Cognitive maps play a crucial role in facilitating flexible behaviour by...
Learning to navigate unknown environments from scratch is a challenging
...
Living organisms need to acquire both cognitive maps for learning the
st...
Understanding the world in terms of objects and the possible interplays ...
Cognitive maps play a crucial role in facilitating flexible behaviour by...
Humans perceive and interact with hundreds of objects every day. In doin...
Representing a scene and its constituent objects from raw sensory data i...
Frequency-modulated continuous-wave (FMCW) radar is a promising sensor
t...
Unsupervised skill learning aims to learn a rich repertoire of behaviors...
Controlling artificial agents from visual sensory data is an arduous tas...
Active inference is a first principles approach for understanding the br...
When studying unconstrained behaviour and allowing mice to leave their c...
Active inference provides a general framework for behavior and learning ...
Over 60,000 songs are released on Spotify every day, and the competition...
The free energy principle, and its corollary active inference, constitut...
Active inference is a unifying theory for perception and action resting ...
Although modern object detection and classification models achieve high
...
Aerial navigation in GPS-denied, indoor environments, is still an open
c...
Biologically inspired algorithms for simultaneous localization and mappi...
Historically, artificial intelligence has drawn much inspiration from
ne...
Training with Reinforcement Learning requires a reward function that is ...
When designing variational autoencoders (VAEs) or other types of latent ...
Active inference is a theory that underpins the way biological agent's
p...
Music that is generated by recurrent neural networks often lacks a sense...
Active inference is a process theory of the brain that states that all l...
Catching objects in-flight is an outstanding challenge in robotics. In t...
Learning to take actions based on observations is a core requirement for...
In this work we explore the generalization characteristics of unsupervis...
Because of their state-of-the-art performance in computer vision, CNNs a...
Learning-based approaches for robotic grasping using visual sensors typi...
Deep neural networks require large amounts of resources which makes them...
Deep residual networks (ResNets) made a recent breakthrough in deep lear...
Recurrent neural networks are nowadays successfully used in an abundance...
Previous work has shown that it is possible to train deep neural network...
The amount of content on online music streaming platforms is immense, an...
Reinforcement learning is a proven technique for an agent to learn a tas...
Deep reinforcement learning is becoming increasingly popular for robot
c...
Short text messages such as tweets are very noisy and sparse in their us...
In this paper we propose a technique which avoids the evaluation of cert...
We present four training and prediction schedules from the same
characte...
Levering data on social media, such as Twitter and Facebook, requires
in...