Stanisław Jastrzebski
7 papers · 2017–2022 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird
🚀
Conference Pioneer
Top co-authors
Research topics
Machine Learning
(6)
Deep Learning
(5)
Architectures
(4)
Optimization & Theory
(4)
Artificial Intelligence
(2)
Core AI
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Healthcare & Medicine
(1)
Interdisciplinary
(1)
Clinical
(1)
Core Methods
(1)
Domain-Specific
(1)
Models
(1)
Keywords
residual network
(2)
representation learning
(1)
image classification
(1)
stochastic gradient descent
(1)
adversarial robustness
(1)
transfer learning
(1)
medical imaging
(1)
iterative refinement
(1)
multi-view learning
(1)
signal propagation
(1)
random matrix theory
(1)
generative model
(1)
learning rate
(1)
deep neural network
(1)
hessian eigenvalue
(1)
drug discovery
(1)
self-supervised pretraining
(1)
spectral density
(1)
medical diagnosis
(1)
molecular property prediction
(1)
Papers
HuggingMolecules: An Open-Source Library for Transformer-Based Molecular Property Prediction (Student Abstract)
AAAI 2022
Cramer-Wold Auto-Encoder
JMLR 2020
Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening
MIDL 2020
Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
AISTATS 2019
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
ICLR 2019
Residual Connections Encourage Iterative Inference
ICLR 2018
A Closer Look at Memorization in Deep Networks
ICML 2017