Search Results for author:
Found 15 papers, 6 papers with code
How explainable are adversarially-robust CNNs?
Here, we perform the first, large-scale evaluation of the relations of the three criteria using 9 feature-importance methods and 12 ImageNet-trained CNNs that are of 3 training algorithms and 5 CNN architectures.
Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers
Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks.
Modeling and Optimizing Laser-Induced Graphene
A lot of technological advances depend on next-generation materials, such as graphene, which enables a raft of new applications, for example better electronics.
Bayesian Optimization in Materials Science: A Survey
Bayesian optimization is used in many areas of AI for the optimization of black-box processes and has achieved impressive improvements of the state of the art for a lot of applications.
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks
FlexiBO weights the improvement of the hypervolume of the Pareto region by the measurement cost of each objective to balance the expense of collecting new information with the knowledge gained through objective evaluations, preventing us from performing expensive measurements for little to no gain.
Transfer Learning for Performance Modeling of Deep Neural Network Systems
Modern deep neural network (DNN) systems are highly configurable with large a number of options that significantly affect their non-functional behavior, for example inference time and energy consumption.
The Algorithm Selection Competitions 2015 and 2017
The algorithm selection problem is to choose the most suitable algorithm for solving a given problem instance.
Hot-Rodding the Browser Engine: Automatic Configuration of JavaScript Compilers
Modern software systems in many application areas offer to the user a multitude of parameters, switches and other customisation hooks.
mlr Tutorial
This document provides and in-depth introduction to the mlr framework for machine learning experiments in R.
ICON Challenge on Algorithm Selection
We present the results of the ICON Challenge on Algorithm Selection.
The Inductive Constraint Programming Loop
Constraint programming is used for a variety of real-world optimisation problems, such as planning, scheduling and resource allocation problems.
ASlib: A Benchmark Library for Algorithm Selection
To address this problem, we introduce a standardized format for representing algorithm selection scenarios and a repository that contains a growing number of data sets from the literature.
Ranking Algorithms by Performance
We evaluate a range of approaches to predict the ranking of a set of algorithms on a problem.
Proteus: A Hierarchical Portfolio of Solvers and Transformations
In recent years, portfolio approaches to solving SAT problems and CSPs have become increasingly common.
LLAMA: Leveraging Learning to Automatically Manage Algorithms
Algorithm portfolio and selection approaches have achieved remarkable improvements over single solvers.
