NeuroEvolution Of Augmenting Topologies Research Articles

Self-Organizing Floor Plans

This article introduces and comments on some of the techniques currently used by designers to generate automatic building floor plans and spatial configurations in general, with emphasis on machine learning and neural networks models. This is a relatively new tendency in computational design that reflects a growing interest in advanced generative and optimization models by architects and building engineers. The first part of this work contextualizes self-organizing floor plans in architecture and computational design, highlighting their importance and potential for designers as well as software developers. The central part discusses some of the most common techniques with concrete examples, including Neuro Evolution of Augmenting Topologies (NEAT) and Generative Adversarial Networks (GAN). The final section of the article provides some general comments considering pitfalls and possible future developments, as well as speculating on the future of this trend.

An Efficient Application of Neuroevolution for Competitive Multiagent Learning

Multiagent systems provide an ideal environment for the evaluation and analysis of real-world problems using reinforcement learning algorithms. Most traditional approaches to multiagent learning are affected by long training periods as well as high computational complexity. NEAT (NeuroEvolution of Augmenting Topologies) is a popular evolutionary strategy used to obtain the best performing neural network architecture often used to tackle optimization problems in the field of artificial intelligence. This paper utilizes the NEAT algorithm to achieve competitive multiagent learning on a modified pong game environment in an efficient manner. The competing agents abide by different rules while having similar observation space parameters. The proposed algorithm utilizes this property of the environment to define a singular neuroevolutionary procedure that obtains the optimal policy for all the agents. The compiled results indicate that the proposed implementation achieves ideal behaviour in a very short training period when compared to existing multiagent reinforcement learning models.

Role Comparison between Deep Belief Neural Network and NeuroEvolution of Augmenting Topologies to Detect Diabetes

Diabetes in Indonesia has been perceived as a grave health problem and has been a concern since the early 1980’s [2]. The prevalence of diabetes in adults in Indonesia, as stated by IDF, was 6.2% with the total case amounting to 10.681.400. Moreover, Indonesia is also in the top ten global countries with the highest diabetes case in 2013. This research will investigate the role of Deep Belief Network (DBN) and NeuroEvolution of Augmenting Topology (NEAT) in solving regression problems in detecting diabetes. DBN works by processing the data in unsupervised network architectures. The algorithm puts Restricted Boltzmann Machines (RBM) into a stacked process. The output of the first RBM will be the input for the next RBM. On the other hand, the NEAT algorithm works by investigating the neural network architecture and evaluating the architecture using a multi-layer perceptron algorithm. Collaboration with a Genetic Algorithm in NEAT is the key process in architecture development. The research results showed that DBN could be utilized as the initial weight for Backpropagation Neural Network at 22.61% on average. On the other hand, the NEAT algorithm could be used by collaborating with a multi-layer perceptron to solve this regression problem by providing 74.5% confidence. This work also reveals potential works in the future by combining the Backpropagation algorithm with NEAT as an evaluation function and by combining it with DBN algorithms to process the produced initial weight.

Difference-Based Mutation Operation for Neuroevolution of Augmented Topologies

In this paper, a novel search operation is proposed for the neuroevolution of augmented topologies, namely the difference-based mutation. This operator uses the differences between individuals in the population to perform more efficient search for optimal weights and structure of the model. The difference is determined according to the innovation numbers assigned to each node and connection, allowing tracking the changes. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses a set of mutation operators, including connections merging and deletion. The algorithm is tested on a set of classification problems and the rotary inverted pendulum control problem. The comparison is performed between the basic approach and modified versions. The sensitivity to parameter values is examined. The experimental results prove that the newly developed operator delivers significant improvements to the classification quality in several cases, and allow finding better control algorithms.

NeuroEvolution of augmenting topologies for solving a two-stage hybrid flow shop scheduling problem: A comparison of different solution strategies

The article investigates the application of NeuroEvolution of Augmenting Topologies (NEAT) to generate and parameterize artificial neural networks (ANN) on determining allocation and sequencing decisions in a two-stage hybrid flow shop scheduling environment with family setup times. NEAT is a machine-learning and neural architecture search algorithm, which generates both, the structure and the hyper-parameters of an ANN. Our experiments show that NEAT can compete with state-of-the-art approaches in terms of solution quality and outperforms them regarding computational efficiency. The main contributions of this article are: (i) A comparison of five different strategies, evaluated with 14 different experiments, on how ANNs can be applied for solving allocation and sequencing problems in a hybrid flow shop environment, (ii) a comparison of the best identified NEAT strategy with traditional heuristic and metaheuristic approaches concerning solution quality and computational efficiency.

Crowded Environment Navigation with NEAT: Impact of Perception Resolution on Controller Optimization

Crowd navigation with autonomous systems is a topic which has seen a rapid increase in interest recently. While it appears natural to humans, being able to reach a target can prove difficult or impossible to a mobile robot because of the safety issues related to collisions with people. In this work we propose an approach to control a robot in a crowded environment; the method employs an Artificial Neural Network (ANN) that is trained with the NeuroEvolution of Augmented Topologies (NEAT) method. Models for the kinematics, perception, and cognition of the robot are presented. In particular, perception is based on a raycasting model which is tailored on the ANN. An in-depth analysis of a number of parameters of the environment and the robot is performed and a comparative analysis is presented; finally, results of the performance of the controller trained with NEAT are compared to those of a human driver who takes over the controller itself. Results show that the intelligent controller is able to perform on par with the human, within the simulated environment.

A Systematic Literature Review of the Successors of "NeuroEvolution of Augmenting Topologies".

NeuroEvolution (NE) refers to a family of methods for optimizing Artificial Neural Networks (ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting Topologies (NEAT) is considered one of the most influential algorithms in the field. Eighteen years after its invention, a plethora of methods have been proposed that extend NEAT in different aspects. In this article, we present a systematic literature review (SLR) to list and categorize the methods succeeding NEAT. Our review protocol identified 232 papers by merging the findings of two major electronic databases. Applying criteria that determine the paper's relevance and assess its quality, resulted in 61 methods that are presented in this article. Our review article proposes a new categorization scheme of NEAT's successors into three clusters. NEAT-based methods are categorized based on 1) whether they consider issues specific to the search space or the fitness landscape, 2) whether they combine principles from NE and another domain, or 3) the particular properties of the evolved ANNs. The clustering supports researchers 1) understanding the current state of the art that will enable them, 2) exploring new research directions or 3) benchmarking their proposed method to the state of the art, if they are interested in comparing, and 4) positioning themselves in the domain or 5) selecting a method that is most appropriate for their problem.

Reinforcement learning of adaptive online rescheduling timing and computing time allocation

Mathematical optimization methods have been developed to a vast variety of complex problems in the field of process systems engineering (e.g., the scheduling of chemical batch processes). However, the use of these methods in online scheduling is hindered by the stochastic nature of the processes and prohibitively long solution times when optimized over long time horizons. The following questions are raised: When to trigger a rescheduling, how much computing resources to allocate, what optimization strategy to use, and how far ahead to schedule? We propose an approach where a reinforcement learning agent is trained to make the first two decisions (i.e., rescheduling timing and computing time allocation). Using neuroevolution of augmenting topologies (NEAT) as the reinforcement learning algorithm, the approach yields, on average, better closed-loop solutions than conventional rescheduling methods on three out of four studied routing problems. We also reflect on expanding the agent’s decision-making to all four decisions.

CA-NEAT: Evolved Compositional Pattern Producing Networks for Cellular Automata Morphogenesis and Replication

Cellular Automata (CA) are a remarkable example of morphogenetic system, where cells grow and self-organize through local interactions. CA have been used as abstractions of biological development and artificial life. Such systems have been able to show properties that are often desirable but difficult to achieve in engineered systems, e.g., morphogenesis and replication of regular patterns without any form of centralized coordination. However, cellular systems are hard to program (i.e., evolve) and control, especially when the number of cell states and neighborhood increase. In this paper, we propose a new principle of morphogenesis based on compositional pattern producing networks (CPPNs), an abstraction of development that has been able to produce complex structural motifs without local interactions. CPPNs are used as CA genotypes and evolved with a neuroevolution of augmenting topologies (NEATs) algorithm. This allows complexification of genomes throughout evolution with phenotypes emerging from self-organization through development based on local interactions. In this paper, the problems of 2-D pattern morphogenesis and replication are investigated. Results show that CA-NEAT is an appropriate means of approaching cellular systems engineering, especially for future applications where natural levels of complexity are targeted. We argue that CA-NEAT could provide a valuable mapping for morphogenetic systems, beyond CA systems, where development through local interactions is desired.

Watershed management using neuroevolution

Neuroevolution refers to evolving neural networks using evolutionary methods. These algorithms have been applied to many problem domains, from game playing to robotics, which motivates this research. The problem of watershed management is addressed here in this research using the most prominent neuroevolution algorithms, i.e. NeuroEvolution of Augmenting Topologies (NEAT), neuro differential evolution and Enforced SubPopulations . The results indicate that neuroevolution is a suitable approach at addressing the watershed management problem, outperforming the other methods of neural network training.

Control structure for a car-like robot using artificial neural networks and genetic algorithms

The idea of improving human’s life quality by making life more comfortable and easy is nowadays possible using current technologies and techniques to solve complex daily problems. The presented idea in this work proposes a control strategy for autonomous robotic systems, specifically car-like robots. The main objective of this work is the development of a reactive navigation controller by means of obstacles avoidance and position control to reach a desired position in an unknown environment. This research goal was achieved by the integration of potential fields and neuroevolution controllers. The neuro-evolutionary controller was designed using the (NEAT) algorithm “Neuroevolution of Augmented Topologies” and trained using a designed training environment. The methodology used allowed the vehicle to reach a certain level of autonomy, obtaining a stable controller that includes kinematic and dynamic considerations. The obtained results showed significant improvements compared to the comparison work.

Playing SNES Games With NeuroEvolution of Augmenting Topologies

Teaching a computer to play video games has generally been seen as a reasonable benchmark for developing new AI techniques. In recent years, extensive research has been completed to develop reinforcement learning (RL) algorithms to play various Atari 2600 games, resulting in new applications of algorithms such as Deep Q-Learning or Policy Gradient that outperform humans. However, games from Super Nintendo Entertainment System (SNES) are far more complicated than Atari 2600 games as many of these state-of-the-art algorithms still struggle to perform on this platform. In this paper, we present a new platform to research algorithms on SNES games and investigate NeuroEvolution of Augmenting Topologies (NEAT) as a possible approach to develop algorithms that outperform humans in SNES games.

Combining NeuroEvolution and Principal Component Analysis to trade in the financial markets

When investing in the financial market, determining a trading signal that can fulfill the financial performance demands of an investor is a difficult task and a very popular research topic in the financial investment area. This paper presents an approach combining the principal component analysis (PCA) with the NeuroEvolution of Augmenting Topologies (NEAT) to generate a trading signal capable of achieving high returns and daily profits with low associated risk. The proposed approach is tested with real daily data from four financial markets of different sectors and with very different characteristics. Three different fitness functions are considered in the NEAT algorithm and the most robust results are produced by a fitness function that measures the mean daily profit obtained by the generated trading signal. The results achieved show that this approach outperforms the Buy and Hold (B&H) strategy in the markets tested (in the S&P 500 index this system achieves a rate of return of 18.89% while the B&H achieves 15.71% and in the Brent Crude futures contract this system achieves a rate of return of 37.91% while the B&H achieves −9.94%). Furthermore, it’s concluded that the PCA method is vital for the good performance of the proposed approach.

ESTIMATION OF HEIGHT OF EUCALYPTUS TREES WITH NEUROEVOLUTION OF AUGMENTING TOPOLOGIES (NEAT)

ABSTRACT The aim of this study was to evaluate the method of neuroevolution of augmenting topologies (NEAT) to adjust the weights and the topology of artificial neural networks (ANNs) in the estimation of tree height in a clonal population of eucalyptus, and compare with estimates obtained by a hypsometric regression model. To estimate the total tree height (Ht), the RNAs and the regression model, we used as variables a diameter of 1.3 m height (dbh) and the dominant height (Hd). The RNAs were adjusted and applied to the computer system NeuroForest, varying the size of the initial population (the genetic algorithm parameter) and the density of initial connections. Estimates of the total height of the trees obtained with the use of RNA and the regression model were evaluated based on the correlation coefficient, the percentage of errors scatter plot, the percentage frequency histogram of percentage errors, and the root mean square error (root mean square error - RMSE). Various settings which resulted in superior statistics to the hypsometric regression model were found. Connections had the highest correlation and the lowest RMSE% with a population size value of 300 and an initial density of 0.1 RNA. The NEAT methodology proved effective in estimating the height of trees in clonal population of eucalyptus.

Estimation of the influence of spiking neural network parameters on classification accuracy using a genetic algorithm

Spiking neural network learning is closely connected to the plasticity mechanism chosen. The aim of this work is to assess, for a network of Leaky Integrate-and-Fire neurons with Spike-Timing-Dependent Plasticity, the influence of STDP constants and input encoding parameters on the accuracy of solving the simple model task of Fisher’s Iris classification. Parameter adjustment is performed with a genetic algorithm (GA) on base of NeuroEvolution of Augmenting Topologies (NEAT). The results of the GA with different fitness functions are compared to randomly generating the network parameters. The use of GA is shown to be able to persistently select the network parameters that achieve the highest accuracy for the configuration considered. The network is shown to be more sensitive to its input encoding parameters (encoding rates), than to plasticity constants.

Agent-based evacuation modeling with multiple exits using NeuroEvolution of Augmenting Topologies

Evacuation modeling offers challenging research topics to solve problems related to the development of emergency planning strategies. In this paper, we built an agent-based evacuation simulation model to study the pedestrian dynamics and learning process by applying the NeuroEvolution of Augmenting Topologies (NEAT) which is a powerful method to evolve artificial neural networks (ANNs) through genetic algorithms (GAs). The NEAT method strengthens the analogy between GAs and biological evolution by both optimizing and complexifying the solutions simultaneously. We set our main goal to develop a model by identifying the most appropriate fitness function for the agents that can learn how to change and improve their behaviors in a simulation environment such as moving towards the visible targets, producing efficient locomotion, communicating with each other, and avoiding obstacles while reaching targets. The fitness function we chose captured the learning process effectively and our NEAT-based implementation evolved suitable structures for the ANNs autonomously. According to our experiments and observations in the simulated environment, the agents accomplished their tasks successfully and found their ways to the exits.

NEAT-FLEX: Predicting the conformational flexibility of amino acids using neuroevolution of augmenting topologies.

The development of computational methods to accurately model three-dimensional protein structures from sequences of amino acid residues is becoming increasingly important to the structural biology field. This paper addresses the challenge of predicting the tertiary structure of a given amino acid sequence, which has been reported to belong to the NP-Complete class of problems. We present a new method, namely NEAT-FLEX, based on NeuroEvolution of Augmenting Topologies (NEAT) to extract structural features from (ABS) proteins that are determined experimentally. The proposed method manipulates structural information from the Protein Data Bank (PDB) and predicts the conformational flexibility (FLEX) of residues of a target amino acid sequence. This information may be used in three-dimensional structure prediction approaches as a way to reduce the conformational search space. The proposed method was tested with 24 different amino acid sequences. Evolving neural networks were compared against a traditional error back-propagation algorithm; results show that the proposed method is a powerful way to extract and represent structural information from protein molecules that are determined experimentally.

Artificial evolution using neuroevolution of augmenting topologies (NEAT) for kinetics study in diverse viscous mediums

This paper proposes a novel approach for the evolution of artificial creatures which moves in a 3D virtual environment based on the neuroevolution of augmenting topologies (NEAT) algorithm. The NEAT algorithm is used to evolve neural networks that observe the virtual environment and respond to it, by controlling the muscle force of the creature. The genetic algorithm is used to emerge the architecture of creature based on the distance metrics for fitness evaluation. The damaged morphologies of creature are elaborated, and a crossover algorithm is used to control it. Creatures with similar morphological traits are grouped into the same species to limit the complexity of the search space. The motion of virtual creature having 2–3 limbs is recorded at three different angles to check their performance in different types of viscous mediums. The qualitative demonstration of motion of virtual creature represents that improved swimming of virtual creatures is achieved in simulating mediums with viscous drag 1–10 arbitrary unit.

Spectrum-Diverse Neuroevolution With Unified Neural Models.

Learning algorithms are being increasingly adopted in various applications. However, further expansion will require methods that work more automatically. To enable this level of automation, a more powerful solution representation is needed. However, by increasing the representation complexity, a second problem arises. The search space becomes huge, and therefore, an associated scalable and efficient searching algorithm is also required. To solve both the problems, first a powerful representation is proposed that unifies most of the neural networks features from the literature into one representation. Second, a new diversity preserving method called spectrum diversity is created based on the new concept of chromosome spectrum that creates a spectrum out of the characteristics and frequency of alleles in a chromosome. The combination of spectrum diversity with a unified neuron representation enables the algorithm to either surpass or equal NeuroEvolution of Augmenting Topologies on all of the five classes of problems tested. Ablation tests justify the good results, showing the importance of added new features in the unified neuron representation. Part of the success is attributed to the novelty-focused evolution and good scalability with a chromosome size provided by spectrum diversity. Thus, this paper sheds light on a new representation and diversity preserving mechanism that should impact algorithms and applications to come.

Introducing Synaptic Delays in the NEAT Algorithm to Improve Modelling in Cognitive Robotics

This paper describes and tests an approach to improve the temporal processing capabilities of the neuroevolution of augmenting topologies (NEAT) algorithm. This algorithm is quite popular within the robotics community for the production of trained neural networks without having to determine a priori their size and topology. The main drawback of the traditional NEAT algorithm is that, even though it can implement recurrent synaptic connections, which allow it to perform some time related processing tasks, its capabilities are rather limited, especially when dealing with precise time dependent phenomena. NEAT's ability to capture the underlying dynamics that correspond to complex time series still has a lot of room for improvement. To address this issue, the paper describes a new implementation of the NEAT algorithm that is able to generate artificial neural networks (ANNs) with trainable time delayed synapses in addition to its previous capacities. We show that this approach, called $$\uptau $$?-NEAT improves the behavior of the neural networks obtained when dealing with complex time related processes. Several examples are presented, both dealing with the generation of ANNs that are able to produce complex theoretical signals such as chaotic signals or real data series, as in the case of the monthly number of international airline passengers or monthly $$\hbox {CO}_{2}$$CO2 concentrations. In these examples, $$\uptau $$?-NEAT clearly improves over the traditional NEAT algorithm in these tasks. A final example of the integration of this approach within a robot cognitive mechanism is also presented, showing the clear improvements it could provide in the modeling required for many cognitive processes.