talks


Adversarially-trained linear regression (November 2022)
   Uppsala University, Sweden @ System and Control Division (Microseminar).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön
Adversarial Attacks in Linear Regression (November 2022)
   Seminars on Advances in Probabilistic Machine Learning @ Aalto University and ELLIS unit Helsinki.

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

Abstract: State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial attacks are a popular framework for studying these vulnerabilities. They consider worst-case input disturbances designed to maximize model error and got a lot of attention due to their impact on the performance of state-of-the-art models. Adversarial training considers extending model training with these examples and is an effective approach to defend against such attacks. This talk will explore adversarial attacks and training in linear regression. There is a strong reason for this focus, for linear regression, adversarial training can be formulated as a convex and quadratic problem. Moreover, many interesting phenomena that can be observed in nonlinear models are still present. The setup is used to study the role of high dimensionality in robustness. And to reveal the connection between adversarial training, parameter-shrinking methods and minimum-norm solutions.

Related publications:
  • Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön
Learning signals and systems and its applications to electrocardiography (June 2022)
   Aalto University, Finland @ Jobtalk (Online).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Automatic diagnosis of the 12-lead ECG using a deep neural network (2020). Nature Communications. Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., Thomas B. Schön, Antonio Luiz P. Ribeiro
Overparameterized Linear Regression under Adversarial Attacks (June 2022)
   University of British Columbia, Canada @ Christos Thrampoulidis group (Online).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

Abstract: State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial attacks are a popular framework for studying these vulnerabilities and got a lot of attention due to their high impact on deep neural network performance. Adversarial training is one of the most effective approaches to defending against such adversarial examples and considers adversarially perturbed samples during training to produce more robust models. This talk will explore adversarial attacks and training in a simpler setting than it is usually studied, linear regression. There is a strong reason for this focus, for linear regression models adversarial training can be simplified into a convex and quadratic form. Moreover, a lot of interesting phenomena that can still be observed in nonlinear models are still present. The setup is used to study how high-dimensionality can be either a source of additional robustness or brittleness. And also to show, in the linear setting, similarities (and differences) between $\ell_\infty$-adversarial training and the lasso and between $\ell_2$-adversarial training and ridge regression.

Related publications:
  • Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön
Deep Neural Networks for Automatic ECG Analysis (March 2022)
   University of Luxembourg @ Systems Control Group, LCSB (Online).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Automatic diagnosis of the 12-lead ECG using a deep neural network (2020). Nature Communications. Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., Thomas B. Schön, Antonio Luiz P. Ribeiro
  • Deep neural network estimated electrocardiographic-age as a mortality predictor (2021). Nature Communications. Emilly M. Lima, Antônio H. Ribeiro, Gabriela MM Paixão, Manoel Horta Ribeiro, Marcelo M. Pinto Filho, Paulo R. Gomes, Derick M. Oliveira, Ester C. Sabino, Bruce B. Duncan, Luana Giatti, Sandhi M. Barreto, Wagner Meira, Thomas B. Schön, Antonio Luiz P. Ribeiro
  • Atrial fibrillation risk prediction from the 12-lead ECG using digital biomarkers and deep representation learning (2021). European Heart Journal - Digital Health. Shany Biton, Sheina Gendelman, Antônio H Ribeiro, Gabriela Miana, Carla Moreira, Antonio Luiz P Ribeiro, Joachim A Behar
On the robustness of overparametrized models (Nov. 2021)
   Uppsala University, Sweden @ System and Control Division (Microseminar).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Overparametrized Regression Under L2 Adversarial Attacks (2021). Workshop on the Theory of Overparameterized Machine Learning (TOPML). Antonio H Ribeiro, Thomas B Schön
  • Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (2021). Proceedings of the 19th IFAC Symposium on System Identification (SYSID) - IFAC-PapersOnLine. Antônio H. Ribeiro, Johannes N. Hendriks, Adrian G. Wills, Thomas B. Schön
Aprendendo modelos para sinais e sistemas (Oct. 2021)
   Premio UFMG de Teses.


This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Learning nonlinear differentiable models for signals and systems: with applications (2020). . Antônio H. Ribeiro
Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (July 2021)
   19th IFAC symposium on System Identification: learning models for decision and control.

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (2021). Proceedings of the 19th IFAC Symposium on System Identification (SYSID) - IFAC-PapersOnLine. Antônio H. Ribeiro, Johannes N. Hendriks, Adrian G. Wills, Thomas B. Schön
How convolutional neural networks deal with aliasing (June 2021)
   IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • How convolutional neural networks deal with aliasing (2021). IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Antonio H. Ribeiro, Thomas B. Schon
Overparametrized Regression Under L2 Adversarial Attacks (April 2021)
   Workshop on the Theory of Overparameterized Machine Learning.


This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Overparametrized Regression Under L2 Adversarial Attacks (2021). Workshop on the Theory of Overparameterized Machine Learning (TOPML). Antonio H Ribeiro, Thomas B Schön
Artificial intelligence for ECG classifcation and prediction of the risk of death (April 2021)
   International Congress on Electrocardiology (Online).


This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Deep neural network estimated electrocardiographic-age as a mortality predictor (2021). Nature Communications. Emilly M. Lima, Antônio H. Ribeiro, Gabriela MM Paixão, Manoel Horta Ribeiro, Marcelo M. Pinto Filho, Paulo R. Gomes, Derick M. Oliveira, Ester C. Sabino, Bruce B. Duncan, Luana Giatti, Sandhi M. Barreto, Wagner Meira, Thomas B. Schön, Antonio Luiz P. Ribeiro
  • Automatic 12-lead ECG classification using a convolutional network ensemble (2020). 2020 Computing in Cardiology (CinC). Antonio H Ribeiro, Daniel Gedon, Daniel Martins Teixeira, Manoel Horta Ribeiro, Antonio L Pinho Ribeiro, Thomas B Schon, Wagner Meira Jr
Artificial intelligence for ECG classification and prediction of the risk of death (March 2021)
   Techinion, Israel @ AIMLab group (Online).

This browser does not support PDFs. Please download the PDF to view it: Download PDF.


Related publications:
  • Deep neural network estimated electrocardiographic-age as a mortality predictor (2021). Nature Communications. Emilly M. Lima, Antônio H. Ribeiro, Gabriela MM Paixão, Manoel Horta Ribeiro, Marcelo M. Pinto Filho, Paulo R. Gomes, Derick M. Oliveira, Ester C. Sabino, Bruce B. Duncan, Luana Giatti, Sandhi M. Barreto, Wagner Meira, Thomas B. Schön, Antonio Luiz P. Ribeiro
  • Automatic 12-lead ECG classification using a convolutional network ensemble (2020). 2020 Computing in Cardiology (CinC). Antonio H Ribeiro, Daniel Gedon, Daniel Martins Teixeira, Manoel Horta Ribeiro, Antonio L Pinho Ribeiro, Thomas B Schon, Wagner Meira Jr
Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness (2020)
   International Conference On Artificial Intelligence And Statistics (AISTATS).


Related publications:
  • Beyond exploding and vanishing gradients: attractors and smoothness in the analysis of recurrent neural network training (2020). Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR. Antônio H. Ribeiro, Koen Tiels, Luis A. Aguirre, Thomas B. Schön