Related papers: Implementing Inductive bias for different navigati…
Understanding how animals learn is a central challenge in neuroscience, with growing relevance to the development of animal- or human-aligned artificial intelligence. However, existing approaches tend to assume fixed parametric forms for…
In this paper, we describe a general framework: Parameters Read-Write Networks (PRaWNs) to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into…
This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…
Conventional deep learning prioritizes unconstrained optimization, yet biological systems operate under strict metabolic constraints. We propose that these physical constraints shape dynamics to function not as limitations, but as a…
Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…
Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit…
We present a semantically rich graph representation for indoor robotic navigation. Our graph representation encodes: semantic locations such as offices or corridors as nodes, and navigational behaviors such as enter office or cross a…
Cerebellar-like networks, in which input activity patterns are separated by projection to a much higher-dimensional space before classification, are a recurring neurobiological motif, present in the cerebellum, dentate gyrus, insect…
Neural dynamical systems with stable attractor structures, such as point attractors and continuous attractors, are hypothesized to underlie meaningful temporal behavior that requires working memory. However, working memory may not support…
Navigation is a complex skill with a long history of research in animals and humans. In this work, we simulate the Morris Water Maze in 2D to train deep reinforcement learning agents. We perform automatic classification of navigation…
The fitness landscape metaphor plays a central role on the modeling of optimizing principles in many research fields, ranging from evolutionary biology, where it was first introduced, to management research. Here we consider the ensemble of…
The efficiency of recurrent neural networks (RNNs) in dealing with sequential data has long been established. However, unlike deep, and convolution networks where we can attribute the recognition of a certain feature to every layer, it is…
Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task related neural dynamics we study trained Recurrent Neural Networks. We develop a Mean Field Theory for Reservoir Computing…
Computational models trained on a large amount of natural images are the state-of-the-art to study human vision - usually adult vision. Computational models of infant vision and its further development are gaining more and more attention in…
Deep artificial neural networks famously struggle to learn from non-stationary streams of data. Without dedicated mitigation strategies, continual learning is associated with continuous forgetting of previous tasks and a progressive loss of…
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…
This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve…
Predicting the motion of a mobile agent from a third-person perspective is an important component for many robotics applications, such as autonomous navigation and tracking. With accurate motion prediction of other agents, robots can plan…
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…