Marijn Stollenga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Marijn Stollenga has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jürgen Schmidhuber
King Abdullah University of Science and Technology
3 shared publications - Alexander Förster
Roboter und Technik, 28213 Bremen, Germany
1 shared publication - Faustino Gomez
Galleria 2 CH-6928 Manno Switzerland
1 shared publication - Jonathan Masci
Istituto Dalle Molle di studi sull'Intelligenza Artificiale (IDSIA) Scuola universitaria professionale della Svizzera italiana (SUPSI) Università della Svizzera italiana (USI) Lugano Switzerland
1 shared publication Juergen Schmidhuber
1 shared publication- Jürgen Leitner
ARC Centre of Excellence for Robotic Vision, Queensland University of Technology, Brisbane, Australia
1 shared publication
Latest Publications
- 1 August 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (8) , 1599-1662
Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis
Consider a self-motivated artificial agent who is exploring a complex environment. Part of the complexity is due to the raw high-dimensional sensory input streams, which the agent needs to make sense of. Such inputs can be compactly encoded through a variety of means; one of these is slow feature analysis (SFA). Slow features encode spatiotemporal regularities, which are information-rich explanatory factors (latent variables) underlying the high-dimensional input streams. In our previous work, we have shown how slow features can be learned incrementally, while the agent explores its world, and modularly, such that different sets of features are learned for different parts of the environment (since a single set of regularities does not explain everything). In what order should the agent explore the different parts of the environment? Following Schmidhuber’s theory of artificial curiosity, the agent should always concentrate on the area where it can learn the easiest-to-learn set of features that it has not...
- 1 August 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (8) , 1599-1662
Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis
Consider a self-motivated artificial agent who is exploring a complex environment. Part of the complexity is due to the raw high-dimensional sensory input streams, which the agent needs to make sense of. Such inputs can be compactly encoded through a variety of means; one of these is slow feature analysis (SFA). Slow features encode spatiotemporal regularities, which are information-rich explanatory factors (latent variables) underlying the high-dimensional input streams. In our previous work, we have shown how slow features can be learned incrementally, while the agent explores its world, and modularly, such that different sets of features are learned for different parts of the environment (since a single set of regularities does not explain everything). In what order should the agent explore the different parts of the environment? Following Schmidhuber’s theory of artificial curiosity, the agent should always concentrate on the area where it can learn the easiest-to-learn set of features that it has not...
- Open Access
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Convolutional Neural Networks (CNNs) can be shifted across 2D images or 3D videos to segment them. They have a fixed input size and typically perceive only small local contexts of the pixels to be classified as foreground or background. In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM). Despite these theoretical advantages, however, unlike CNNs, previous MD-LSTM variants were hard to parallelize on GPUs. Here we re-arrange the traditional cuboid order of computations in MD-LSTM in pyramidal fashion. The resulting PyraMiD-LSTM is easy to parallelize, especially for 3D data such as stacks of brain slice images. PyraMiD-LSTM achieved best known pixel-wise brain image segmentation results on MRBrainS13 (and competitive results on EM-ISBI12).
Open AccessParallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Convolutional Neural Networks (CNNs) can be shifted across 2D images or 3D videos to segment them. They have a fixed input size and typically perceive only small local contexts of the pixels to be classified as foreground or background. In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM). Despite these theoretical advantages, however, unlike CNNs, previous MD-LSTM variants were hard to parallelize on GPUs. Here we re-arrange the traditional cuboid order of computations in MD-LSTM in pyramidal fashion. The resulting PyraMiD-LSTM is easy to parallelize, especially for 3D data such as stacks of brain slice images. PyraMiD-LSTM achieved best known pixel-wise brain image segmentation results on MRBrainS13 (and competitive results on EM-ISBI12).
- Open Access
Deep Networks with Internal Selective Attention through Feedback Connections
Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNets feedback structure can dynamically alter its convolutional filter sensitivities during classification. It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters. Feedback is trained through direct policy search in a huge million-dimensional parameter space, through scalable natural evolution strategies (SNES). On the CIFAR-10 and CIFAR-100 datasets, dasNet outperforms the previous state-of-the-art model.
Open AccessDeep Networks with Internal Selective Attention through Feedback Connections
Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNets feedback structure can dynamically alter its convolutional filter sensitivities during classification. It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters. Feedback is trained through direct policy search in a huge million-dimensional parameter space, through scalable natural evolution strategies (SNES). On the CIFAR-10 and CIFAR-100 datasets, dasNet outperforms the previous state-of-the-art model.
- Open Access
- 1 January 2014
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 7, 1-15
Curiosity driven reinforcement learning for motion planning on humanoids
Most previous work on \textit{artificial curiosity} and \textit{intrinsic motivation} focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study artificial curiosity in a more realistic setting, we \emph{embody} a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores \textit{intelligently}, showing \textit{interest} in its physical constraints as well as in objects it finds in its environment
- 1 January 2014
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 7, 1-15
Open AccessCuriosity driven reinforcement learning for motion planning on humanoids
Most previous work on \textit{artificial curiosity} and \textit{intrinsic motivation} focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study artificial curiosity in a more realistic setting, we \emph{embody} a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores \textit{intelligently}, showing \textit{interest} in its physical constraints as well as in objects it finds in its environment