
Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
Versatile movement representations allow robots to learn new tasks and r...
read it

Mind the Gap when Conditioning Amortised Inference in Sequential LatentVariable Models
Amortised inference enables scalable learning of sequential latentvaria...
read it

Dalek – a deeplearning emulator for TARDIS
Supernova spectral time series contain a wealth of information about the...
read it

Layerwise learning for quantum neural networks
With the increased focus on quantum circuit learning for nearterm appli...
read it

Variational StateSpace Models for Localisation and Dense 3D Mapping in 6 DoF
We solve the problem of 6DoF localisation and 3D dense reconstruction i...
read it

Learning to Fly via Deep ModelBased Reinforcement Learning
Learning to control robots without requiring models has been a longterm...
read it

Learning Flat Latent Manifolds with VAEs
Measuring the similarity between data points often requires domain knowl...
read it

Beta DVBF: Learning StateSpace Models for Control from High Dimensional Observations
Learning a model of dynamics from highdimensional images can be a core ...
read it

Variational Tracking and Prediction with Generative Disentangled StateSpace Models
We address tracking and prediction of multiple moving objects in visual ...
read it

Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images
The study of dexterous manipulation has provided important insights in h...
read it

Increasing the Generalisaton Capacity of Conditional VAEs
We address the problem of onetomany mappings in supervised learning, w...
read it

Switching Linear Dynamics for Variational Bayes Filtering
System identification of complex and nonlinear systems is a central prob...
read it

Learning Hierarchical Priors in VAEs
We propose to learn a hierarchical prior in the context of variational a...
read it

On Deep Set Learning and the Choice of Aggregations
Recently, it has been shown that many functions on sets can be represent...
read it

Bayesian Learning of Neural Network Architectures
In this paper we propose a Bayesian method for estimating architectural ...
read it

Fast Approximate Geodesics for Deep Generative Models
The length of the geodesic between two data points along the Riemannian ...
read it

MultiSource Neural Variational Inference
Learning from multiple sources of information is an important problem in...
read it

Active Learning based on Data Uncertainty and Model Sensitivity
Robots can rapidly acquire new skills from demonstrations. However, duri...
read it

Approximate Bayesian inference in spatial environments
We propose to learn a stochastic recurrent model to solve the problem of...
read it

Gaussian Process Neurons Learn Stochastic Activation Functions
We propose stochastic, nonparametric activation functions that are full...
read it

Automatic Differentiation for Tensor Algebras
Kjolstad et. al. proposed a tensor algebra compiler. It takes expression...
read it

Metrics for Deep Generative Models
Neural samplers such as variational autoencoders (VAEs) or generative ad...
read it

Unsupervised RealTime Control through Variational Empowerment
We introduce a methodology for efficiently computing a lower bound to em...
read it

TwoStream RNN/CNN for Action Recognition in 3D Videos
The recognition of actions from video sequences has many applications in...
read it

CNNbased Segmentation of Medical Imaging Data
Convolutional neural networks have been applied to a wide variety of com...
read it

Variational Inference with Hamiltonian Monte Carlo
Variational inference lies at the core of many stateoftheart algorith...
read it

Unsupervised preprocessing for Tactile Data
Tactile information is important for gripping, stable grasp, and inhand...
read it

Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
We introduce Deep Variational Bayes Filters (DVBF), a new method for uns...
read it

A Differentiable Transition Between Additive and Multiplicative Neurons
Existing approaches to combine both additive and multiplicative neural u...
read it

Variational Inference for Online Anomaly Detection in HighDimensional Time Series
Approximate variational inference has shown to be a powerful tool for mo...
read it

Scalability in Neural Control of Musculoskeletal Robots
Anthropomimetic robots are robots that sense, behave, interact and feel ...
read it

Efficient Empowerment
Empowerment quantifies the influence an agent has on its environment. Th...
read it

FlowNet: Learning Optical Flow with Convolutional Networks
Convolutional neural networks (CNNs) have recently been very successful ...
read it

A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions
Existing approaches to combine both additive and multiplicative neural u...
read it

On Fast Dropout and its Applicability to Recurrent Networks
Recurrent Neural Networks (RNNs) are rich models for the processing of s...
read it

Convolutional Neural Networks learn compact local image descriptors
A standard deep convolutional neural network paired with a suitable loss...
read it

Unsupervised Feature Learning for lowlevel Local Image Descriptors
Unsupervised feature learning has shown impressive results for a wide ra...
read it

Learning Sequence Neighbourhood Metrics
Recurrent neural networks (RNNs) in combination with a pooling operator ...
read it
Patrick van der Smagt
is this you? claim profile
Director of Fundamental AI Research at VW Group, Director of AI Research at Volkswagen AG, Chairman of the Board of Directors at Assistenzrobotik e.V., Professor for biomimetic robotics and machine learning at Technische Universität München from 20122016, Professor/ Scientist at Fortiss from 20122016, Head of assistive robotics and bionics, Center for Robotics and Mechatronics at DLR from 20082012, CoFounder at Simplias GmbH 2012, Postdoc at DLR from 19951998, Visiting Assistant Professor at University of Illinois at UrbanaChampaign 1992