Search Results for author: Lars Hertel

Found 11 papers, 3 papers with code

Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning

no code implementations29 Jul 2020 Lars Hertel, Pierre Baldi, Daniel L. Gillen

Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds.

Bayesian Optimization Hyperparameter Optimization +2

Deep Convolutional Neural Networks as Generic Feature Extractors

no code implementations6 Oct 2017 Lars Hertel, Erhardt Barth, Thomas Käster, Thomas Martinetz

Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task.

General Classification Image Classification

Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling

1 code implementation11 Jul 2016 Lars Hertel, Huy Phan, Alfred Mertins

We trained a deep all-convolutional neural network with masked global pooling to perform single-label classification for acoustic scene classification and multi-label classification for domestic audio tagging in the DCASE-2016 contest.

Acoustic Scene Classification Audio Tagging +5

CNN-LTE: a Class of 1-X Pooling Convolutional Neural Networks on Label Tree Embeddings for Audio Scene Recognition

no code implementations8 Jul 2016 Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins

This category taxonomy is then used in the feature extraction step in which an audio scene instance is represented by a label tree embedding image.

Scene Recognition

CaR-FOREST: Joint Classification-Regression Decision Forests for Overlapping Audio Event Detection

no code implementations8 Jul 2016 Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins

The regression phase is then carried out to let the positive audio segments vote for the event onsets and offsets, and therefore model the temporal structure of audio events.

Event Detection General Classification +1

Label Tree Embeddings for Acoustic Scene Classification

no code implementations25 Jun 2016 Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins

We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels.

Acoustic Scene Classification Classification +3

Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks

1 code implementation21 Apr 2016 Huy Phan, Lars Hertel, Marco Maass, Alfred Mertins

We present in this paper a simple, yet efficient convolutional neural network (CNN) architecture for robust audio event recognition.

Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning

no code implementations18 Mar 2016 Lars Hertel, Huy Phan, Alfred Mertins

Recognizing acoustic events is an intricate problem for a machine and an emerging field of research.

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