Search Results for author:
Found 7 papers, 2 papers with code
Probabilistic Forecasting of Irregular Time Series via Conditional Flows
Probabilistic forecasting of irregularly sampled multivariate time series with missing values is an important problem in many fields, including health care, astronomy, and climate.
When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development
ML can be seen as a set of tools that contribute to the automation of the whole experimental cycle, including model building and practical planning, thus allowing human experts to focus on the more demanding and overarching cognitive tasks.
Deep Metric Learning for Ground Images
Ground texture based localization methods are potential prospects for low-cost, high-accuracy self-localization solutions for robots.
Multi-script Handwritten Digit Recognition Using Multi-task Learning
Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated.
Improving Sample Efficiency with Normalized RBF Kernels
Experiments on CIFAR-10 and CIFAR-100 show that networks with normalized kernels as output layer can achieve higher sample efficiency, high compactness and well-separability through the presented method in comparison to networks with SoftMax output layer.
Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization.
Learning Surrogate Losses
Ultimately, the surrogate losses are learned jointly with the prediction model via bilevel optimization.
