Conservation machine learning: a case study of random forests.

Conservation machine learning conserves models across runs, users, and experiments-and puts them to good use. We have previously shown the merit of this idea through a small-scale preliminary experiment, involving a single dataset source, 10 datasets, and a single so-called cultivation method-used to produce the final ensemble. In this paper, focusing on classification tasks, we perform extensive experimentation with conservation random forests, involving 5 cultivation methods (including a novel one introduced herein-lexigarden), 6 dataset sources, and 31 datasets. We show that significant improvement can be attained by making use of models we are already in possession of anyway, and envisage the possibility of repositories of models (not merely datasets, solutions, or code), which could be made available to everyone, thus having conservation live up to its name, furthering the cause of data and computational science.

Gamorithm.

Examining games from a fresh perspective we present the idea of game-inspired and game-based algorithms, dubbed gamorithms.

OMNIREP: Originating Meaning by Coevolving Encodings and Representations.

A major effort in the practice of evolutionary computation (EC) goes into deciding how to represent individuals in the evolving population. This task is actually composed of two subtasks: defining a data structure that is the representation and defining the encoding that enables to interpret the representation. In this paper we employ a coevolutionary algorithm-dubbed omnirep-to discover both a representation and an encoding that solve a particular problem of interest. We describe four experiments that provide a proof-of-concept of omnirep's essential merit. We think that the proposed methodology holds potential as a problem solver and also as an exploratory medium when scouting for good representations.

Correction to: Investigating the parameter space of evolutionary algorithms.

[This corrects the article DOI: 10.1186/s13040-018-0164-x.].

Automated discovery of test statistics using genetic programming.

The process of developing new test statistics is laborious, requiring the manual development and evaluation of mathematical functions that satisfy several theoretical properties. Automating this process, hitherto not done, would greatly accelerate the discovery of much-needed, new test statistics. This automation is a challenging problem because it requires the discovery method to know something about the desirable properties of a good test statistic in addition to having an engine that can develop and explore candidate mathematical solutions with an intuitive representation. In this paper we describe a genetic programming-based system for the automated discovery of new test statistics. Specifically, our system was able to discover test statistics as powerful as the t-test for comparing sample means from two distributions with equal variances.

EBIC: an evolutionary-based parallel biclustering algorithm for pattern discovery.

Motivation: Biclustering algorithms are commonly used for gene expression data analysis. However, accurate identification of meaningful structures is very challenging and state-of-the-art methods are incapable of discovering with high accuracy different patterns of high biological relevance. Results: In this paper, a novel biclustering algorithm based on evolutionary computation, a sub-field of artificial intelligence, is introduced. The method called EBIC aims to detect order-preserving patterns in complex data. EBIC is capable of discovering multiple complex patterns with unprecedented accuracy in real gene expression datasets. It is also one of the very few biclustering methods designed for parallel environments with multiple graphics processing units. We demonstrate that EBIC greatly outperforms state-of-the-art biclustering methods, in terms of recovery and relevance, on both synthetic and genetic datasets. EBIC also yields results over 12 times faster than the most accurate reference algorithms. Availability and implementation: EBIC source code is available on GitHub at https://github.com/EpistasisLab/ebic. Supplementary information: Supplementary data are available at Bioinformatics online.

Investigating the parameter space of evolutionary algorithms.

Evolutionary computation (EC) has been widely applied to biological and biomedical data. The practice of EC involves the tuning of many parameters, such as population size, generation count, selection size, and crossover and mutation rates. Through an extensive series of experiments over multiple evolutionary algorithm implementations and 25 problems we show that parameter space tends to be rife with viable parameters, at least for the problems studied herein. We discuss the implications of this finding in practice for the researcher employing EC.

Finding a common motif of RNA sequences using genetic programming: the GeRNAMo system.

We focus on finding a consensus motif of a set of homologous or functionally related RNA molecules. Recent approaches to this problem have been limited to simple motifs, require sequence alignment, and make prior assumptions concerning the data set. We use genetic programming to predict RNA consensus motifs based solely on the data set. Our system -- dubbed GeRNAMo (Genetic programming of RNA Motifs) -- predicts the most common motifs without sequence alignment and is capable of dealing with any motif size. Our program only requires the maximum number of stems in the motif, and if prior knowledge is available the user can specify other attributes of the motif (e.g., the range of the motif's minimum and maximum sizes), thereby increasing both sensitivity and speed. We describe several experiments using either ferritin iron response element (IRE); signal recognition particle (SRP); or microRNA sequences, showing that the most common motif is found repeatedly, and that our system offers substantial advantages over previous methods.

The data-and-signals cellular automaton and its application to growing structures.

In a traditional cellular automaton (CA) a cell is implemented by a rule table defining its state at the next time step, given its present state and those of its neighbors. The cell thus deals only with states. We present a novel CA where the cell handles data and signals. The cell is designed as a digital system comprising a processing unit and a control unit. This allows the realization of various growing structures, including self-replicating loops and biomorphs. We also describe the hardware implementation of these structures within our electronic wall for bio-inspired applications, the BioWall.

Coevolving solutions to the shortest common superstring problem.

The shortest common superstring (SCS) problem, known to be NP-Complete, seeks the shortest string that contains all strings from a given set. In this paper we compare four approaches for finding solutions to the SCS problem: a standard genetic algorithm, a novel cooperative-coevolutionary algorithm, a benchmark greedy algorithm, and a parallel coevolutionary-greedy approach. We show the coevolutionary approach produces the best results, and discuss directions for future research.

Evolutionary plantographics.

This letter describes an evolutionary system for creating lifelike three-dimensional plants and flowers, our main goal being the facilitation of producing realistic plant imagery. With these two goals in mind--ease of generation and realism--we designed the plant genotype and the genotype-to-phenotype mapping. Diversity in our system comes about through two distinct processes--evolution and randomization--allowing the creation not only of single plants but of entire gardens and forests. Thus, we are able to readily produce natural-looking artificial scenes.

An interactive self-replicator implemented in hardware.

Self-replicating loops presented to date are essentially worlds unto themselves, inaccessible to the observer once the replication process is launched. In this article we present the design of an interactive self-replicating loop of arbitrary size, wherein the user can physically control the loop's replication and induce its destruction. After introducing the BioWall, a reconfigurable electronic wall for bio-inspired applications, we describe the design of our novel loop and delineate its hardware implementation in the wall.