Infant-inspired intrinsically motivated curious robots
G Gordon - Current Opinion in Behavioral Sciences, 2020 - Elsevier
Highlights•Curious robots select actions to maximize intrinsic rewards that quantify learning
progress.•Curious robots exhibit emergence of infant-like exploration behaviors.•Open …
progress.•Curious robots exhibit emergence of infant-like exploration behaviors.•Open …
Social behaviour as an emergent property of embodied curiosity: a robotics perspective
G Gordon - … Transactions of the Royal Society B, 2019 - royalsocietypublishing.org
Social interaction is an extremely complex yet vital component in daily life. We present a
bottom-up approach for the emergence of social behaviours from the interaction of the …
bottom-up approach for the emergence of social behaviours from the interaction of the …
Curious instance selection
M Moran, T Cohen, Y Ben-Zion, G Gordon - Information Sciences, 2022 - Elsevier
In the process of building machine learning models data sometimes must be sampled before
the learning process can be applied. This step, known as instance selection, is mostly done …
the learning process can be applied. This step, known as instance selection, is mostly done …
Radiotracking invasive spread: Are common mynas more active and exploratory on the invasion front?
Understanding the drivers of invasive species' range expansion is key to effective
management and successful control. Spatial sorting theory advances that invasive species …
management and successful control. Spatial sorting theory advances that invasive species …
Emergent exploration via novelty management
When encountering novel environments, animals perform complex yet structured exploratory
behaviors. Despite their typical structuring, the principles underlying exploratory patterns are …
behaviors. Despite their typical structuring, the principles underlying exploratory patterns are …
Curious feature selection
M Moran, G Gordon - Information Sciences, 2019 - Elsevier
In state-of-the-art big-data applications, the process of building machine learning models
can be very challenging due to continuous changes in data structures and the need for …
can be very challenging due to continuous changes in data structures and the need for …
Active learning of affordances for robot use of household objects
Learning to perform household tasks is a key step towards developing cognitive service
robots. This requires that robots are capable of discovering how to use human-designed …
robots. This requires that robots are capable of discovering how to use human-designed …
Deep Curious Feature Selection: A Recurrent, Intrinsic-Reward Reinforcement Learning Approach to Feature Selection
M Moran, G Gordon - IEEE Transactions on Artificial …, 2023 - ieeexplore.ieee.org
Feature selection (FS) is an important step in the process of building machine learning-
based models. The goal of the FS step is to find a small subset of features that will provide …
based models. The goal of the FS step is to find a small subset of features that will provide …
Curious Feature Selection-Based Clustering
M Moran, G Gordon - IEEE Transactions on Artificial …, 2024 - ieeexplore.ieee.org
In tabular data, certain challenges can negatively affect the quality of machine learning
models, such as high dimensionality, noisy, irrelevant, or repetitive features, interactions …
models, such as high dimensionality, noisy, irrelevant, or repetitive features, interactions …
Coping with Space Neophobia in Drosophila melanogaster: The Asymmetric Dynamics of Crossing a Doorway to the Untrodden
S Cohen, Y Benjamini, I Golani - PloS one, 2015 - journals.plos.org
We discover and examine within a wide phylogenetic perspective spatial neophobia,
avoidance of untrodden terrain, in fruit flies, in an experimental setup that reduces the gap …
avoidance of untrodden terrain, in fruit flies, in an experimental setup that reduces the gap …