Alex Hernández-García
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Alex Hernández-García has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Peter König
University of Osnabrück
4 shared publications Peter König
University of Osnabrück
2 shared publications- Yoshua Bengio
Mila, Montréal, Canada
2 shared publications Alain Tchagang
National Research Council Canada, Ottawa, Canada
1 shared publication- Alessandro Grillini
Laboratory for Experimental Ophthalmology, University Medical Center Groningen, Groningen, Netherlands
1 shared publication - Alexandra Volokhova
MILA, Université de Montréal, Canada
1 shared publication
Latest Publications
- Open Access
- 16 January 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (2) , 910-918
OBELiX: a curated dataset of crystal structures and experimentally measured ionic conductivities for lithium solid-state electrolytes
OBELiX is a database of 599 synthesized solid electrolyte materials and their experimentally measured room temperature ionic conductivities gathered from literature and curated by domain experts.
- 16 January 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (2) , 910-918
Open AccessOBELiX: a curated dataset of crystal structures and experimentally measured ionic conductivities for lithium solid-state electrolytes
OBELiX is a database of 599 synthesized solid electrolyte materials and their experimentally measured room temperature ionic conductivities gathered from literature and curated by domain experts.
- Open Access
- 29 April 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (5) , 1038-1047
Towards equilibrium molecular conformation generation with GFlowNets
GFlowNets allow for sampling diverse, thermodynamically feasible molecular conformations from the Boltzmann distribution.
- 29 April 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (5) , 1038-1047
Open AccessTowards equilibrium molecular conformation generation with GFlowNets
GFlowNets allow for sampling diverse, thermodynamically feasible molecular conformations from the Boltzmann distribution.
- Open Access
Data augmentation instead of explicit regularization
Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay and dropout, require costly fine-tuning of sensitive hyperparameters, the interplay between them and other elements that provide implicit regularization is not well understood yet. Shedding light upon these interactions is key to efficiently using computational resources and may contribute to solving the puzzle of generalization in deep learning. Here, we first provide formal definitions of explicit and implicit regularization that help understand essential differences between techniques. Second, we contrast data augmentation with weight decay and dropout. Our results show that visual object categorization models trained with data augmentation alone achieve the same performance or higher than models trained also with weight decay and dropout, as is common practice. We conclude that the contribution on generalization of weight decay and dropout is not only superfluous when sufficient implicit regularization is provided, but also such techniques can dramatically deteriorate the performance if the hyperparameters are not carefully tuned for the architecture and data set. In contrast, data augmentation systematically provides large generalization gains and does not require hyperparameter re-tuning. In view of our results, we suggest to optimize neural networks without weight decay and dropout to save computational resources, hence carbon emissions, and focus more on data augmentation and other inductive biases to improve performance and robustness.
Open AccessData augmentation instead of explicit regularization
Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay and dropout, require costly fine-tuning of sensitive hyperparameters, the interplay between them and other elements that provide implicit regularization is not well understood yet. Shedding light upon these interactions is key to efficiently using computational resources and may contribute to solving the puzzle of generalization in deep learning. Here, we first provide formal definitions of explicit and implicit regularization that help understand essential differences between techniques. Second, we contrast data augmentation with weight decay and dropout. Our results show that visual object categorization models trained with data augmentation alone achieve the same performance or higher than models trained also with weight decay and dropout, as is common practice. We conclude that the contribution on generalization of weight decay and dropout is not only superfluous when sufficient implicit regularization is provided, but also such techniques can dramatically deteriorate the performance if the hyperparameters are not carefully tuned for the architecture and data set. In contrast, data augmentation systematically provides large generalization gains and does not require hyperparameter re-tuning. In view of our results, we suggest to optimize neural networks without weight decay and dropout to save computational resources, hence carbon emissions, and focus more on data augmentation and other inductive biases to improve performance and robustness.
- Open Access
- 1 July 2020
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 20 (7) , 27
Global visual salience of competing stimuli
Current computational models of visual salience accurately predict the distribution of fixations on isolated visual stimuli. It is not known, however, whether the global salience of a stimulus, that is, its effectiveness in the competition for attention with other stimuli, is a function of the local salience or an independent measure. Further, do task and familiarity with the competing images influence eye movements? Here, we investigated the direction of the first saccade to characterize and analyze the global visual salience of competing stimuli. Participants freely observed pairs of images while eye movements were recorded. The pairs balanced the combinations of new and already seen images, as well as task and task-free trials. Then, we trained a logistic regression model that accurately predicted the location—left or right image—of the first fixation for each stimulus pair, accounting too for the influence of task, familiarity, and lateral bias. The coefficients of the model provided a reliable measure of global salience, which we contrasted with two distinct local salience models, GBVS and Deep Gaze. The lack of correlation of the behavioral data with the former and the small correlation with the latter indicate that global salience cannot be explained by the feature-driven local salience of images. Further, the influence of task and familiarity was rather small, and we reproduced the previously reported left-sided bias. Summarized, we showed that natural stimuli have an intrinsic global salience related to the human initial gaze direction, independent of the local salience and little influenced by task and familiarity.
- 1 July 2020
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 20 (7) , 27
Open AccessGlobal visual salience of competing stimuli
Current computational models of visual salience accurately predict the distribution of fixations on isolated visual stimuli. It is not known, however, whether the global salience of a stimulus, that is, its effectiveness in the competition for attention with other stimuli, is a function of the local salience or an independent measure. Further, do task and familiarity with the competing images influence eye movements? Here, we investigated the direction of the first saccade to characterize and analyze the global visual salience of competing stimuli. Participants freely observed pairs of images while eye movements were recorded. The pairs balanced the combinations of new and already seen images, as well as task and task-free trials. Then, we trained a logistic regression model that accurately predicted the location—left or right image—of the first fixation for each stimulus pair, accounting too for the influence of task, familiarity, and lateral bias. The coefficients of the model provided a reliable measure of global salience, which we contrasted with two distinct local salience models, GBVS and Deep Gaze. The lack of correlation of the behavioral data with the former and the small correlation with the latter indicate that global salience cannot be explained by the feature-driven local salience of images. Further, the influence of task and familiarity was rather small, and we reproduced the previously reported left-sided bias. Summarized, we showed that natural stimuli have an intrinsic global salience related to the human initial gaze direction, independent of the local salience and little influenced by task and familiarity.
- Open Access
Further advantages of data augmentation on convolutional neural networks
Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we systematically analyze these techniques through ablation studies of different network architectures trained with different amounts of training data. Our results unveil a largely ignored advantage of data augmentation: networks trained with just data augmentation more easily adapt to different architectures and amount of training data, as opposed to weight decay and dropout, which require specific fine-tuning of their hyperparameters.
Open AccessFurther advantages of data augmentation on convolutional neural networks
Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we systematically analyze these techniques through ablation studies of different network architectures trained with different amounts of training data. Our results unveil a largely ignored advantage of data augmentation: networks trained with just data augmentation more easily adapt to different architectures and amount of training data, as opposed to weight decay and dropout, which require specific fine-tuning of their hyperparameters.
- 22 February 2019
- Published by SAGE Publications in Web Intelligence
- Vol. 17 (1) , 29-40
Emotion and attention: Audiovisual models for group-level skin response recognition in short movies
The electrodermal activity (EDA) is a psychophysiological indicator which can be considered a somatic marker of the emotional and attentional reaction of subjects towards stimuli. EDA measurements are not biased by the cognitive process of giving an
- 22 February 2019
- Published by SAGE Publications in Web Intelligence
- Vol. 17 (1) , 29-40
Emotion and attention: Audiovisual models for group-level skin response recognition in short movies
The electrodermal activity (EDA) is a psychophysiological indicator which can be considered a somatic marker of the emotional and attentional reaction of subjects towards stimuli. EDA measurements are not biased by the cognitive process of giving an
- Open Access
- 1 January 2019
- Published by Cognitive Computational Neuroscience
Learning robust visual representations using data augmentation invariance
- 1 January 2019
- Published by Cognitive Computational Neuroscience
Open AccessLearning robust visual representations using data augmentation invariance
- 27 September 2018
- Published by Springer Nature
- p. 95-103
Further Advantages of Data Augmentation on Convolutional Neural Networks
- 27 September 2018
- Published by Springer Nature
- p. 95-103
Further Advantages of Data Augmentation on Convolutional Neural Networks