Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Stanisław Jastrzębski

Stanisław Jastrzębski

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design


Nov 25, 2020
Cheng-Hao Liu, Maksym Korablyov, Stanisław Jastrzębski, Paweł Włodarczyk-Pruszyński, Yoshua Bengio, Marwin H. S. Segler

Figure 1 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 2 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 3 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 4 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
* Machine Learning for Molecules Workshop at NeurIPS 2020 
  Access Paper or Ask Questions

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks


Nov 19, 2020
Luke Darlow, Stanisław Jastrzębski, Amos Storkey

Figure 1 for Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
Figure 2 for Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
Figure 3 for Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
Figure 4 for Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
* 10 pages, 4 figures, submitted to AISTATS 2021 
  Access Paper or Ask Questions

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department


Aug 04, 2020
Farah E. Shamout, Yiqiu Shen, Nan Wu, Aakash Kaku, Jungkyu Park, Taro Makino, Stanisław Jastrzębski, Duo Wang, Ben Zhang, Siddhant Dogra, Meng Cao, Narges Razavian, David Kudlowitz, Lea Azour, William Moore, Yvonne W. Lui, Yindalon Aphinyanaphongs, Carlos Fernandez-Granda, Krzysztof J. Geras

Figure 1 for An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department
Figure 2 for An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department
Figure 3 for An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department
Figure 4 for An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department

  Access Paper or Ask Questions

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits


Jun 27, 2020
Mikołaj Sacha, Mikołaj Błaż, Piotr Byrski, Paweł Włodarczyk-Pruszyński, Stanisław Jastrzębski

Figure 1 for Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
Figure 2 for Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
Figure 3 for Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
Figure 4 for Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

  Access Paper or Ask Questions

Understanding the robustness of deep neural network classifiers for breast cancer screening


Mar 23, 2020
Witold Oleszkiewicz, Taro Makino, Stanisław Jastrzębski, Tomasz Trzciński, Linda Moy, Kyunghyun Cho, Laura Heacock, Krzysztof J. Geras

Figure 1 for Understanding the robustness of deep neural network classifiers for breast cancer screening
Figure 2 for Understanding the robustness of deep neural network classifiers for breast cancer screening
Figure 3 for Understanding the robustness of deep neural network classifiers for breast cancer screening
Figure 4 for Understanding the robustness of deep neural network classifiers for breast cancer screening
* Accepted as a workshop paper at AI4AH, ICLR 2020 
  Access Paper or Ask Questions

Molecule Attention Transformer


Feb 19, 2020
Łukasz Maziarka, Tomasz Danel, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor, Stanisław Jastrzębski

Figure 1 for Molecule Attention Transformer
Figure 2 for Molecule Attention Transformer
Figure 3 for Molecule Attention Transformer
Figure 4 for Molecule Attention Transformer

  Access Paper or Ask Questions

Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift


Apr 06, 2019
Michał Zając, Konrad Żołna, Stanisław Jastrzębski

Figure 1 for Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
Figure 2 for Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
Figure 3 for Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
Figure 4 for Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
* Under review for ECML PKDD 2019 
  Access Paper or Ask Questions

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening


Mar 20, 2019
Nan Wu, Jason Phang, Jungkyu Park, Yiqiu Shen, Zhe Huang, Masha Zorin, Stanisław Jastrzębski, Thibault Févry, Joe Katsnelson, Eric Kim, Stacey Wolfson, Ujas Parikh, Sushma Gaddam, Leng Leng Young Lin, Kara Ho, Joshua D. Weinstein, Beatriu Reig, Yiming Gao, Hildegard Toth, Kristine Pysarenko, Alana Lewin, Jiyon Lee, Krystal Airola, Eralda Mema, Stephanie Chung, Esther Hwang, Naziya Samreen, S. Gene Kim, Laura Heacock, Linda Moy, Kyunghyun Cho, Krzysztof J. Geras

Figure 1 for Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
Figure 2 for Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
Figure 3 for Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
Figure 4 for Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

  Access Paper or Ask Questions

Non-linear ICA based on Cramer-Wold metric


Mar 01, 2019
Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski

Figure 1 for Non-linear ICA based on Cramer-Wold metric
Figure 2 for Non-linear ICA based on Cramer-Wold metric
Figure 3 for Non-linear ICA based on Cramer-Wold metric
Figure 4 for Non-linear ICA based on Cramer-Wold metric

  Access Paper or Ask Questions

Neural Architecture Search Over a Graph Search Space


Dec 27, 2018
Quentin de Laroussilhe, Stanisław Jastrzębski, Neil Houlsby, Andrea Gesmundo

Figure 1 for Neural Architecture Search Over a Graph Search Space
Figure 2 for Neural Architecture Search Over a Graph Search Space
Figure 3 for Neural Architecture Search Over a Graph Search Space
Figure 4 for Neural Architecture Search Over a Graph Search Space

  Access Paper or Ask Questions

Cramer-Wold AutoEncoder


Oct 04, 2018
Jacek Tabor, Szymon Knop, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

Figure 1 for Cramer-Wold AutoEncoder
Figure 2 for Cramer-Wold AutoEncoder
Figure 3 for Cramer-Wold AutoEncoder
Figure 4 for Cramer-Wold AutoEncoder

  Access Paper or Ask Questions

Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function


Sep 24, 2018
Wojciech Tarnowski, Piotr Warchoł, Stanisław Jastrzębski, Jacek Tabor, Maciej A. Nowak

Figure 1 for Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
Figure 2 for Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
Figure 3 for Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
Figure 4 for Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function

  Access Paper or Ask Questions

Three Factors Influencing Minima in SGD


Sep 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

Figure 1 for Three Factors Influencing Minima in SGD
Figure 2 for Three Factors Influencing Minima in SGD
Figure 3 for Three Factors Influencing Minima in SGD
Figure 4 for Three Factors Influencing Minima in SGD
* First two authors contributed equally. Short version accepted into ICLR workshop. Accepted to Artificial Neural Networks and Machine Learning, ICANN 2018 
  Access Paper or Ask Questions

DNN's Sharpest Directions Along the SGD Trajectory


Jul 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

Figure 1 for DNN's Sharpest Directions Along the SGD Trajectory
Figure 2 for DNN's Sharpest Directions Along the SGD Trajectory
Figure 3 for DNN's Sharpest Directions Along the SGD Trajectory
Figure 4 for DNN's Sharpest Directions Along the SGD Trajectory
* Short version accepted into Modern Trends in Nonconvex Optimization for Machine Learning workshop at International Conference on Machine Learning 2018 
  Access Paper or Ask Questions

Commonsense mining as knowledge base completion? A study on the impact of novelty


Apr 24, 2018
Stanisław Jastrzębski, Dzmitry Bahdanau, Seyedarian Hosseini, Michael Noukhovitch, Yoshua Bengio, Jackie Chi Kit Cheung

Figure 1 for Commonsense mining as knowledge base completion? A study on the impact of novelty
Figure 2 for Commonsense mining as knowledge base completion? A study on the impact of novelty
Figure 3 for Commonsense mining as knowledge base completion? A study on the impact of novelty
Figure 4 for Commonsense mining as knowledge base completion? A study on the impact of novelty
* Published in Workshop on New Forms of Generalization in Deep Learning and Natural Language Processing (NAACL 2018) 
  Access Paper or Ask Questions

Learning to SMILE(S)


Mar 08, 2018
Stanisław Jastrzębski, Damian Leśniak, Wojciech Marian Czarnecki

Figure 1 for Learning to SMILE(S)
Figure 2 for Learning to SMILE(S)
* Accepted as a workshop contribution to ICLR 2016 
  Access Paper or Ask Questions

Residual Connections Encourage Iterative Inference


Mar 08, 2018
Stanisław Jastrzębski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio

Figure 1 for Residual Connections Encourage Iterative Inference
Figure 2 for Residual Connections Encourage Iterative Inference
Figure 3 for Residual Connections Encourage Iterative Inference
Figure 4 for Residual Connections Encourage Iterative Inference
* First two authors contributed equally. Published in ICLR 2018 
  Access Paper or Ask Questions

Learning to Compute Word Embeddings On the Fly


Mar 07, 2018
Dzmitry Bahdanau, Tom Bosc, Stanisław Jastrzębski, Edward Grefenstette, Pascal Vincent, Yoshua Bengio

Figure 1 for Learning to Compute Word Embeddings On the Fly
Figure 2 for Learning to Compute Word Embeddings On the Fly
Figure 3 for Learning to Compute Word Embeddings On the Fly
Figure 4 for Learning to Compute Word Embeddings On the Fly

  Access Paper or Ask Questions

A Closer Look at Memorization in Deep Networks


Jul 01, 2017
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, Simon Lacoste-Julien

Figure 1 for A Closer Look at Memorization in Deep Networks
Figure 2 for A Closer Look at Memorization in Deep Networks
Figure 3 for A Closer Look at Memorization in Deep Networks
Figure 4 for A Closer Look at Memorization in Deep Networks
* Appears in Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Devansh Arpit, Stanis{\l}aw Jastrz\k{e}bski, Nicolas Ballas, and David Krueger contributed equally to this work 
  Access Paper or Ask Questions