• Publications
  • Influence
Expressive Power of Conditional Restricted Boltzmann Machines
We address the representational power of these models, proving results on the minimal size of universal approximators of conditional probability distributions, the maximal model approximation errors, and the dimension of the set of representable conditional distributions. Expand
On the records
World record setting has long attracted public interest and scientific investigation. Extremal records summarize the limits of the space explored by a process, and the historical progression of aExpand
NMODE - Neuro-MODule Evolution.
We show that NMODE is able to evolve a locomotion behaviour for a standard six-legged walking machine in approximately 10 generations and show how it can be used for incremental evolution of a complex walking machine. Expand
Quantifying Morphological Computation of Soft Robotic Hands
Soft manipulators realize complex grasping behavior with simple control, as demonstrated by research with compliant and soft hands [1], [2], [3]. To understand the contribution of compliance to theExpand
From Morphological Computation to Morphological Intelligence
How the physical properties of my body reduce the amount of computation that my brain has to do in situations that otherwise would require extensive and expensive calculations. Expand
Numerical Analysis of the Morphological Intelligence Quantifications
The previous chapter introduced and discussed five different concepts to quantify morphological intelligence. Expand
A Theory of Morphological Intelligence
Pfeifer and Iida [1] and Paul [2] state that “One problem with the concept of morphological computation is that while intuitively plausible, it has defied serious quantification efforts. Expand