no code implementations • 18 Sep 2023 • Daria de Tinguy, Toon Van de Maele, Tim Verbelen, Bart Dhoedt
Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment.
no code implementations • 22 Aug 2023 • Toon Van de Maele, Bart Dhoedt, Tim Verbelen, Giovanni Pezzulo
Through a series of simulations, we demonstrate that the model's dual layers acquire effective cognitive maps for navigation within physical (HC map) and task (mPFC map) spaces, using a biologically-inspired approach: a clone-structured cognitive graph.
no code implementations • 16 Aug 2023 • Toon Van de Maele, Bart Dhoedt, Tim Verbelen, Giovanni Pezzulo
Living organisms need to acquire both cognitive maps for learning the structure of the world and planning mechanisms able to deal with the challenges of navigating ambiguous environments.
no code implementations • 5 Jul 2023 • Stefano Ferraro, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt
Understanding the world in terms of objects and the possible interplays with them is an important cognition ability, especially in robotics manipulation, where many tasks require robot-object interactions.
no code implementations • 23 Jun 2023 • Daria de Tinguy, Toon Van de Maele, Tim Verbelen, Bart Dhoedt
Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment.
no code implementations • 7 Feb 2023 • Toon Van de Maele, Tim Verbelen, Pietro Mazzaglia, Stefano Ferraro, Bart Dhoedt
Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment.
1 code implementation • 23 Nov 2022 • Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar
Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment.
1 code implementation • 24 Sep 2022 • Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen, Alexandre Piché, Bart Dhoedt, Aaron Courville, Alexandre Lacoste
In this work, we study the URLB and propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent, and a task-aware fine-tuning strategy combined with a new proposed hybrid planner, Dyna-MPC, to adapt the agent for downstream tasks.
no code implementations • 16 Sep 2022 • Stefano Ferraro, Toon Van de Maele, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt
Recently, deep learning methods have been proposed to learn a hidden state space structure purely from data, alleviating the experimenter from this tedious design task, but resulting in an entangled, non-interpreteable state space.
no code implementations • 19 Aug 2022 • Daria de Tinguy, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt
When studying unconstrained behaviour and allowing mice to leave their cage to navigate a complex labyrinth, the mice exhibit foraging behaviour in the labyrinth searching for rewards, returning to their home cage now and then, e. g. to drink.
no code implementations • 18 Aug 2022 • Samuel T. Wauthier, Bram Vanhecke, Tim Verbelen, Bart Dhoedt
The ability of tensor networks to represent the probabilistic nature of quantum states as well as to reduce large state spaces makes tensor networks a natural candidate for active inference.
no code implementations • 14 Jul 2022 • James Marien, Sam Leroux, Bart Dhoedt, Cedric De Boom
We find that our framework can generate suitable cover art for most genres, and that the visual features adapt themselves to audio feature changes.
no code implementations • 13 Jul 2022 • Pietro Mazzaglia, Tim Verbelen, Ozan Çatal, Bart Dhoedt
The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i. e., they minimize their free energy.
1 code implementation • NeurIPS 2021 • Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt
In this work, we propose a contrastive objective for active inference that strongly reduces the computational burden in learning the agent's generative model and planning future actions.
no code implementations • 26 Aug 2021 • Toon Van de Maele, Tim Verbelen, Ozan Catal, Bart Dhoedt
In this paper, we propose an active inference agent that actively gathers evidence for object classifications, and can learn novel object categories over time.
no code implementations • 17 Jun 2021 • Ni Wang, Ozan Catal, Tim Verbelen, Matthias Hartmann, Bart Dhoedt
Aerial navigation in GPS-denied, indoor environments, is still an open challenge.
no code implementations • 7 May 2021 • Ozan Çatal, Wouter Jansen, Tim Verbelen, Bart Dhoedt, Jan Steckel
Biologically inspired algorithms for simultaneous localization and mapping (SLAM) such as RatSLAM have been shown to yield effective and robust robot navigation in both indoor and outdoor environments.
1 code implementation • 22 Apr 2021 • Samuel T. Wauthier, Pietro Mazzaglia, Ozan Çatal, Cedric De Boom, Tim Verbelen, Bart Dhoedt
Historically, artificial intelligence has drawn much inspiration from neuroscience to fuel advances in the field.
2 code implementations • ICLR Workshop SSL-RL 2021 • Pietro Mazzaglia, Ozan Catal, Tim Verbelen, Bart Dhoedt
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition.
no code implementations • 24 Mar 2020 • Cedric De Boom, Samuel Wauthier, Tim Verbelen, Bart Dhoedt
In case the dimensionality is not predefined, this parameter is usually determined using time- and resource-consuming cross-validation.
no code implementations • 6 Mar 2020 • Ozan Çatal, Samuel Wauthier, Tim Verbelen, Cedric De Boom, Bart Dhoedt
Active inference is a theory that underpins the way biological agent's perceive and act in the real world.
no code implementations • 21 Feb 2020 • Cedric De Boom, Stephanie Van Laere, Tim Verbelen, Bart Dhoedt
Music that is generated by recurrent neural networks often lacks a sense of direction and coherence.
no code implementations • 30 Jan 2020 • Ozan Çatal, Tim Verbelen, Johannes Nauta, Cedric De Boom, Bart Dhoedt
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy.
no code implementations • 28 Jan 2020 • Ozan Çatal, Lawrence De Mol, Tim Verbelen, Bart Dhoedt
To develop and test our method, we start with an easy to identify object: a stuffed Piglet.
no code implementations • 17 Apr 2019 • Ozan Çatal, Johannes Nauta, Tim Verbelen, Pieter Simoens, Bart Dhoedt
Learning to take actions based on observations is a core requirement for artificial agents to be able to be successful and robust at their task.
no code implementations • 12 Nov 2018 • Xander Steenbrugge, Sam Leroux, Tim Verbelen, Bart Dhoedt
In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices.
no code implementations • 11 Sep 2018 • Pieter Van Molle, Miguel De Strooper, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
In this paper, we try to open the black box of the CNN by inspecting and visualizing the learned feature maps, in the field of dermatology.
no code implementations • 9 Jun 2018 • Pieter Van Molle, Tim Verbelen, Elias De Coninck, Cedric De Boom, Pieter Simoens, Bart Dhoedt
Learning-based approaches for robotic grasping using visual sensors typically require collecting a large size dataset, either manually labeled or by many trial and errors of a robotic manipulator in the real or simulated world.
no code implementations • 30 May 2018 • Sam Leroux, Tim Verbelen, Pieter Simoens, Bart Dhoedt
Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices.
no code implementations • 26 Apr 2018 • Sam Leroux, Pavlo Molchanov, Pieter Simoens, Bart Dhoedt, Thomas Breuel, Jan Kautz
Deep residual networks (ResNets) made a recent breakthrough in deep learning.
2 code implementations • 2 Jan 2018 • Cedric De Boom, Thomas Demeester, Bart Dhoedt
Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems.
no code implementations • 29 Nov 2017 • Sam Leroux, Steven Bohez, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
Binary neural networks are attractive in this case because the logical operations are very fast and efficient when implemented in hardware.
no code implementations • 9 Aug 2017 • Pieter Van Molle, Tim Verbelen, Steven Bohez, Sam Leroux, Pieter Simoens, Bart Dhoedt
However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task.
no code implementations • 13 Mar 2017 • Steven Bohez, Tim Verbelen, Elias De Coninck, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy.
1 code implementation • 2 Jul 2016 • Cedric De Boom, Steven Van Canneyt, Thomas Demeester, Bart Dhoedt
Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications such as event detection, opinion mining, news recommendation, etc.
no code implementations • 27 May 2016 • Sam Leroux, Steven Bohez, Cedric De Boom, Elias De Coninck, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network.
1 code implementation • 9 May 2016 • Cedric De Boom, Sam Leroux, Steven Bohez, Pieter Simoens, Thomas Demeester, Bart Dhoedt
We present four training and prediction schedules from the same character-level recurrent neural network.
no code implementations • 2 Dec 2015 • Cedric De Boom, Steven Van Canneyt, Steven Bohez, Thomas Demeester, Bart Dhoedt
We therefore investigated several text representations as a combination of word embeddings in the context of semantic pair matching.