Search Results for author: J. Michael Herrmann

Found 5 papers, 0 papers with code

Evolutionary Selective Imitation: Interpretable Agents by Imitation Learning Without a Demonstrator

no code implementations17 Sep 2020 Roy Eliya, J. Michael Herrmann

We propose a new method for training an agent via an evolutionary strategy (ES), in which we iteratively improve a set of samples to imitate: Starting with a random set, in every iteration we replace a subset of the samples with samples from the best trajectories discovered so far.

Imitation Learning OpenAI Gym +1

Lagged correlation-based deep learning for directional trend change prediction in financial time series

no code implementations27 Nov 2018 Ben Moews, J. Michael Herrmann, Gbenga Ibikunle

Trend change prediction in complex systems with a large number of noisy time series is a problem with many applications for real-world phenomena, with stock markets as a notoriously difficult to predict example of such systems.

Feature Engineering Time Series +1

The Voynich Manuscript is Written in Natural Language: The Pahlavi Hypothesis

no code implementations6 Sep 2017 J. Michael Herrmann

Here, we provide evidence that the VM is written in natural language by establishing a relation of the Voynich alphabet and the Iranian Pahlavi script.

Relation Translation

Critical Parameters in Particle Swarm Optimisation

no code implementations19 Nov 2015 J. Michael Herrmann, Adam Erskine, Thomas Joyce

Particle swarm optimisation is a metaheuristic algorithm which finds reasonable solutions in a wide range of applied problems if suitable parameters are used.

CriPS: Critical Dynamics in Particle Swarm Optimization

no code implementations27 Feb 2014 Adam Erskine, J. Michael Herrmann

Particle Swarm Optimisation (PSO) makes use of a dynamical system for solving a search task.

Cannot find the paper you are looking for? You can Submit a new open access paper.