Search Results for author: Bart Dhoedt

Found 31 papers, 4 papers with code

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

no code implementations16 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.

Disentanglement

Home Run: Finding Your Way Home by Imagining Trajectories

no code implementations19 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.

Navigate

Learning Generative Models for Active Inference using Tensor Networks

no code implementations18 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.

Tensor Networks

Audio-guided Album Cover Art Generation with Genetic Algorithms

no code implementations14 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.

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

no code implementations13 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.

Variational Inference

Contrastive Active Inference

no code implementations NeurIPS 2021 Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt

Finally, we also show that contrastive methods perform significantly better in the case of distractors in the environment and that our method is able to generalize goals to variations in the background.

reinforcement-learning

Disentangling What and Where for 3D Object-Centric Representations Through Active Inference

no code implementations26 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.

object-detection Object Detection

LatentSLAM: unsupervised multi-sensor representation learning for localization and mapping

no code implementations7 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.

Representation Learning Robot Navigation +2

A learning gap between neuroscience and reinforcement learning

1 code implementation22 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.

reinforcement-learning

Curiosity-Driven Exploration via Latent Bayesian Surprise

no 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.

Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization

no code implementations24 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.

Deep Active Inference for Autonomous Robot Navigation

no code implementations6 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.

Bayesian Inference Robot Navigation

Rhythm, Chord and Melody Generation for Lead Sheets using Recurrent Neural Networks

no code implementations21 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.

Learning Perception and Planning with Deep Active Inference

no code implementations30 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.

Learning to Catch Piglets in Flight

no code implementations28 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.

object-detection Object Detection

Bayesian policy selection using active inference

no code implementations17 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.

Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

no code implementations12 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.

Relational Reasoning Representation Learning

Learning to Grasp from a Single Demonstration

no code implementations9 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.

Robotic Grasping

Privacy Aware Offloading of Deep Neural Networks

no code implementations30 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.

Character-level Recurrent Neural Networks in Practice: Comparing Training and Sampling Schemes

2 code implementations2 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.

Recommendation Systems

Transfer Learning with Binary Neural Networks

no code implementations29 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.

Transfer Learning

Decoupled Learning of Environment Characteristics for Safe Exploration

no code implementations9 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.

reinforcement-learning Safe Exploration

Sensor Fusion for Robot Control through Deep Reinforcement Learning

no code implementations13 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.

reinforcement-learning

Representation learning for very short texts using weighted word embedding aggregation

1 code implementation2 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.

Event Detection News Recommendation +4

Lazy Evaluation of Convolutional Filters

no code implementations27 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.

Efficiency Evaluation of Character-level RNN Training Schedules

1 code implementation9 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.

Learning Semantic Similarity for Very Short Texts

no code implementations2 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.

Information Retrieval Semantic Similarity +3

Cannot find the paper you are looking for? You can Submit a new open access paper.