Marijn F. Stollenga

Learn More
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. DasNet's feedback structure can dynamically alter its convolutional filter(More)
To produce even the simplest human-like behaviors, a humanoid robot must be able to see, act, and react, within a tightly integrated behavioral control system. Although there exists a rich body of literature in Computer Vision, Path Planning, and Feedback Control, wherein many critical subproblems are addressed individually , most demonstrable behaviors for(More)
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(More)
— We introduce a novel framework that builds task-relevant roadmaps (TRMs). TRMs can be used to plan complex task-relevant motions on robots with many degrees of freedom. To this end we create a new sampling based inverse kinematics optimizer called Natural Gradient Inverse Kinematics (NGIK), based on the principled heuristic solver called natural evolution(More)
—Pure scientists do not only invent new methods to solve given problems. They also invent new problems. The recent POWERPLAY framework formalizes this type of curiosity and creativity in a new, general, yet practical way. To acquire problem solving prowess through playing, POWERPLAY-based artificial explorers by design continually come up with the fastest(More)
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(More)
Planning movements for humanoid robots is still a major challenge due to the very high degrees-of-freedom involved. Most hu-manoid control frameworks incorporate dynamical constraints related to a task that require detailed knowledge of the robot's dynamics, making them impractical as efficient planning. In previous work, we introduced a novel planning(More)
  • 1