Bartosz Wieloch

Semantic Backpropagation for Designing Search Operators in Genetic Programming

In genetic programming, a search algorithm is expected to produce a program that achieves the desired final computation state (desired output). To reach that state, an executing program needs to traverse certain intermediate computation states. An evolutionary search process is expected to autonomously discover such states. This can be difficult for nontrivial tasks that require long programs to be solved. The semantic backpropagation algorithm proposed in this paper heuristically inverts the execution of evolving programs to determine the desired intermediate computation states. Two search operators, random desired operator and approximately geometric semantic crossover, use the intermediate states determined by semantic backpropagation to define subtasks of the original programming task, which are then solved using an exhaustive search. The operators outperform the standard genetic search operators and other semantic-aware operators when compared on a suite of symbolic regression and Boolean benchmarks. This result and additional analysis conducted in this paper indicate that semantic backpropagation helps evolution to identify the desired intermediate computation states and makes the search process more efficient.

Evolving strategy for a probabilistic game of imperfect information using genetic programming

We provide the complete record of methodology that let us evolve BrilliAnt, the winner of the Ant Wars contest. Ant Wars contestants are virtual ants collecting food on a grid board in the presence of a competing ant. BrilliAnt has been evolved through a competitive one-population coevolution using genetic programming and fitnessless selection. In this paper, we detail the evolutionary setup that lead to BrilliAnt’s emergence, assess its direct and indirect human-competitiveness, and describe the behavioral patterns observed in its strategy.

Automatic generation and exploitation of related problems in genetic programming

We propose an evolutionary framework that uses the set of instructions provided with a genetic programming (GP) problem to automatically build a repertoire of related problems and subsequently uses them to improve the performance of search. The novel idea is to use the synthesized related problems to simultaneously exert multiple selection pressures on the evolving population(s). For that framework, we design two methods. In the first method, individuals optimizing for particular problems dwell in separate populations and spawn clones which migrate to other populations, similarly to the island model. The second method operates on a single population and ranks the fitness values that individuals receive from particular problems to make them comparable. When applied to six symbolic regression problems of different difficulty, both methods perform better than the standard GP, though sometimes fail to prove superior to certain control setup.

Learning and Recognition of Hand-Drawn Shapes Using Generative Genetic Programming

We describe a novel method of evolutionary visual learning that uses generative approach for assessing learners ability to recognize image contents. Each learner, implemented as a genetic programming individual, processes visual primitives that represent local salient features derived from a raw input raster image. In response to that input, the learner produces partial reproduction of the input image, and is evaluated according to the quality of that reproduction. We present the method in detail and verify it experimentally on the real-world task of recognition of hand-drawn shapes.

Running programs backwards: instruction inversion for effective search in semantic spaces

The instructions used for solving typical genetic programming tasks have strong mathematical properties. In this study, we leverage one of such properties: invertibility. A search operator is proposed that performs an approximate reverse execution of program fragments, trying to determine in this way the desired semantics (partial outcome) at intermediate stages of program execution. The desired semantics determined in this way guides the choice of a subprogram that replaces the old program fragment. An extensive computational experiment on 20 symbolic regression and Boolean domain problems leads to statistically significant evidence that the proposed Random Desired Operator outperforms all typical combinations of conventional mutation and crossover operators.

Fitnessless coevolution

We introduce fitnessless coevolution (FC), a novel method of comparative one-population coevolution. FC plays games between individuals to settle tournaments in the selection phase and skips the typical phase of evaluation. The selection operator applies a single-elimination tournament to a randomly drawn group of individuals, and the winner of the final round becomes the result of selection. Therefore, FC does not involve explicit fitness measure. We prove that, under a condition of transitivity of the payoff matrix, the dynamics of FC is identical to that of the traditional evolutionary algorithm. The experimental results, obtained on a diversified group of problems, demonstrate that FC is able to produce solutions that are equally good or better than solutions obtained using fitness-based one-population coevolution with different selection methods.

Multitask visual learning using genetic programming

We propose a multitask learning method of visual concepts within the genetic programming (GP) framework. Each GP individual is composed of several trees that process visual primitives derived from input images. Two trees solve two different visual tasks and are allowed to share knowledge with each other by commonly calling the remaining GP trees (subfunctions) included in the same individual. The performance of a particular tree is measured by its ability to reproduce the shapes contained in the training images. We apply this method to visual learning tasks of recognizing simple shapes and compare it to a reference method. The experimental verification demonstrates that such multitask learning often leads to performance improvements in one or both solved tasks, without extra computational effort.

Knowledge reuse in genetic programming applied to visual learning

We propose a method of knowledge reuse for an ensemble of genetic programming-based learners solving a visual learning task. First, we introduce a visual learning method that uses genetic programming individuals to represent hypotheses. Individuals-hypotheses process image representation composed of visual primitives derived from the training images that contain objects to be recognized. The process of recognition is generative, i.e., an individual is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This canonical method is extended with a knowledge reuse mechanism that allows a learner to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare the performance of the extended approach to the basic method on a real-world tasks of handwritten character recognition, and conclude that knowledge reuse leads to significant convergence speedup and, more importantly, significantly reduces the risk of overfitting.

CROSS-TASK CODE REUSE IN GENETIC PROGRAMMING APPLIED TO VISUAL LEARNING

Abstract We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a visual learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit visual similarity.

Genetic programming for cross-task knowledge sharing

We consider multitask learning of visual concepts within genetic programming (GP) framework. The proposed method evolves a population of GP individuals, with each of them composed of several GP trees that process visual primitives derived from input images. The two main trees are delegated to solving two different visual tasks and are allowed to share knowledge with each other by calling the remaining GP trees (subfunctions) included in the same individual. The method is applied to the visual learning task of recognizing simple shapes, using generative approach based on visual primitives. We compare this approach to a reference method devoid of knowledge sharing, and conclude that in the worst case cross-task learning performs equally well, and in many cases it leads to significant performance improvements in one or both solved tasks.