The most common normalization method, batch normalization, reduces the distribution shift during training but is agnostic to changes in the input distribution during test time.
In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases.
Our experiments show, that the use of CVCNNs increases data efficiency, speeds up network training and substantially improves the conservation of phase information during interference removal.
This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments.
Ranked #17 on Keyword Spotting on Google Speech Commands (Google Speech Commands V2 12 metric)
In this paper, we present the Blind Speech Separation and Dereverberation (BSSD) network, which performs simultaneous speaker separation, dereverberation and speaker identification in a single neural network.
This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments.
We combine real measurements with simulated interference in order to create input-output data suitable for training the model.
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles.
While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches.
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches.
Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs.
Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately.
Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment.
As a result, PSP maintains prediction performance, creates a substantial amount of sparsity that is structured and, thus, easy and efficient to map to a variety of massively parallel processors, which are mandatory for utmost compute power and energy efficiency.
While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure learners, most of them are somewhat ad-hoc and based on intuition rather than a clear learning principle.
It seems to be a pearl of conventional wisdom that parameter learning in deep sum-product networks is surprisingly fast compared to shallow mixture models.
In this work we propose a method for weight and activation quantization that is scalable in terms of quantization levels (n-ary representations) and easy to compute while maintaining the performance close to full-precision CNNs.
no code implementations • 5 Dec 2018 • Franz Pernkopf, Wolfgang Roth, Matthias Zoehrer, Lukas Pfeifenberger, Guenther Schindler, Holger Froening, Sebastian Tschiatschek, Robert Peharz, Matthew Mattina, Zoubin Ghahramani
In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems.
In this paper, we introduce a natural and expressive way to tackle these problems, by incorporating GPs in sum-product networks (SPNs), a recently proposed tractable probabilistic model allowing exact and efficient inference.
We consider higher-order linear-chain conditional random fields (HO-LC-CRFs) for sequence modelling, and use sum-product networks (SPNs) for representing higher-order input- and output-dependent factors.
The increasing demand for neural networks (NNs) being employed on embedded devices has led to plenty of research investigating methods for training low precision NNs.
Moreover, we show that this fixed point gives a good approximation, and the NPHC method is able to obtain this fixed point.
We discuss conditional independencies in augmented SPNs, formally establish the probabilistic interpretation of the sum-weights and give an interpretation of augmented SPNs as Bayesian networks.