Search Results for author:
Found 23 papers, 13 papers with code
Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary
The increasing use of deep learning across various domains highlights the importance of understanding the decision-making processes of these black-box models.
Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks
In this work, we propose a novel parameter search method to improve the quality of these linear approximations.
AI Competitions and Benchmarks: Dataset Development
Initially, we develop the tasks involved in dataset development and offer insights into their effective management (including requirements, design, implementation, evaluation, distribution, and maintenance).
Subspace Adaptation Prior for Few-Shot Learning
Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent.
Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques
Whilst meta-learning techniques have been observed to be successful at this in various scenarios, recent results suggest that when evaluated on tasks from a different data distribution than the one used for training, a baseline that simply finetunes a pre-trained network may be more effective than more complicated meta-learning techniques such as MAML, which is one of the most popular meta-learning techniques.
Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward
Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet.
Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
In this domain, one of the more investigated approaches is the use of a special type of quantum circuit - a so-called quantum neural network -- to serve as a basis for a machine learning model.
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available.
Learning Curves for Decision Making in Supervised Machine Learning -- A Survey
Learning curves are a concept from social sciences that has been adopted in the context of machine learning to assess the performance of a learning algorithm with respect to a certain resource, e. g. the number of training examples or the number of training iterations.
Fast and Informative Model Selection using Learning Curve Cross-Validation
Common cross-validation (CV) methods like k-fold cross-validation or Monte-Carlo cross-validation estimate the predictive performance of a learner by repeatedly training it on a large portion of the given data and testing on the remaining data.
Meta-Learning for Symbolic Hyperparameter Defaults
Hyperparameter optimization in machine learning (ML) deals with the problem of empirically learning an optimal algorithm configuration from data, usually formulated as a black-box optimization problem.
Towards Model Selection using Learning Curve Cross-Validation
We run a large scale experiment on the 67 datasets from the AutoML benchmark, and empirically show that LCCV in over 90\% of the cases leads to similar performance (at most 0. 5\% difference) as 10-fold CV, but provides additional insights on the behaviour of a given model.
Stateless Neural Meta-Learning using Second-Order Gradients
Deep learning typically requires large data sets and much compute power for each new problem that is learned.
A Survey of Deep Meta-Learning
Meta-learning is one approach to address this issue, by enabling the network to learn how to learn.
OpenML-Python: an extensible Python API for OpenML
It also provides functionality to conduct machine learning experiments, upload the results to OpenML, and reproduce results which are stored on OpenML.
Learning Multiple Defaults for Machine Learning Algorithms
The performance of modern machine learning methods highly depends on their hyperparameter configurations.
Don't Rule Out Simple Models Prematurely: A Large Scale Benchmark Comparing Linear and Non-linear Classifiers in OpenML
A basic step for each data-mining or machine learning task is to determine which model to choose based on the problem and the data at hand.
The Algorithm Selection Competitions 2015 and 2017
The algorithm selection problem is to choose the most suitable algorithm for solving a given problem instance.
OpenML Benchmarking Suites
Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks.
The Complexity of Rummikub Problems
Rummikub is a tile-based game in which each player starts with a hand of $14$ tiles.
Computational Complexity
Endgame Analysis of Dou Shou Qi
Dou Shou Qi is a game in which two players control a number of pieces, each of them aiming to move one of their pieces onto a given square.
OpenML: networked science in machine learning
Many sciences have made significant breakthroughs by adopting online tools that help organize, structure and mine information that is too detailed to be printed in journals.
