution is essential for multiscale modeling, but restoring details at higher resolution remains challenging.

Chemical Physics Computational Physics

Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward Networks

no code implementations ICLR 2021 Christian H.X. Ali Mehmeti-Göpel, David Hartmann, Michael Wand

In this paper, we apply harmonic distortion analysis to understand the effect of nonlinearities in the spectral domain.

Meta-Learning for Recalibration of EMG-Based Upper Limb Prostheses

no code implementations ICML Workshop LifelongML 2020 Krsto Proroković, Michael Wand, Jürgen Schmidhuber

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.

Meta-Learning

Deep Non-Line-of-Sight Reconstruction

no code implementations CVPR 2020 Javier Grau Chopite, Matthias B. Hullin, Michael Wand, Julian Iseringhausen

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.

Progressive Stochastic Binarization of Deep Networks

1 code implementation3 Apr 2019 David Hartmann, Michael Wand

By focusing computational attention using progressive sampling, we reduce inference costs on ImageNet further by a factor of up to 33% (before network pruning).

Binarization Network Pruning +1

Investigations on End-to-End Audiovisual Fusion

no code implementations30 Apr 2018 Michael Wand, Ngoc Thang Vu, Juergen Schmidhuber

Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal.

Speech Recognition

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

no code implementations4 Aug 2017 Michael Wand, Juergen Schmidhuber

We present a Lipreading system, i. e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence.

Lipreading Speech Recognition

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

2 code implementations15 Apr 2016 Chuan Li, Michael Wand

This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis.

Style Transfer Texture Synthesis

Lipreading with Long Short-Term Memory

no code implementations29 Jan 2016 Michael Wand, Jan Koutník, Jürgen Schmidhuber

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.

Lipreading Speech Recognition

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

6 code implementations CVPR 2016 Chuan Li, Michael Wand

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.

Image Generation Texture Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.