Automated deep learning: Neural architecture search is not the end

X Dong, DJ Kedziora, K Musial… - … and Trends® in …, 2024 - nowpublishers.com
Deep learning (DL) has proven to be a highly effective approach for developing models in
diverse contexts, including visual perception, speech recognition, and machine translation …

AlphaD3M: Machine learning pipeline synthesis

I Drori, Y Krishnamurthy, R Rampin… - arXiv preprint arXiv …, 2021 - arxiv.org
We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta
reinforcement learning using sequence models with self play. AlphaD3M is based on edit …

[图书][B] The science of deep learning

I Drori - 2022 - books.google.com
The Science of Deep Learning emerged from courses taught by the author that have
provided thousands of students with training and experience for their academic studies, and …

mlr3pipelines-flexible machine learning pipelines in r

M Binder, F Pfisterer, M Lang, L Schneider… - Journal of Machine …, 2021 - jmlr.org
Recent years have seen a proliferation of ML frameworks. Such systems make ML
accessible to non-experts, especially when combined with powerful parameter tuning and …

Deepline: Automl tool for pipelines generation using deep reinforcement learning and hierarchical actions filtering

Y Heffetz, R Vainshtein, G Katz, L Rokach - Proceedings of the 26th ACM …, 2020 - dl.acm.org
Automatic Machine Learning (AutoML) is an area of research aimed at automating Machine
Learning (ML) activities that currently require the involvement of human experts. One of the …

Autonoml: Towards an integrated framework for autonomous machine learning

DJ Kedziora, K Musial, B Gabrys - arXiv preprint arXiv:2012.12600, 2020 - arxiv.org
Over the last decade, the long-running endeavour to automate high-level processes in
machine learning (ML) has risen to mainstream prominence, stimulated by advances in …

Automatic machine learning by pipeline synthesis using model-based reinforcement learning and a grammar

I Drori, Y Krishnamurthy, R Lourenco, R Rampin… - arXiv preprint arXiv …, 2019 - arxiv.org
Automatic machine learning is an important problem in the forefront of machine learning.
The strongest AutoML systems are based on neural networks, evolutionary algorithms, and …

Toward machine learning optimization of experimental design

AG Baydin, K Cranmer, PC Manzano… - Nuclear Physics …, 2021 - Taylor & Francis
The design of instruments that rely on the interaction of radiation with matter for their
operation is a quite complex task if our goal is to achieve near optimality on some well …

A survey on trusted distributed artificial intelligence

MA Ağca, S Faye, D Khadraoui - IEEE Access, 2022 - ieeexplore.ieee.org
Emerging Artificial Intelligence (AI) systems are revolutionizing computing and data
processing approaches with their strong impact on society. Data is processed with …

WindTunnel: towards differentiable ML pipelines beyond a single model

GI Yu, S Amizadeh, S Kim, A Pagnoni… - Proceedings of the …, 2021 - dl.acm.org
While deep neural networks (DNNs) have shown to be successful in several domains like
computer vision, non-DNN models such as linear models and gradient boosting trees are …