Search Results for author:
Found 25 papers, 7 papers with code
Fast Inference of Tree Ensembles on ARM Devices
Second, we extend our implementation from ranking models to classification models such as Random Forests.
Energy Efficiency Considerations for Popular AI Benchmarks
Advances in artificial intelligence need to become more resource-aware and sustainable.
Self-Supervised Pretraining of Graph Neural Network for the Retrieval of Related Mathematical Expressions in Scientific Articles
This is mainly due to the retrieval with keyword queries: technical terms differ in different sciences or at different times.
Shrub Ensembles for Online Classification
Among the most successful online learning methods are Decision Tree (DT) ensembles.
There is no Double-Descent in Random Forests
Last, we study the diversity of an ensemble as a tool the estimate its performance.
Improving the Accuracy-Memory Trade-Off of Random Forests Via Leaf-Refinement
In this paper, we revisit ensemble pruning in the context of `modernly' trained Random Forests where trees are very large.
Explaining Deep Learning Representations by Tracing the Training Process
We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process.
Noisy Labels for Weakly Supervised Gamma Hadron Classification
Gamma hadron classification, a central machine learning task in gamma ray astronomy, is conventionally tackled with supervised learning.
The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning
On the other hand, care labels are the result of a certification suite that tests whether stated guarantees hold.
Providing Meaningful Data Summarizations Using Exemplar-based Clustering in Industry 4.0
Data summarizations are a valuable tool to derive knowledge from large data streams and have proven their usefulness in a great number of applications.
Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework
How can they be guaranteed for a certain implementation of a machine learning model?
Bit Error Tolerance Metrics for Binarized Neural Networks
In this study, our objective is to investigate the internal changes in the NNs that bit flip training causes, with a focus on binarized NNs (BNNs).
GPU-Accelerated Optimizer-Aware Evaluation of Submodular Exemplar Clustering
The optimization of submodular functions constitutes a viable way to perform clustering.
Fighting Filterbubbles with Adversarial BERT-Training for News-Recommendation
Our experiments show that the features we can extract this way are significantly less predictive of the news outlet and thus offer the possibility to reduce the risk of manifestation of new filter bubbles.
Generalized Negative Correlation Learning for Deep Ensembling
Ensemble algorithms offer state of the art performance in many machine learning applications.
Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots.
Very Fast Streaming Submodular Function Maximization
Data summarization has become a valuable tool in understanding even terabytes of data.
Resource-Constrained On-Device Learning by Dynamic Averaging
This paper investigates an approach to communication-efficient on-device learning of integer exponential families that can be executed on low-power processors, is privacy-preserving, and effectively minimizes communication.
Towards Explainable Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks
Finally, we explore the influence of a novel regularizer that optimizes with respect to this metric, with the aim of providing a configurable trade-off in accuracy and BET.
The SpectACl of Nonconvex Clustering: A Spectral Approach to Density-Based Clustering
When it comes to clustering nonconvex shapes, two paradigms are used to find the most suitable clustering: minimum cut and maximum density.
The Trustworthy Pal: Controlling the False Discovery Rate in Boolean Matrix Factorization
The Boolean product is a disjunction of rank-1 binary matrices, each describing a feature-relation, called pattern, for a group of samples.
The PRIMPing Routine -- Tiling through Proximal Alternating Linearized Minimization
In contrast to existing work, the new algorithm minimizes the description length of the resulting factorization.
C-SALT: Mining Class-Specific ALTerations in Boolean Matrix Factorization
Given labeled data represented by a binary matrix, we consider the task to derive a Boolean matrix factorization which identifies commonalities and specifications among the classes.
Evolution of Eigenvalue Decay in Deep Networks
The linear transformations in converged deep networks show fast eigenvalue decay.
Machine Learning meets Data-Driven Journalism: Boosting International Understanding and Transparency in News Coverage
Migration crisis, climate change or tax havens: Global challenges need global solutions.
