Related papers: On the Positioning of Objects in Space
Recommender systems leverage both content and user interactions to generate recommendations that fit users' preferences. The recent surge of interest in deep learning presents new opportunities for exploiting these two sources of…
In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…
Here we will discuss the philosophical differences between an approach to the deep nature of physical space based on the concept of coordinates and one based on the concept of relation. The philosophical superiority of the second approach…
It is shown that, in the model of a flat 3D space, the time (i.e., the Hubble or the gravitation constant) plays a role of a spatial property. Gravitation field of spherical central mass does not lead to a lowering of symmetry of the space…
Human environments contain numerous objects configured in a variety of arrangements. Our goal is to enable robots to repose previously unseen objects according to learned semantic relationships in novel environments. We break this problem…
Context plays an important role in visual recognition. Recent studies have shown that visual recognition networks can be fooled by placing objects in inconsistent contexts (e.g., a cow in the ocean). To model the role of contextual…
Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the…
Many approaches have dealt with the hypothesis that the environment contain information, mostly focusing on how humans decode information from the environment in visual perception, navigation, and spatial decision-making. A question yet to…
The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…
Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical work suggests that the concept of space…
A general sketch on how the problem of space dimensionality depends on anthropic arguments is presented. Several examples of how life has been used to constraint space dimensionality (and vice-versa) are reviewed. In particular, the…
We present a new scheme of defining invariant observables for general relativistic systems. The scheme is based on the introduction of an observer which endowes the construction with a straightforward physical interpretation. The…
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a…
The motion of astronomical bodies and the centre of mass of the system is not always well perceived by students. One of the struggles is the conceptual change of reference frame, which is the same that held back the acceptance of the…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
Objects are a centerpiece of the mathematical realm and our interaction with and reasoning about it, just as they are of the physical one (if not more). And humans' mathematical reasoning must ultimately be grounded in our general…
When we experience an event, it feels like our previous experiences, our interpretations of that event (e.g., aesthetics, emotions), and our current state will determine how we will remember it. However, recent work has revealed a strong…
Spatial relationships between objects represent key scene information for humans to understand and interact with the world. To study the capability of current computer vision systems to recognize physically grounded spatial relations, we…
We investigate how deformations of special relativity in momentum space can be extended to position space in a consistent way, such that the dimensionless contraction between wave-vector and coordinate-vector remains invariant. By using a…
We model endogenous perception of private information in single-agent screening problems, with potential evaluation errors. The agent's evaluation of their type depends on their cognitive state: either attentive (i.e., they correctly…