Search Results for author:
Found 62 papers, 11 papers with code
LIMT: Language-Informed Multi-Task Visual World Models
Our results highlight the benefits of using language-driven task representations for world models and a clear advantage of model-based multi-task learning over the more common model-free paradigm.
The Shortcomings of Force-from-Motion in Robot Learning
Robotic manipulation requires accurate motion and physical interaction control.
Pragmatic auditing: a pilot-driven approach for auditing Machine Learning systems
For such a novel type of algorithmic auditing to become standard practice, two main prerequisites need to be available: A lifecycle model that is tailored towards transparency and accountability, and a principled risk assessment procedure that allows the proper scoping of the audit.
Overcoming Knowledge Barriers: Online Imitation Learning from Observation with Pretrained World Models
In this paper, we study Imitation Learning from Observation with pretrained models and find existing approaches such as BCO and AIME face knowledge barriers, specifically the Embodiment Knowledge Barrier (EKB) and the Demonstration Knowledge Barrier (DKB), greatly limiting their performance.
A dataset of primary nasopharyngeal carcinoma MRI with multi-modalities segmentation
Multi-modality magnetic resonance imaging data with various sequences facilitate the early diagnosis, tumor segmentation, and disease staging in the management of nasopharyngeal carcinoma (NPC).
Guided Decoding for Robot Motion Generation and Adaption
This integration facilitates rapid adaptation to new tasks and optimizes the utilization of accumulated expertise by allowing robots to learn and generalize from demonstrated trajectories.
Sequential Model for Predicting Patient Adherence in Subcutaneous Immunotherapy for Allergic Rhinitis
How to enhance the adherence of patients to maximize the benefit of allergen immunotherapy (AIT) plays a crucial role in the management of AIT.
On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
We study the choice of action space in robot manipulation learning and sim-to-real transfer.
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
Our method is "zero-shot" in the sense that it does not require further training for the world model or online interactions with the environment after given the demonstration.
Filter-Aware Model-Predictive Control
Partially-observable problems pose a trade-off between reducing costs and gathering information.
PRISM: Probabilistic Real-Time Inference in Spatial World Models
We introduce PRISM, a method for real-time filtering in a probabilistic generative model of agent motion and visual perception.
CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts.
Probabilistic Dalek -- Emulator framework with probabilistic prediction for supernova tomography
Supernova spectral time series can be used to reconstruct a spatially resolved explosion model known as supernova tomography.
Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphs
Auto-encoder models that preserve similarities in the data are a popular tool in representation learning.
Flat Latent Manifolds for Human-machine Co-creation of Music
We therefore consider a music-generating algorithm as a counterpart to a human musician, in a setting where reciprocal interplay is to lead to new experiences, both for the musician and the audience.
Tracking and Planning with Spatial World Models
We introduce a method for real-time navigation and tracking with differentiably rendered world models.
Latent Matters: Learning Deep State-Space Models
Our results show that the constrained optimisation framework significantly improves system identification and prediction accuracy on the example of established state-of-the-art DSSMs.
Exploration via Empowerment Gain: Combining Novelty, Surprise and Learning Progress
We show that while such an agent is still novelty seeking, i. e. interested in exploring the whole state space, it focuses on exploration where its perceived influence is greater, avoiding areas of greater stochasticity or traps that limit its control.
Less Suboptimal Learning and Control in Variational POMDPs
We examine the effect of the conditioning gap on model-based reinforcement learning with variational world models.
Model-based Reinforcement Learning
reinforcement-learning
+2
Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
We unify previous adaptation techniques, for example, various types of obstacle avoidance, via-points, mutual avoidance, in one single framework and combine them to solve complex robotic problems.
Robotics
Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO).
Dalek -- a deep-learning emulator for TARDIS
We show that we can train an emulator for this problem given a modest training set of a hundred thousand spectra (easily calculable on modern supercomputers).
Layerwise learning for quantum neural networks
In order to ameliorate some of these challenges, we investigate a layerwise learning strategy for parametrized quantum circuits.
Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
We solve the problem of 6-DoF localisation and 3D dense reconstruction in spatial environments as approximate Bayesian inference in a deep state-space model.
Continual Learning with Bayesian Neural Networks for Non-Stationary Data
We represent the posterior approximation of the network weights by a diagonal Gaussian distribution and a complementary memory of raw data.
Learning to Fly via Deep Model-Based Reinforcement Learning
Learning to control robots without requiring engineered models has been a long-term goal, promising diverse and novel applications.
Model-based Reinforcement Learning
reinforcement-learning
+1
Learning Flat Latent Manifolds with VAEs
Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry.
Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision making.
Variational Tracking and Prediction with Generative Disentangled State-Space Models
We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model.
FLAT MANIFOLD VAES
Latent-variable models represent observed data by mapping a prior distribution over some latent space to an observed space.
Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images
In addition, compared with previous single finger estimation in an experimental environment, we extend the approach to multiple finger force estimation, which can be used for applications such as human grasping analysis.
Increasing the Generalisation Capacity of Conditional VAEs
We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost.
Switching Linear Dynamics for Variational Bayes Filtering
System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning.
Learning Hierarchical Priors in VAEs
We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution.
On Deep Set Learning and the Choice of Aggregations
Recently, it has been shown that many functions on sets can be represented by sum decompositions.
Bayesian Learning of Neural Network Architectures
In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth.
Fast Approximate Geodesics for Deep Generative Models
The length of the geodesic between two data points along a Riemannian manifold, induced by a deep generative model, yields a principled measure of similarity.
Multi-Source Neural Variational Inference
Learning from multiple sources of information is an important problem in machine-learning research.
Active Learning based on Data Uncertainty and Model Sensitivity
It relies on the Jacobian of the likelihood to detect non-smooth transitions in the latent space, i. e., transitions that lead to abrupt changes in the movement of the robot.
Approximate Bayesian inference in spatial environments
Model-based approaches bear great promise for decision making of agents interacting with the physical world.
Gaussian Process Neurons
We propose a method to learn stochastic activation functions for use in probabilistic neural networks.
Gaussian Process Neurons Learn Stochastic Activation Functions
The proposed model can intrinsically handle uncertainties in its inputs and self-estimate the confidence of its predictions.
Metrics for Deep Generative Models
Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution represented by a dataset.
Automatic Differentiation for Tensor Algebras
For the function $f_{ij} (x) = x_i^2$, the derivative of the loss is $(dx)_i=\partial l/\partial x_i=\sum_j (df)_{ij}2x_i$; the sum is necessary because index $j$ does not appear in the indices of $f$.
Unsupervised Real-Time Control through Variational Empowerment
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control.
Two-Stream RNN/CNN for Action Recognition in 3D Videos
The recognition of actions from video sequences has many applications in health monitoring, assisted living, surveillance, and smart homes.
CNN-based Segmentation of Medical Imaging Data
While most of the existing literature on medical image segmentation focuses on soft tissue and the major organs, this work is validated on data both from the central nervous system as well as the bones of the hand.
Ranked #2 on
Brain Tumor Segmentation
on BRATS-2015
(using extra training data)
Variational Inference with Hamiltonian Monte Carlo
Variational inference lies at the core of many state-of-the-art algorithms.
Unsupervised preprocessing for Tactile Data
Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors.
ML-based tactile sensor calibration: A universal approach
We study the responses of two tactile sensors, the fingertip sensor from the iCub and the BioTac under different external stimuli.
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models.
A Differentiable Transition Between Additive and Multiplicative Neurons
Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform.
Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series
Approximate variational inference has shown to be a powerful tool for modeling unknown complex probability distributions.
Scalability in Neural Control of Musculoskeletal Robots
Anthropomimetic robots are robots that sense, behave, interact and feel like humans.
Efficient Empowerment
This is a natural candidate for an intrinsic reward signal in the context of reinforcement learning: the agent will place itself in a situation where its action have maximum stability and maximum influence on the future.
Fast Adaptive Weight Noise
Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods.
FlowNet: Learning Optical Flow with Convolutional Networks
Optical flow estimation has not been among the tasks where CNNs were successful.
A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions
Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform.
On Fast Dropout and its Applicability to Recurrent Networks
Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data.
Convolutional Neural Networks learn compact local image descriptors
A standard deep convolutional neural network paired with a suitable loss function learns compact local image descriptors that perform comparably to state-of-the art approaches.
Unsupervised Feature Learning for low-level Local Image Descriptors
Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision.
Learning Sequence Neighbourhood Metrics
Recurrent neural networks (RNNs) in combination with a pooling operator and the neighbourhood components analysis (NCA) objective function are able to detect the characterizing dynamics of sequences and embed them into a fixed-length vector space of arbitrary dimensionality.
