Stanislaw Jastrzebski

Orcid: 0000-0003-4138-1818

Affiliations:
  • Jagiellonian University, Cracow, Poland


According to our database1, Stanislaw Jastrzebski authored at least 47 papers between 2013 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Relative molecule self-attention transformer.
J. Cheminformatics, December, 2024

An Efficient Deep Neural Network to Classify Large 3D Images With Small Objects.
IEEE Trans. Medical Imaging, January, 2024

Generative Active Learning for the Search of Small-molecule Protein Binders.
CoRR, 2024

2023
Generative Models Should at Least Be Able to Design Molecules That Dock Well: A New Benchmark.
J. Chem. Inf. Model., June, 2023

Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction.
CoRR, 2023

2022
RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis Software.
J. Chem. Inf. Model., 2022

3D-GMIC: an efficient deep neural network to find small objects in large 3D images.
CoRR, 2022

Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks.
Proceedings of the International Conference on Machine Learning, 2022

HuggingMolecules: An Open-Source Library for Transformer-Based Molecular Property Prediction (Student Abstract).
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department.
npj Digit. Medicine, 2021

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits.
J. Chem. Inf. Model., 2021

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening.
IEEE Trans. Medical Imaging, 2020

Cramer-Wold Auto-Encoder.
J. Mach. Learn. Res., 2020

Emulating Docking Results Using a Deep Neural Network: A New Perspective for Virtual Screening.
J. Chem. Inf. Model., 2020

Differences between human and machine perception in medical diagnosis.
CoRR, 2020

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design.
CoRR, 2020

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks.
CoRR, 2020

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department.
CoRR, 2020

We should at least be able to Design Molecules that Dock Well.
CoRR, 2020

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits.
CoRR, 2020

Understanding the robustness of deep neural network classifiers for breast cancer screening.
CoRR, 2020

Molecule Attention Transformer.
CoRR, 2020

Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening.
Proceedings of the International Conference on Medical Imaging with Deep Learning, 2020

Non-linear ICA Based on Cramer-Wold Metric.
Proceedings of the Neural Information Processing - 27th International Conference, 2020

The Break-Even Point on Optimization Trajectories of Deep Neural Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
Development of New Methods Needs Proper Evaluation - Benchmarking Sets for Machine Learning Experiments for Class A GPCRs.
J. Chem. Inf. Model., 2019

Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift.
CoRR, 2019

Large Scale Structure of Neural Network Loss Landscapes.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Parameter-Efficient Transfer Learning for NLP.
Proceedings of the 36th International Conference on Machine Learning, 2019

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length.
Proceedings of the 7th International Conference on Learning Representations, 2019

Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Neural Architecture Search Over a Graph Search Space.
CoRR, 2018

DNN's Sharpest Directions Along the SGD Trajectory.
CoRR, 2018

Cramer-Wold AutoEncoder.
CoRR, 2018

Commonsense mining as knowledge base completion? A study on the impact of novelty.
CoRR, 2018

Finding Flatter Minima with SGD.
Proceedings of the 6th International Conference on Learning Representations, 2018

Residual Connections Encourage Iterative Inference.
Proceedings of the 6th International Conference on Learning Representations, 2018

Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio.
Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2018, 2018

2017
Three Factors Influencing Minima in SGD.
CoRR, 2017

How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks.
CoRR, 2017

Learning to Compute Word Embeddings On the Fly.
CoRR, 2017

A Closer Look at Memorization in Deep Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Deep Nets Don't Learn via Memorization.
Proceedings of the 5th International Conference on Learning Representations, 2017

2016
Osprey: Hyperparameter Optimization for Machine Learning.
J. Open Source Softw., 2016

Learning to SMILE(S).
CoRR, 2016

2013
Density Invariant Detection of Osteoporosis Using Growing Neural Gas.
Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, 2013


  Loading...