Search Results for author:
Found 38 papers, 8 papers with code
Representation learning for very short texts using weighted word embedding aggregation
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.
Curiosity-Driven Exploration via Latent Bayesian Surprise
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition.
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
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.
Choreographer: Learning and Adapting Skills in Imagination
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.
Character-level Recurrent Neural Networks in Practice: Comparing Training and Sampling Schemes
Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems.
Efficiency Evaluation of Character-level RNN Training Schedules
We present four training and prediction schedules from the same character-level recurrent neural network.
A learning gap between neuroscience and reinforcement learning
Historically, artificial intelligence has drawn much inspiration from neuroscience to fuel advances in the field.
Contrastive Active Inference
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.
Learning to Grasp from a Single Demonstration
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.
Privacy Aware Offloading of Deep Neural Networks
Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices.
IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
Deep residual networks (ResNets) made a recent breakthrough in deep learning.
Transfer Learning with Binary Neural Networks
Binary neural networks are attractive in this case because the logical operations are very fast and efficient when implemented in hardware.
Decoupled Learning of Environment Characteristics for Safe Exploration
However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task.
Sensor Fusion for Robot Control through Deep Reinforcement Learning
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.
Lazy Evaluation of Convolutional Filters
In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network.
Learning Semantic Similarity for Very Short Texts
We therefore investigated several text representations as a combination of word embeddings in the context of semantic pair matching.
Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification
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.
Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations
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.
Bayesian policy selection using active inference
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.
Learning to Catch Piglets in Flight
To develop and test our method, we start with an easy to identify object: a stuffed Piglet.
Learning Perception and Planning with Deep Active Inference
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.
Rhythm, Chord and Melody Generation for Lead Sheets using Recurrent Neural Networks
Music that is generated by recurrent neural networks often lacks a sense of direction and coherence.
Deep Active Inference for Autonomous Robot Navigation
Active inference is a theory that underpins the way biological agent's perceive and act in the real world.
Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization
In case the dimensionality is not predefined, this parameter is usually determined using time- and resource-consuming cross-validation.
LatentSLAM: unsupervised multi-sensor representation learning for localization and mapping
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.
Towards bio-inspired unsupervised representation learning for indoor aerial navigation
Aerial navigation in GPS-denied, indoor environments, is still an open challenge.
Disentangling What and Where for 3D Object-Centric Representations Through Active Inference
In this paper, we propose an active inference agent that actively gathers evidence for object classifications, and can learn novel object categories over time.
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
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.
Audio-guided Album Cover Art Generation with Genetic Algorithms
We find that our framework can generate suitable cover art for most genres, and that the visual features adapt themselves to audio feature changes.
Learning Generative Models for Active Inference using Tensor Networks
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.
Home Run: Finding Your Way Home by Imagining Trajectories
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.
Disentangling Shape and Pose for Object-Centric Deep Active Inference Models
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.
Object-Centric Scene Representations using Active Inference
Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment.
Inferring Hierarchical Structure in Multi-Room Maze Environments
Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment.
FOCUS: Object-Centric World Models for Robotics Manipulation
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.
Integrating cognitive map learning and active inference for planning in ambiguous environments
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.
Bridging Cognitive Maps: a Hierarchical Active Inference Model of Spatial Alternation Tasks and the Hippocampal-Prefrontal Circuit
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.
Learning Spatial and Temporal Hierarchies: Hierarchical Active Inference for navigation in Multi-Room Maze Environments
Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment.
