Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Scholz, Randolf"'
Autor:
Yalavarthi, Vijaya Krishna, Scholz, Randolf, Madhusudhanan, Kiran, Born, Stefan, Schmidt-Thieme, Lars
Probabilistic forecasting models for joint distributions of targets in irregular time series are a heavily under-researched area in machine learning with, to the best of our knowledge, only three models researched so far: GPR, the Gaussian Process Re
Externí odkaz:
http://arxiv.org/abs/2406.07246
Probabilistic forecasting of irregularly sampled multivariate time series with missing values is an important problem in many fields, including health care, astronomy, and climate. State-of-the-art methods for the task estimate only marginal distribu
Externí odkaz:
http://arxiv.org/abs/2402.06293
Autor:
Duong-Trung, Nghia, Born, Stefan, Kim, Jong Woo, Schermeyer, Marie-Therese, Paulick, Katharina, Borisyak, Maxim, Cruz-Bournazou, Mariano Nicolas, Werner, Thorben, Scholz, Randolf, Schmidt-Thieme, Lars, Neubauer, Peter, Martinez, Ernesto
Machine learning (ML) is becoming increasingly crucial in many fields of engineering but has not yet played out its full potential in bioprocess engineering. While experimentation has been accelerated by increasing levels of lab automation, experimen
Externí odkaz:
http://arxiv.org/abs/2209.01083
Ground texture based localization methods are potential prospects for low-cost, high-accuracy self-localization solutions for robots. These methods estimate the pose of a given query image, i.e. the current observation of the ground from a downward-f
Externí odkaz:
http://arxiv.org/abs/2109.01569
Autor:
Mione, Federico M., Kaspersetz, Lucas, Luna, Martin F., Aizpuru, Judit, Scholz, Randolf, Borisyak, Maxim, Kemmer, Annina, Schermeyer, M. Therese, Martinez, Ernesto C., Neubauer, Peter, Cruz Bournazou, M. Nicolas
Publikováno v:
In Computers and Chemical Engineering August 2024 187
Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it
Externí odkaz:
http://arxiv.org/abs/2106.08267
Autor:
Pineda-Arango, Sebastian, Obando-Paniagua, David, Dedeoglu, Alperen, Kurzendörfer, Philip, Schestag, Friedemann, Scholz, Randolf
In deep learning models, learning more with less data is becoming more important. This paper explores how neural networks with normalized Radial Basis Function (RBF) kernels can be trained to achieve better sample efficiency. Moreover, we show how th
Externí odkaz:
http://arxiv.org/abs/2007.15397
Autor:
Brinkmeyer, Lukas, Drumond, Rafael Rego, Scholz, Randolf, Grabocka, Josif, Schmidt-Thieme, Lars
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial parameter set can be learned from a population of supervised learning ta
Externí odkaz:
http://arxiv.org/abs/1909.13576
The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-differentiable and non-decomposable loss function (e.g. Miss-classifica
Externí odkaz:
http://arxiv.org/abs/1905.10108
Autor:
Duong-Trung, Nghia, Born, Stefan, Kim, Jong Woo, Schermeyer, Marie-Therese, Paulick, Katharina, Borisyak, Maxim, Cruz-Bournazou, Mariano Nicolas, Werner, Thorben, Scholz, Randolf, Schmidt-Thieme, Lars, Neubauer, Peter, Martinez, Ernesto
Publikováno v:
In Biochemical Engineering Journal January 2023 190