Viviane Clay
Viviane Clay
Doctor of Engineering
I research new methods for machine intelligence that are more similar to human intelligence.
About
16
Publications
35,659
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
416
Citations
Introduction
I'm Viviane Clay, a student of Cognitive Science at the University of Osnabrück. Lately I've focused on deep learning, reinforcement learning and applying theories about the human brain to machine learning. I am very interested in how humans explore, understand and interact with the world and how this knowledge can be applied in new soft- and hardware.I'm currently pursuing a PhD in Computational Cognition. Check out my work here: http://www.vivianeclay.com/
Publications
Publications (16)
The intent of this paper is to provide an introduction into the bourgeoning field of eye track-ing in Virtual Reality (VR). VR itself is an emerging technology on the consumer market,which will create many new opportunities in research. It offers a lab environment with highimmersion and close alignment with reality. An experiment which is using VR...
How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment? Here we investigate embodiment with a closed loop between action and perception as one key component in this process. We take a close look at the representations learned by a deep reinforcement learning agent t...
The fields of biologically inspired artificial intelligence, neuroscience, and psychology have had exciting influences on each other over the past decades. Especially recently, with the increased popularity and success of artificial neural networks (ANNs), ANNs have enjoyed frequent use as models for brain function. However, there are still many di...
Most artificial neural networks used for object recognition are trained in a fully supervised setup. This is not only resource consuming as it requires large data sets of labeled examples but also quite different from how humans learn. We use a setup in which an artificial agent first learns in a simulated world through self-supervised, curiosity-d...
Artificial intelligence has advanced rapidly in the last decade, driven primarily by progress in the scale of deep-learning systems. Despite these advances, the creation of intelligent systems that can operate effectively in diverse, real-world environments remains a significant challenge. In this white paper, we outline the Thousand Brains Project...
Spatial relations can be defined with respect to the body (egocentric) or among environmental objects only (allocentric). Egocentric relations are necessarily transformed by bodily action. To what extent allocentric cognitive representations are structured through our body remains unclear. In our study, participants navigate a virtual-reality (VR)...
Snow-layer segmentation and classification are essential diagnostic tasks for various cryospheric applications. The SnowMicroPen (SMP) measures the snowpack's penetration force at submillimeter intervals in snow depth. The resulting depth–force profile can be parameterized for density and specific surface area. However, no information on traditiona...
Snow-layer segmentation and classification is an essential diagnostic task for a wide variety of cryospheric applications. The SnowMicroPen (SMP) measures the snowpack's penetration force at submillimetre resolution against the snow depth. The resulting depth-force profile can be parameterized for density and specific surface area. However, no info...
Investigating spatial knowledge acquisition in virtual environments allows studying different sources of information under controlled conditions. Therefore, we built a virtual environment in the style of a European village and investigated spatial knowledge acquisition by experience in the immersive virtual environment and compared it to using an i...
Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self...
Classifying artists and their work as distinct art styles has been an important task of scholars in the field of art history. Due to its subjectivity, scholars often contradict one another. Our project investigated differences in aesthetic qualities of seven art styles through quantitative means. This was achieved with state-of-the-art deep-learnin...
Investigating spatial navigation in virtual environments enables to study spatial learning with different sources of information. Therefore, we designed a large virtual city and investigated spatial knowledge acquisition after direct experience in the virtual environment and compared this with results after exploration with an interactive map (Koni...
To become acquainted with large-scale environments such as cities people combine direct experience and indirect sources such as maps. To ascertain which type of spatial knowledge is acquired by which source is difficult to evaluate. Using virtual reality enables the possibility to investigate whether knowledge is learned by direct experience or the...
On the basis of embodied/-enacted theories of the mind, investigations of spatial cognition related to real world environments have become current research interests. How this perspective relates to acquiring spatial knowledge not by active exploration, but through map learning, however, remains unresolved. Therefore, we designed a large virtual ci...
In this thesis I will explore the possibility of progressively learning new information during neural network training by using a growing network which is increasing in size according to the complexity of the task assigned to it. Just as humans can keep learning during life this ability can be very helpful in many applications. So far however, neur...
Questions
Question (1)
Many papers are behind a paywall and I can't read them without using tools like SciHub (even my institution login doesn't give access to many papers). I would like to cite some of these papers and I know that they contain the correct information but officially I can only access their abstract. Would I get into any trouble if I cite such papers? Should I just cite the abstract (the main message is in there)?
