Hyperspectral image classification is gaining popularity for high-precision vision tasks in remote sensing, thanks to their ability to capture visual information available in a wide continuum of spectra.
Ranked #1 on Hyperspectral Image Classification on Houston (OA@15perclass metric)
Therefore, we perform a comprehensive study in which we investigate various DST components to find the best topology per task on well-known CIFAR100 and miniImageNet benchmarks in a task-incremental CL setup since our primary focus is to evaluate the performance of various DST criteria, rather than the process of mask selection.
This review provides a comprehensive technical overview of meta-learning, emphasizing its importance in real-world applications where data may be scarce or expensive to obtain.
Bayesian optimization (BO) is a popular method to optimize costly black-box functions.
Class-Incremental Learning updates a deep classifier with new categories while maintaining the previously observed class accuracy.
no code implementations • 15 Mar 2023 • Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Edward Bergman, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter
The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices.
We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks.
Automated machine learning has been widely researched and adopted in the field of supervised classification and regression, but progress in unsupervised settings has been limited.
Comparing different AutoML frameworks is notoriously challenging and often done incorrectly.
1 code implementation • 20 Jul 2022 • Mark Mazumder, Colby Banbury, Xiaozhe Yao, Bojan Karlaš, William Gaviria Rojas, Sudnya Diamos, Greg Diamos, Lynn He, Alicia Parrish, Hannah Rose Kirk, Jessica Quaye, Charvi Rastogi, Douwe Kiela, David Jurado, David Kanter, Rafael Mosquera, Juan Ciro, Lora Aroyo, Bilge Acun, Lingjiao Chen, Mehul Smriti Raje, Max Bartolo, Sabri Eyuboglu, Amirata Ghorbani, Emmett Goodman, Oana Inel, Tariq Kane, Christine R. Kirkpatrick, Tzu-Sheng Kuo, Jonas Mueller, Tristan Thrush, Joaquin Vanschoren, Margaret Warren, Adina Williams, Serena Yeung, Newsha Ardalani, Praveen Paritosh, Ce Zhang, James Zou, Carole-Jean Wu, Cody Coleman, Andrew Ng, Peter Mattson, Vijay Janapa Reddi
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems.
Teaching robots to learn diverse locomotion skills under complex three-dimensional environmental settings via Reinforcement Learning (RL) is still challenging.
Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.
For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques.
Automated RL provides a framework in which different components of RL including MDP modeling, algorithm selection and hyper-parameter optimization are modeled and defined automatically.
Machine learning, already at the core of increasingly many systems and applications, is set to become even more ubiquitous with the rapid rise of wearable devices and the Internet of Things.
Many machine learning libraries require that string features be converted to a numerical representation for the models to work as intended.
There is currently no consensus on how to choose appropriate source data, and in the literature we can find both evidence of favoring large natural image datasets such as ImageNet, and evidence of favoring more specialized medical datasets.
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.
One drawback however is the high computational complexity and high memory consumption of CNNs which makes them unfeasible for execution on embedded platforms which are constrained on physical resources needed to support CNNs.
1 code implementation • 12 Jan 2021 • The DarkMachines High Dimensional Sampling Group, Csaba Balázs, Melissa van Beekveld, Sascha Caron, Barry M. Dillon, Ben Farmer, Andrew Fowlie, Will Handley, Luc Hendriks, Guðlaugur Jóhannesson, Adam Leinweber, Judita Mamužić, Gregory D. Martinez, Pat Scott, Eduardo C. Garrido-Merchán, Roberto Ruiz de Austri, Zachary Searle, Bob Stienen, Joaquin Vanschoren, Martin White
Optimisation problems are ubiquitous in particle and astrophysics, and involve locating the optimum of a complicated function of many parameters that may be computationally expensive to evaluate.
Bayesian Optimisation High Energy Physics - Phenomenology Computational Physics
Bayesian Optimization is a popular tool for tuning algorithms in automatic machine learning (AutoML) systems.
Psychological theories of habit posit that when a strong habit is formed through behavioral repetition, it can trigger behavior automatically in the same environment.
Hence, we also propose a new benchmark on the DroneDeploy test set using the best performing DeepLabv3+ Xception65 architecture, with a mIOU score of 52. 5%.
Ranked #1 on Semantic Segmentation on DroneDeploy
The performance of many machine learning algorithms depends on their hyperparameter settings.
The General Automated Machine learning Assistant (GAMA) is a modular AutoML system developed to empower users to track and control how AutoML algorithms search for optimal machine learning pipelines, and facilitate AutoML research itself.
To that end, we propose 6 concept drift adaptation strategies and evaluate their effectiveness on different AutoML approaches.
It also provides functionality to conduct machine learning experiments, upload the results to OpenML, and reproduce results which are stored on OpenML.
In recent years, an active field of research has developed around automated machine learning (AutoML).
For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them.
no code implementations • 29 Mar 2019 • Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael. I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Experimental results indicate that hyperparameter tuning provides statistically significant improvements for C4. 5 and CTree in only one-third of the datasets, and in most of the datasets for CART.
In all three problems, transformative machine learning significantly outperforms the best intrinsic representation.
These characterizations, also called meta-features, describe properties of the data which are predictive for the performance of machine learning algorithms trained on them.
The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments.
With the demand for machine learning increasing, so does the demand for tools which make it easier to use.
We first carried out the most comprehensive ever comparison of machine learning methods for QSAR learning: 18 regression methods, 6 molecular representations, applied to more than 2, 700 QSAR problems.
Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks.
We show how the OpenML package allows R users to easily search, download and upload data sets and machine learning tasks.
2 code implementations • 8 Jun 2015 • Bernd Bischl, Pascal Kerschke, Lars Kotthoff, Marius Lindauer, Yuri Malitsky, Alexandre Frechette, Holger Hoos, Frank Hutter, Kevin Leyton-Brown, Kevin Tierney, Joaquin Vanschoren
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.
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.
We present OpenML and mldata, open science platforms that provides easy access to machine learning data, software and results to encourage further study and application.