223 citations · 465 across the 22 of their papers we have counts for
8 papers · 1 filter
A Frequency-Domain Encoding for Neuroevolution
Jan Koutník, Juergen Schmidhuber, Faustino Gomez
Neuroevolution has yet to scale up to complex reinforcement learning tasks that require large networks. Networks with many inputs (e.g. raw video) imply a very high dimensional sea…
A Learning Framework for Morphological Operators using Counter-Harmonic Mean
Jonathan Masci, Jesús Angulo, Jürgen Schmidhuber
We present a novel framework for learning morphological operators using counter-harmonic mean. It combines concepts from morphology and convolutional neural networks. A thorough ex…
First Experiments with PowerPlay
Rupesh Kumar Srivastava, Bas R. Steunebrink, Jürgen Schmidhuber
Like a scientist or a playing child, PowerPlay not only learns new skills to solve given problems, but also invents new interesting problems by itself. By design, it continually co…
Self-Delimiting Neural Networks
Juergen Schmidhuber
Self-delimiting (SLIM) programs are a central concept of theoretical computer science, particularly algorithmic information & probability theory, and asymptotically optimal program…
Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices
Yi Sun, Faustino Gomez, Juergen Schmidhuber
We present a new way of converting a reversible finite Markov chain into a non-reversible one, with a theoretical guarantee that the asymptotic variance of the MCMC estimator based…
Efficient Natural Evolution Strategies
Yi Sun, Daan Wierstra, Tom Schaul +1
Efficient Natural Evolution Strategies (eNES) is a novel alternative to conventional evolutionary algorithms, using the natural gradient to adapt the mutation distribution. Unlike…