dr Stanisław Jastrzębski

Jednostki:

  • Wydział Matematyki i Informatyki UJ
  • Instytut Informatyki i Matematyki Komputerowej
  • Katedra Uczenia Maszynowego

Doktorat  Otwarcie: 2017-06-29, Zamknięcie: 2019-03-28

Publikacje:

24.
Tobiasz Ciepliński, Tomasz Danel, Sabina Podlewska, Stanisław Jastrzębski
Generative Models Should at Least Be Able to Design Molecules That Dock Well: A New Benchmark, Journal of Chemical Information and Modeling vol. 63 (2023), 3238-3247
23.
Piotr Gaiński, Łukasz Maziarka, Tomasz Danel, Stanisław Jastrzębski
HuggingMolecules: An Open-Source Library for Transformer-Based Molecular Property Prediction (Student Abstract), National Conference of the American Association for Artificial Intelligence [AAAI], (2022), 12949-12950
22.
Tomasz Danel, Piotr Gaiński, Stanisław Jastrzębski, Łukasz Maziarka
HuggingMolecules: an open-source library for transformer-based molecular property prediction, International Conference On Learning Representations (workshop Track) (2021),
21.
Andrzej Bojarski, Stanisław Jastrzębski, Stefan Mordalski, Sabina Podlewska, Maciej Szymczak, Jacek Tabor, Agnieszka Wojtuch
Emulating docking results using a deep neural network: a new perspective for virtual screening, Journal of Chemical Information and Modeling (2020), 4246-4262
20.
Stanisław Jastrzębski, Łukasz Maziarka, Aleksandra Nowak, Przemysław Spurek, Jacek Tabor
Non-linear ICA based on Cramer-Wold metric, International Conference On Neural Information Processing vol. Lecture Notes in Computer Science book series (LNCS, volume 12534) (2020),
19.
Devansh Arpit, Kyunghyun Cho, Stanislav Fort, Krzysztof J. Geras, Stanisław Jastrzębski, Maciej Szymczak, Jacek Tabor
The Break-Even Point on Optimization Trajectories of Deep Neural Networks, 8th International Conference On Learning Representations (2020),
18.
Andrzej Bojarski, Stanisław Jastrzębski, Stefan Mordalski, Sabina Podlewska, Maciej Szymczak, Jacek Tabor, Agnieszka Wojtuch
Emulating Docking Results Using a Deep Neural Network: A New Perspective for Virtual Screening, Journal of Chemical Information and Modeling vol. 60 (2020), 4246-4262
17.
Stanisław Jastrzębski, Szymon Knop, Marcin Mazur, Igor Podolak, Przemysław Spurek, Jacek Tabor
Cramer-Wold Auto-Encoder, Journal of Machine Learning Research vol. 21 (2020), 1-28
16.
Stanisław Jastrzębski, Maciej A. Nowak, Jacek Tabor, Wojciech Tarnowski, Piotr Warchoł
Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function, International Conference on Artificial Intelligence and Statistics [AISTATS], (2019), 10
15.
Andrzej Bojarski, Stanisław Jastrzębski, Damian Leśniak, Sabina Podlewska, Igor Sieradzki, Jacek Tabor
Development of New Methods Needs Proper Evaluation -- Benchmarking Sets for Machine Learning Experiments for Class A GPCRs, Journal of Chemical Information and Modeling vol. 59 (2019), 4974-4992
14.
Tomasz Danel, Stanisław Jastrzębski, Łukasz Maziarka, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor
Molecule-Augmented Attention Transformer, Neural Information Processing Systems (workshop Track) (2019),
13.
Jakub Chłędowski, Stanisław Jastrzębski, Tomasz Wesołowski
Improving utilization of lexical knowledge in natural language inference, Schedae Informaticae vol. Vol 27 (2018),
12.
Andrzej Bojarski, Stanisław Jastrzębski, Damian Leśniak, Sabina Podlewska, Igor Sieradzki, Jacek Tabor
Three-dimensional descriptors for aminergic GPCRs: dependence on docking conformation and crystal structure, Molecular Diversity vol. vol.23 no.3 (2018), 603-613
11.
Devansh Arpit, Nicolas Ballas, Yoshua Bengio, Stanisław Jastrzębski
Residual connections encourage iterative inference, International Conference On Learning Algorithms 2018 (2017),
10.
Yoshua Bengio, Bahdanau Dzmitry, Grefenstette Edward, Stanisław Jastrzębski, Vincent Pascal, Bosc Tom
Learning to Compute Word Embeddings On the Fly, Montreal Ai Symposium 2017 (2017),
9.
Devansh Arpit, Nicolas Ballas, Yoshua Bengio, Bengio Emmanuel, Asja Fischer, Stanisław Jastrzębski, Maxinder S. Kanwal, David Krueger, Simon Lacoste-Julien, Tegan Maharaj
A Closer Look at Memorization in Deep Networks, (2017),
8.
Wojciech Czarnecki, Stanisław Jastrzębski, Damian Leśniak
How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks, Arxiv (2017),
7.
Devansh Arpit, Nicolas Ballas, Aaron Courville, Bengio Emmanuel, Asja Fischer, Stanisław Jastrzębski, Maxinder S. Kanwal, David Krueger, Tegan Maharaj
Deep Nets Don't Learn via Memorization, International Conference On Learning Representations (workshop Track) (2017),
6.
Andrzej Bojarski, Wojciech Czarnecki, Stanisław Jastrzębski, Damian Leśniak, Sabina Podlewska
Quo vadis G Protein-Coupled Receptor ligands? A tool for analysis of the emergence of new groups of compounds over time, Bioorganic and Medicinal Chemistry Letters vol. 27 (2017), 626-631
5.
Stanisław Jastrzębski, Igor Sieradzki
On Certain Limitations of Recursive Representation Model, Schedae Informaticae vol. 25 (2016), 37-47
4.
Wojciech Czarnecki, Stanisław Jastrzębski, Damian Leśniak
Learning to SMILE(S), International Conference On Learning Representations (workshop Track) (2016),
3.
Wojciech Czarnecki, Stanisław Jastrzębski, Sabina Podlewska, Igor Sieradzki
Active Learning of Compounds Activity - Towards Scientifically Sound Simulation of Drug Candidates Identification, Proceedings of 2nd Workshop On Machine Learning in Life Sciences (2015), 40-51
2.
Wojciech Czarnecki, Stanisław Jastrzębski
Analysis of compounds activity concept learned by SVM using robust Jaccard based low-dimensional embedding, Schedae Informaticae vol. 24 (2015), 9-19
1.
Stanisław Jastrzębski, Igor Podolak
Density Invariant Detection of Osteoporosis Using Growing Neural Gas, Proceedings of the 8th International Conference On Computer Recognition Systems Cores 2013 vol. Springer International Publishing (2013), 629-638

Granty (realizowane po maju 2009 roku)

TytułRolaRozpoczęcieZakończenie
Nowe metody uczenia reprezentacji w Deep LearninguKierownik2017-10-022019-10-01
Rzadka reprezentacja słów wzbogacona o różnorodne źródłaKierownik2015-09-212018-09-20

Nagrody

RokRodzajRodzaj uhonorowanej działalnościTyp 
2021nagrodadziałalność naukowa lub naukowo-badawczakrajowaSzczegóły