Questions tagged [evolutionary-algorithms]

For questions about algorithms that exhibit characteristics of evolution in that the structure, form, or processes of that which is evolving incrementally improves, either by DNA mutation and selection, symbiosis, or other operations that can produce improvement.

Filter by
Sorted by
Tagged with
2
votes
0answers
18 views

How to calculate multiobjective optimization cost for ordinary problems?

What I did: Created a population of 2D legged robots in a simulated environment. Found the best motor rotation values to make the robots move rightward, using an objective function with Differential ...
5
votes
1answer
75 views

Why evolutionary training of neural networks is not popular?

Evolutionary algorithms are mentioned in some sources as possible to be used to train a neural network (finding weights, not hyperparameters), however I have not heard about one practical application ...
-3
votes
1answer
71 views

Easy way to create Strong AI [closed]

If you have a hard time researching artificial intelligence filled with fog. just by increasing computational power of computer and running evolutionary algorithm, you can get an Strong AI ...
-3
votes
3answers
222 views

Evolutionary neural architecture?

I'm working on an idea for an AI architecture, and would like to know if there are any apparent flaws, or if there is prior work in this vein. Set I/O so that the neural network can read and write ...
3
votes
0answers
62 views

Why isn't the evolutionary Turing machine mainstream?

Given that recurrent neural networks are equivalent to a Turing machine, then why isn't the evolutionary Turing machine, e.g. described in the paper Evolution of evolution: Self-constructing ...
0
votes
0answers
19 views

Is there a rule-of-thumb to determine which behaviours must be learned in a lifetime and which innate?

I was training an AI to learn things during its lifetime such as find food and navigate a maze. Behaviors that might change during its lifetime. But I hit upon a snag. Some behaviors, like avoiding ...
1
vote
0answers
37 views

How can I solve the linkage problem in genetic algorithms?

In a genetic algorithm, the order of the genes on a chromosome can have a significant effect on the performance (capacity to generate adaptation) of the genetic algorithm, where two or more genes ...
2
votes
1answer
66 views

Can we automate the choice of the hyper-parameters of the evolutionary algorithms?

Certain hyper-parameters (e.g. the size of the offspring generation or the definition of the fitness function) and the design (e.g. how the mutation is performed) of evolutionary algorithms usually ...
2
votes
2answers
96 views

Is there any research work that attempts to combine neuroevolution with deep reinforcement learning

Neuroevolution can be used to evolve a network's architecture (and weights, of course). Deep reinforcement learning, on the other hand, has been proven to be extremely powerful at optimising the ...
0
votes
0answers
55 views

Exploding population size in neat-python

I am trying to make my AI win the board game "Catan" against my friends. Therefore i am using the python implementation of NEAT. As I changed the values of ...
1
vote
0answers
27 views

What qualifies as 'fitness' for a genetic algorithm that minimizes an error function?

Suppose I have a set of data that I want to apply a segmented regression to, fitting linearly across the breakpoint. I aim to find the offsets and slopes of either line and the position of the ...
2
votes
1answer
299 views

Can we evolve 0 and 1?

Is it possible to combine or create conditional statements of 0 and 1, and optimize with an evolutionary algorithm (given that all computers use a binary system)? There may be an algorithm that maps ...
2
votes
2answers
56 views

How to reduce amount of species in NEAT?

I am using the following library: https://github.com/vishnugh/evo-NEAT which seems to be a pretty simple NEAT-implementation. Therefore I am using the following Config: ...
0
votes
0answers
31 views

How do I choose an appropriate fitness function and hyper-parameters to train a 7-DOF arm?

I am trying to train an ANN to control a 7 Degrees-Of-Freedom arm. It should reach a target avoiding a single obstacle. Given my modeling of the situation, my input layer is composed of 12 nodes: 5 ...
2
votes
0answers
12 views

Shortest route GA: One loop through one dataset vs multiple loops through subsets of the same data?

I've a rather simple question for a school project. We're developing a GA solution for the following problem: Chromosome: A location with lat-lon coords. There are two types of locations - up to 15 ...
1
vote
1answer
52 views

Is there a reason evolutionary algorithms are language-bound in research material?

I've been working on genetic algorithms & evolutionary strategies for a while now in a research context. Across the vast majority of the articles and content I've read, every single one of them ...
5
votes
3answers
247 views

Can neural networks evolve other neural networks?

Can neural networks change or evolve other neural networks? Also, could evolutionary algorithms be applied to evolve neural networks? For example, suppose that we have neural networks A and B. The ...
1
vote
1answer
48 views

How can I calculate the shortest route between two 2d vector points with obstacles?

I have a 2D plane, with a fixed height and width of 10M. The plane has a robot in the point (1,2.2), and an electric outlet in the point (8.2, 9.1). The plane has a series of obstacles like polygons ...
3
votes
1answer
46 views

How accurate are neuroevolution algorithms in modelling organism evolution?

How accurate are neuro-evolution algorithms (such as NEAT) in modelling real organism evolution?
2
votes
0answers
35 views

Can neuroevolution be used for solving tasks other than games?

I'm seeing a lot of examples of neuroevolution techniques involving games or robot problems. Can neuroevolution be used for solving tasks other than games? For example, how could you transform a CSV ...
0
votes
1answer
24 views

How to shape the weights or nodes during gradient training of neural network? Training with constraints?

Gradient training changes indiscriminately all the weights and nodes of the neural network. But one can imagine the situations when the training should be shaped, e.g.: One can put constraints on ...
4
votes
3answers
412 views

How to design an AI that discovers more complex concepts on its own?

How would I go about designing a (relatively) simple AI that discovers and invents random more complex concepts on its own? For example, say I had a robot car. It doesn't know it's a car. It has ...
2
votes
1answer
85 views

Can NEAT produce neural networks where inputs are directly connected to outputs?

Can NEAT produce neural networks where inputs are directly (without intermediate hidden neurons) connected to outputs?
6
votes
3answers
566 views

How to create a good fitness function?

In genetic algorithms, a function called "fitness" (or "evaluation") function is used to determine the "fitness" of the chromosomes. Creating a good fitness function is one of the challenging tasks in ...
2
votes
1answer
58 views

How can a genetic algorithm adapt and get better in a changing environment?

I've just started studying genetic algorithms and I'm not able to understand why a genetic algorithm can improve if, at each learning, the 'world' that the population encounters change. For example, ...
4
votes
4answers
1k views

What is the difference between “mutation” and “crossover”?

In the context of evolutionary computation, in particular genetic algorithms, there are two stochastic operations "mutation" and "crossover". What are the differences between them?
1
vote
1answer
215 views

How Swarm Intelligence can empower Blockchain?

Are there examples of applications in blockchain consensus using swarm intelligence, as opposed to classical consensus mechanisms like PoW or PBFT? Please note that recent classical consensuses, ...
1
vote
1answer
92 views

Some RL algorithms (especially policy gradients) initialize with random policies, which often manifests as random jitter on spot for a long time?

I am reviewing a statement on the website for ES regarding structured exploration. https://blog.openai.com/evolution-strategies/ Structured exploration. Some RL algorithms (especially policy ...
1
vote
0answers
703 views

NEAT + Keras : reproducibility problem (World Models implementation)

I'm trying to apply the World Models architecture to the Sonic game (using the gym-retro library). My problem concerns the evolutionnary algorithm part that I use as the controller (worldmodels = ...
1
vote
1answer
48 views

What is the difference between the study of Evolutionary algorithm vs. Optimization?

I have a course named "Evolutionary Algorithm". But, our teacher is always mentioning the word "Optimization" in his lectures. I am confused. Is he actually teaching Optimization? If yes, why is the ...
6
votes
2answers
128 views

Evolving network in game

So I wrote simple feed forward neural network that plays tic-tac-toe: 9 neurons in input layers: 1 - my sign, -1 - opponent's sign, 0 - empty; 9 neurons in hidden layer: value calculated using Relu; ...
5
votes
2answers
342 views

More effective way to improve the heuristics of an AI… evolution or testing between thousands of pre-determined sets of heuristics?

I'm making a Connect Four game where my engine uses Minimax with Alpha-Beta pruning to search. Since Alpha-Beta pruning is much more effective when it looks at the best moves first (since then it can ...
9
votes
3answers
514 views

Is human-like intelligence the smart objective?

It appears to always have been the focus in the literature to approximate components of the human mind, assuming it to be the most advanced. If other animals came into the AI landscape, it was only ...
2
votes
1answer
408 views

What is the order of the genetic operations in NEAT?

I was trying to implement NEAT, but I got stuck at the speciating of my clients/genomes. What I got so far is: the distance function implemented, each genome can mutate nodes/connections, two ...
3
votes
4answers
760 views

AI applications of the Fibonacci series

I have been looking at Fibonacci series, the golden ratio and its uses in nature, like how flowers and animals grow based on the series. I was wondering whether we could use the Fibonacci series and ...
3
votes
1answer
73 views

Is there a way to predict points on a map?

I have a data set with historical information of some events (let's say event A and event B),these events describe the discovery of land mines, the coordinates of the event and the date of the event; ...
1
vote
0answers
34 views

Crossover in differential evolution for separable and non-separable functions

This article "Enhancing Differential Evolution Utilizing Eigenvector-Based Crossover Operator" said for a non-separable function traditional crossover algorithm are not suitable and they can not ...
1
vote
4answers
885 views

How to evaluate a NEAT neural network?

I'm trying to write my own implementation of NEAT and I'm stuck on the network evaluate function, which calculates the output of the network. NEAT as you may know contains a group of neural networks ...
4
votes
1answer
2k views

Several questions regarding the NEAT algorithm

I've recently read the paper Evolving Neural Networks through Augmenting Topologies which introduces NEAT. I am now trying to prototype it myself in JavaScript. However, I stumbled across a few ...
2
votes
2answers
286 views

What's the difference in between biological evolution and artificial evolution?

I am trying to understand the difference between the workings biological evolution and artificial evolution. If we look at it in terms of genetics, in both of them, selection is the key term, natural ...
2
votes
1answer
531 views

How are connection weights “perturbed”?

I am reading through the NEAT paper here. On page 14 of the PDF, there is this quote about mutation: There was an 80% chance of a genome having its connection weights mutated, in which case each ...
5
votes
2answers
586 views

Does NEAT require only connection genes to be marked with a global innovation number?

Does NEAT require only connection genes to be marked with a global innovation number? From the NEAT paper Whenever a new gene appears (through structural mutation), a global innovation number is ...
1
vote
0answers
81 views

Novelty Search Mutation Algorithm

I have been reading a lot lately about some very promising work coming out of Uber's AI Labs using mutation algorithms enhanced with NOVELTY SEARCH to evolve deep neural nets. https://www.arxiv-...
3
votes
2answers
84 views

Can the first emergence of consciousness in evolution be replicated in AI?

At some point in time during the evolution, because of some factors, some beings first started to become conscious of themselves and their surroundings. That conscious experience is beyond some mere ...
1
vote
0answers
17 views

ES- Modify sigma before mutate object parameters

I'm reading the book Introduction to Evolutionary Computing and on the chapter about Evolution Strategies said that we have to modify the strategy parameter sigma (standard deviation or mutation step ...
3
votes
1answer
485 views

How do I write a good evaluation function?

I'm currently writing an Alpha-Beta-Pruning algorithm for a board game. Now I need to come up with a good evaluation function. The game is a bit like snakes and ladders (you have to finish the race ...
1
vote
0answers
47 views

Mini (local) NN for Mobile?

I'm working on architecture for a game AI where, due to the nature of the game, the classical approach seems likely be sufficient to beat most humans--the endgame is tractable and traditional game-...
0
votes
1answer
690 views

Does fitness proportionate selection select multiple individuals?

Does fitness proportionate selection select multiple individuals? So i read on Wikipedia and on multiple stack exchange threads about fitness proportionate selection or rather roulette selection but ...
2
votes
3answers
259 views

Do genetic algorithms evolve?

After witnessing the rise of deep learning as automatic feature/pattern recognition over classic machine learning techniques, I had an insight that the more you automate at each level, the better the ...
2
votes
1answer
391 views

How can one use Genetic Algorithms to solve the “15 Puzzle” (Mystic Square)?

How would one go about solving the 15 squares puzzle using a Genetic Algorithms approach? In particular, I'd like to understand how you would represent the "chromosome" in the evolving system. That ...