Search Results for author: Maximilian Alber

Found 11 papers, 6 papers with code

iNNvestigate neural networks!

1 code implementation13 Aug 2018 Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele, Kristof T. Schütt, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller, Sven Dähne, Pieter-Jan Kindermans

The presented library iNNvestigate addresses this by providing a common interface and out-of-the- box implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods.

Interpretable Machine Learning

Software and application patterns for explanation methods

1 code implementation9 Apr 2019 Maximilian Alber

Building on this we show how explanation methods can be used in applications to understand predictions for miss-classified samples, to compare algorithms or networks, and to examine the focus of networks.

Autonomous Driving

Distributed Optimization of Multi-Class SVMs

1 code implementation25 Nov 2016 Maximilian Alber, Julian Zimmert, Urun Dogan, Marius Kloft

Training of one-vs.-rest SVMs can be parallelized over the number of classes in a straight forward way.

Distributed Optimization General Classification +2

Backprop Evolution

no code implementations8 Aug 2018 Maximilian Alber, Irwan Bello, Barret Zoph, Pieter-Jan Kindermans, Prajit Ramachandran, Quoc Le

The back-propagation algorithm is the cornerstone of deep learning.

Balancing the composition of word embeddings across heterogenous data sets

no code implementations14 Jan 2020 Stephanie Brandl, David Lassner, Maximilian Alber

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications.

Word Embeddings Word Similarity

Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides

no code implementations3 Feb 2023 Miriam Hägele, Johannes Eschrich, Lukas Ruff, Maximilian Alber, Simon Schallenberg, Adrien Guillot, Christoph Roderburg, Frank Tacke, Frederick Klauschen

Motivated by the medical application, we demonstrate for general segmentation tasks that including additional patches with solely weak complementary labels during model training can significantly improve the predictive performance and robustness of a model.

Segmentation Semantic Segmentation +1

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