Search Results for author: Stanisław Jastrzębski

Found 24 papers, 9 papers with code

Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction

no code implementations11 Oct 2023 Mikołaj Sacha, Michał Sadowski, Piotr Kozakowski, Ruard van Workum, Stanisław Jastrzębski

Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors.

Retrosynthesis

An efficient deep neural network to find small objects in large 3D images

1 code implementation16 Oct 2022 Jungkyu Park, Jakub Chłędowski, Stanisław Jastrzębski, Jan Witowski, Yanqi Xu, Linda Du, Sushma Gaddam, Eric Kim, Alana Lewin, Ujas Parikh, Anastasia Plaunova, Sardius Chen, Alexandra Millet, James Park, Kristine Pysarenko, Shalin Patel, Julia Goldberg, Melanie Wegener, Linda Moy, Laura Heacock, Beatriu Reig, Krzysztof J. Geras

On a dataset collected at NYU Langone Health, including 85, 526 patients with full-field 2D mammography (FFDM), synthetic 2D mammography, and 3D mammography, 3D-GMIC achieves an AUC of 0. 831 (95% CI: 0. 769-0. 887) in classifying breasts with malignant findings using 3D mammography.

Anatomy

Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks

1 code implementation10 Feb 2022 Nan Wu, Stanisław Jastrzębski, Kyunghyun Cho, Krzysztof J. Geras

We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning.

Relative Molecule Self-Attention Transformer

no code implementations12 Oct 2021 Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gaiński, Jacek Tabor, Igor Podolak, Paweł Morkisz, Stanisław Jastrzębski

Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data.

Drug Discovery Property Prediction +1

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

no code implementations25 Nov 2020 Cheng-Hao Liu, Maksym Korablyov, Stanisław Jastrzębski, Paweł Włodarczyk-Pruszyński, Yoshua Bengio, Marwin H. S. Segler

A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility.

Retrosynthesis

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks

no code implementations19 Nov 2020 Luke Darlow, Stanisław Jastrzębski, Amos Storkey

By training neural networks on these adversarial examples, we can improve their generalisation in collider bias settings.

Selection bias

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

1 code implementation4 Aug 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

In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time.

COVID-19 Diagnosis Decision Making +1

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

no code implementations23 Mar 2020 Witold Oleszkiewicz, Taro Makino, Stanisław Jastrzębski, Tomasz Trzciński, Linda Moy, Kyunghyun Cho, Laura Heacock, Krzysztof J. Geras

Deep neural networks (DNNs) show promise in breast cancer screening, but their robustness to input perturbations must be better understood before they can be clinically implemented.

Molecule Attention Transformer

6 code implementations19 Feb 2020 Łukasz Maziarka, Tomasz Danel, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor, Stanisław Jastrzębski

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry.

Drug Discovery Property Prediction

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

no code implementations ICLR Workshop LLD 2019 Michał Zając, Konrad Żołna, Stanisław Jastrzębski

Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples.

Image Classification

Non-linear ICA based on Cramer-Wold metric

no code implementations1 Mar 2019 Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski

Non-linear source separation is a challenging open problem with many applications.

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

no code implementations24 Sep 2018 Wojciech Tarnowski, Piotr Warchoł, Stanisław Jastrzębski, Jacek Tabor, Maciej A. Nowak

We propose that in ResNets this can be resolved based on our results, by ensuring the same level of dynamical isometry at initialization.

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length

1 code implementation ICLR 2019 Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

When studying the SGD dynamics in relation to the sharpest directions in this initial phase, we find that the SGD step is large compared to the curvature and commonly fails to minimize the loss along the sharpest directions.

Relation

Cramer-Wold AutoEncoder

2 code implementations ICLR 2019 Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE.

Three Factors Influencing Minima in SGD

no code implementations ICLR 2018 Stanisław Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

In particular we find that the ratio of learning rate to batch size is a key determinant of SGD dynamics and of the width of the final minima, and that higher values of the ratio lead to wider minima and often better generalization.

Memorization Open-Ended Question Answering

Residual Connections Encourage Iterative Inference

no code implementations ICLR 2018 Stanisław Jastrzębski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio

In general, a Resnet block tends to concentrate representation learning behavior in the first few layers while higher layers perform iterative refinement of features.

Representation Learning

Learning to SMILE(S)

no code implementations19 Feb 2016 Stanisław Jastrzębski, Damian Leśniak, Wojciech Marian Czarnecki

This paper shows how one can directly apply natural language processing (NLP) methods to classification problems in cheminformatics.

Activity Prediction General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.