Visualizing the Hidden Activity of Artificial Neural Networks

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Visualizing the Hidden Activity of Artificial Neural Networks. / Rauber, Paulo E.; Fadel, Samuel G.; Falcão, Alexandre X. et al.
in: IEEE Transactions on Visualization and Computer Graphics, Jahrgang 23, Nr. 1, 7539329, 01.2017, S. 101-110.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Rauber PE, Fadel SG, Falcão AX, Telea AC. Visualizing the Hidden Activity of Artificial Neural Networks. IEEE Transactions on Visualization and Computer Graphics. 2017 Jan;23(1):101-110. 7539329. doi: 10.1109/TVCG.2016.2598838

Bibtex

@article{65c0ec990e9241a0b69a8ffd4695998f,
title = "Visualizing the Hidden Activity of Artificial Neural Networks",
abstract = "In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks are typically used as black-boxes, they are also widely believed to learn (high-dimensional) higher-level representations of the original observations. In this paper, we propose using dimensionality reduction for two tasks: visualizing the relationships between learned representations of observations, and visualizing the relationships between artificial neurons. Through experiments conducted in three traditional image classification benchmark datasets, we show how visualization can provide highly valuable feedback for network designers. For instance, our discoveries in one of these datasets (SVHN) include the presence of interpretable clusters of learned representations, and the partitioning of artificial neurons into groups with apparently related discriminative roles.",
keywords = "algorithm understanding, Artificial neural networks, dimensionality reduction, Informatics, Business informatics",
author = "Rauber, {Paulo E.} and Fadel, {Samuel G.} and Falc{\~a}o, {Alexandre X.} and Telea, {Alexandru C.}",
year = "2017",
month = jan,
doi = "10.1109/TVCG.2016.2598838",
language = "English",
volume = "23",
pages = "101--110",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

RIS

TY - JOUR

T1 - Visualizing the Hidden Activity of Artificial Neural Networks

AU - Rauber, Paulo E.

AU - Fadel, Samuel G.

AU - Falcão, Alexandre X.

AU - Telea, Alexandru C.

PY - 2017/1

Y1 - 2017/1

N2 - In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks are typically used as black-boxes, they are also widely believed to learn (high-dimensional) higher-level representations of the original observations. In this paper, we propose using dimensionality reduction for two tasks: visualizing the relationships between learned representations of observations, and visualizing the relationships between artificial neurons. Through experiments conducted in three traditional image classification benchmark datasets, we show how visualization can provide highly valuable feedback for network designers. For instance, our discoveries in one of these datasets (SVHN) include the presence of interpretable clusters of learned representations, and the partitioning of artificial neurons into groups with apparently related discriminative roles.

AB - In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks are typically used as black-boxes, they are also widely believed to learn (high-dimensional) higher-level representations of the original observations. In this paper, we propose using dimensionality reduction for two tasks: visualizing the relationships between learned representations of observations, and visualizing the relationships between artificial neurons. Through experiments conducted in three traditional image classification benchmark datasets, we show how visualization can provide highly valuable feedback for network designers. For instance, our discoveries in one of these datasets (SVHN) include the presence of interpretable clusters of learned representations, and the partitioning of artificial neurons into groups with apparently related discriminative roles.

KW - algorithm understanding

KW - Artificial neural networks

KW - dimensionality reduction

KW - Informatics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=84998953869&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2016.2598838

DO - 10.1109/TVCG.2016.2598838

M3 - Journal articles

C2 - 27875137

AN - SCOPUS:84998953869

VL - 23

SP - 101

EP - 110

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 1

M1 - 7539329

ER -

DOI

Zuletzt angesehen

Publikationen

  1. CSR
  2. Rapid allocation of temporal attention in the Attentional Blink Paradigm
  3. Crowdsourcing
  4. Factored MDPs for detecting topics of user sessions
  5. Creating a space for cooperation
  6. Programmed Visions
  7. Plasma Frequency Regulation using Sliding Mode Control for Gaussian Normalized Periodic Model in the Presence of Disturbances
  8. Inherent and induced anisotropic finite visco-plasticity with applications to the forming of DC06 sheets
  9. A piezo servo hydraulic actuator for use in camless combustion engines and its control with MPC
  10. An analysis of the requirements for DSS on integrated river basin management
  11. Increasing personal initiative in small business managers or owners leads to entrepreneurial success: A theory-based controlled randomized field intervention for evidence-based management
  12. Contaminated sediment in Ramsar wetlands; A challenge towards sustainable management of sensitive ecosystems
  13. Decision-making models for Robotic Warehouse
  14. Navigating conflicting landscape aspirations
  15. Genie in the bottle – Der Flaschengeist
  16. Fest oder flüssig? Nichtnewtonsche Stoffsysteme
  17. INFLeXions Nr. 4 - Transversal Fields of Experience
  18. Science, policy and implementation gaps: An exploration of groundwater management in Hungary
  19. Dynamic Capabilities in Sustainable Supply Chain Management
  20. Scenarios for Encapsulated and Suspended Bodies
  21. Transformative learning in the field of sustainability: a systematic literature review (1999-2019)
  22. Video
  23. "…some purpose other than decorative."
  24. The abuse of executive powers
  25. Schwellenphänomene
  26. "Have We Seen It All Before?"
  27. Das Alltagsmedium Blatt im kulturellen Wandel
  28. The defence of necessity
  29. The European Union
  30. Eight hypotheses why librarians don't like discovery