KANDINSKYPatterns--An experimental exploration environment for Pattern Analysis and Machine Intelligence
Machine intelligence is very successful at standard recognition tasks when having high-
quality training data. There is still a significant gap between machine-level pattern …
quality training data. There is still a significant gap between machine-level pattern …
[PDF][PDF] Toward human-level concept learning: Pattern benchmarking for AI algorithms
Artificial intelligence (AI) today is very successful at standard pattern-recognition tasks due to
the availability of large amounts of data and advances in statistical data-driven machine …
the availability of large amounts of data and advances in statistical data-driven machine …
[HTML][HTML] Kandinsky patterns
H Müller, A Holzinger - Artificial intelligence, 2021 - Elsevier
Abstract Kandinsky Figures and Kandinsky Patterns are mathematically describable, simple,
self-contained hence controllable synthetic test data sets for the development, validation and …
self-contained hence controllable synthetic test data sets for the development, validation and …
Kandinsky patterns as iq-test for machine learning
AI follows the notion of human intelligence which is unfortunately not a clearly defined term.
The most common definition given by cognitive science as mental capability, includes …
The most common definition given by cognitive science as mental capability, includes …
How intelligent are convolutional neural networks?
Motivated by the Gestalt pattern theory, and the Winograd Challenge for language
understanding, we design synthetic experiments to investigate a deep learning algorithm's …
understanding, we design synthetic experiments to investigate a deep learning algorithm's …
Back to the feature: A neural-symbolic perspective on explainable AI
A Campagner, F Cabitza - … Learning and Knowledge Extraction: 4th IFIP …, 2020 - Springer
We discuss a perspective aimed at making black box models more eXplainable, within the
eXplainable AI (XAI) strand of research. We argue that the traditional end-to-end learning …
eXplainable AI (XAI) strand of research. We argue that the traditional end-to-end learning …
NxPlain: Web-based Tool for Discovery of Latent Concepts
The proliferation of deep neural networks in various domains has seen an increased need
for the interpretability of these models, especially in scenarios where fairness and trust are …
for the interpretability of these models, especially in scenarios where fairness and trust are …
[PDF][PDF] Deconstructing the Final Frontier of Artificial Intelligence: Five Theses for a Constructivist Machine Learning.
T Schmid - aaai Spring Symposium: Combining Machine Learning …, 2019 - ceur-ws.org
Ambiguity and diversity in human cognition can be regarded a final frontier in developing
equivalent systems of artificial intelligence. Despite astonishing accomplishments, modern …
equivalent systems of artificial intelligence. Despite astonishing accomplishments, modern …
Changes from the trenches: Should we automate them?
Code changes constitute one of the most important features of software evolution. Studying
them can provide insights into the nature of software development and also lead to practical …
them can provide insights into the nature of software development and also lead to practical …
More interpretable decision trees
E Gilmore, V Estivill-Castro, R Hexel - Hybrid Artificial Intelligent Systems …, 2021 - Springer
We present a new Decision Tree Classifier (DTC) induction algorithm that produces vastly
more interpretable trees in many situations. These understandable trees are highly relevant …
more interpretable trees in many situations. These understandable trees are highly relevant …