PhD student @ Jagiellonian University supervised by prof. Jacek Tabor and co-advised by prof. Amos Storkey. Currently intern with prof. Yoshua Bengio. My email is staszek.jastrzebski (on gmail).

Research interests:

  • Deep Representation Learning
  • Natural Language Processing
  • Computer Aided Drug Design

Supervised MSc/BSc students:

  • Andrii Krutsylo - Physics aware representation for drug discovery
  • [Defended] Jakub Chłędowski - Representation learning for textual entailment

Selected publications

Logo image

Learning to Compute Word Embeddings on The Fly

D. Bahdanau, T. Bosc*, S. Jastrzębski*, E. Grefenstette, P. Vincent, Y. Bengio

code .pdf poster

Logo image

A Closer Look at Memorization in Deep Networks

D. Arpit*, S. Jastrzębski*, N. Ballas*, D. Krueger*, T. Maharaj, E. Bengio, A. Fischer, A. Courville, S. Lacoste-Julien, Y. Bengio

ICML 2017
.pdf poster slides

Logo image

How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks

S. Jastrzębski, D. Lesniak, W. M. Czarnecki

.pdf

Logo image

Quo vadis G Protein-Coupled Receptor ligands? A tool for analysis of the emergence of new groups of compounds over time

D. Lesniak, S. Jastrzębski, W. M. Czarnecki, S. Podlewska, A. Bojarski

Bioorganic & Medicinal Chemistry Letters, 2017
.pdf

Logo image

Learning to SMILE(S)

S. Jastrzębski, D. Lesniak, W. M. Czarnecki

ICLR 2016 (workshop track)
.pdf poster

Logo image

Active Learning of Compounds Activity–Towards Scientifically Sound Simulation of Drug Candidates Identification

W. M. Czarnecki, S. Jastrzębski, I. Sieradzki, S. Podlewska

MLLS workshop, ECML 2015
code .pdf slides

Logo image

Analysis of compounds activity concept learned by SVM using robust Jaccard based low-dimensional embedding

S. Jastrzębski, W. M. Czarnecki

TFML 2015
code .pdf slides

Logo image

Density Invariant Detection of Osteoporosis Using Growing Neural Gas

I. T. Podolak, S. Jastrzębski

CORES 2013
code slides

Short CV

Logo image

MILA Lab

Research intern, Working on new methods for representation learning with application in NLP and cheminformatics. prof. Yoshua Bengio

2017, Montreal, Canda

Logo image

MILA Lab

Research intern, Deep Learning with application in protein folding, under the supervision of prof. Yoshua Bengio

2016, Montreal, Canda

Logo image

Palantir

Machine Learning intern, production fraud models and Deep Learning in NER tagging

2016, London, UK

Logo image

University of Edinburgh

Research intern, Deep Learning for Go, under the supervision of prof. Amos Storkey

2015, Edinburgh, UK

Logo image

Palantir

SDE intern, distributed data systems

2015, Palo Alto, USA

Logo image

Microsoft

SDE intern, API research and design

2014, Redmond, USA

Logo image

wide.io

SDE intern, data processing framework development

2013, London, UK

Code

Logo image

Word Embeddings Benchmarks

Python package for evaluating word embeddings.

github

Logo image

alpy

Python package for Active Learning with scikit-learn compatible API.

Work in progress

Logo image

GMUM.R

ML algorithms C++ implementations for R, including online clustering, swappable SVM library interface and new clustering algorithm.

github url

Logo image

KrakRobot Simulator

Simulator for 2015 and 2016 editions online qualification round.

github url