Bartosz Wójcik

Bartosz Wójcik

Auto-generated profile, based on publicly available information

Bartosz Wójcik

IDEAS NCBR

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2023 in Neural Networks
Verified
Journal Article
Open access
BWBartosz Wójcik
Bartosz Wójcik
MPMarcin Przewiȩźlikowski
Marcin Przewiȩźlikowski
FSFilip Szatkowski
Filip Szatkowski
MWMaciej Wołczyk
Maciej Wołczyk
KBKlaudia Bałazy
Klaudia Bałazy
Tomasz TrzcinskiTomasz Trzcinski
Tomasz Trzcinski
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers of a neural network. ICs can quickly return predictions for easy examples and, as a result, reduce the average inference time of the whole model. However, if a particular IC does not decide to return an answer early, its predictions are discarded, with its computations effectively being wasted. To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. We conduct extensive experiments across various multiple modes, datasets, and architectures to demonstrate that ZTW achieves a significantly better accuracy vs. inference time trade-off than other early exit methods. On the ImageNet dataset, it obtains superior results over the best baseline method in 11 out of 16 cases, reaching up to 5 percentage points of improvement on low computational budgets.

29 June 2022 in Applied Soft Computing
Verified
Journal Article
Closed access
BWBartosz Wójcik
Bartosz Wójcik
JGJacek Grela
Jacek Grela
MŚMarek Śmieja
Marek Śmieja
KMKrzysztof Misztal
Krzysztof Misztal
JTJacek Tabor
Jacek Tabor

16 October 2024
Verified
Book Chapter
Open access
PDF file
Tomasz TrzcinskiTomasz Trzcinski
Tomasz Trzcinski
BTBartłomiej Twardowski
Bartłomiej Twardowski
BZBartosz Zieliński
Bartosz Zieliński
KAKamil Adamczewski
Kamil Adamczewski
BWBartosz Wójcik
Bartosz Wójcik
Today, both science and industry rely heavily on machine learning models, predominantly artificial neural networks, that become increasingly complex and demand more computing resources to be trained. In this paper, we will look holistically at the efficiency of machine learning models and draw the inspirations to address their main challenges from the green sustainable economy principles. Instead of constraining some computations or memory used by the models, we will focus on reusing what is available to them: computations done in the previous processing steps, partial information accessible at run-time, or knowledge gained by the model during previous training sessions in continually learned models. This new research path of zero-waste machine learning can lead to several research questions related to efficiency of contemporary neural networks - how machine learning models can learn better with less data? How they select relevant data samples out of many? Finally, how can they build on top of already trained models to reduce the need for more training samples? Here, we explore all the above questions and attempt to answer them.