Vitalii Bilokon @NewgroundAI

We believe that the next big thing in AI will be related to the bio-inspired evolutionary algorithms. #Neuroevolution Algorithms. newgroundadvancedresearch.com Seattle, WA Joined October 2009

Tweets

26
Followers

1K
Following

3K
Likes

1K

Vitalii Bilokon @NewgroundAI

6 years ago

If memories aren’t stored in synaptic connections, where are they stored instead? They might reside in the nucleus of the neuron cell, where DNA and RNA sequences compose instructions for life processes. nautil.us/blog/memories-…

1 9 15 0 1

View Details

Vitalii Bilokon @NewgroundAI

6 years ago

In this article we present the results of our research related to the study of correlations between specific visual stimulation and the elicited brain's electro-physiological response collected by EEG sensors from a group of participants - cutt.ly/eyjUiLe

0 4 2 0 0

View Details

Vitalii Bilokon @NewgroundAI

6 years ago

Our new research interests include #GeneticAlgorithms/#neuroevolution, synthetic cognitive systems and cooperative robotics amazon.com/dp/B082J28SZ7/…

0 2 2 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

In this work we have tested two approaches to perform fitness function optimization with #NEAT algorithm: novelty search and objective-based. The novelty search optimization was found as outperforming method for solving of deceptive tasks when strong local optima present.

1 1 11 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

Our experiment demonstrates that #NoveltySearch based optimization able to avoid deceptive strong local optima introduced in hard maze and produce effective solver agents in less than 300 #generations over the same ten trial executions.

0 1 7 0 1

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

In this experiment evaluated the performance of maze agent controlled by ANN which is created by #NEAT algorithm with objective-based fitnessoptimization. The mentioned optimization is based on maximizing solving agent's fitness by following its objective.

0 0 6 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

From the plot we can see that winner species produced organisms that control agents in such a way that its final destinations is evenly distributed through the maze. As a result it was possible to produce control ANN able to solve the maze.

0 1 5 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

The top plot shows final destinations of the most fit agents (fitness >= 0.8) and bottom is the rest. The fitness of agent is measured as distance from it's final position to the maze exit after 400 time steps of simulation.

0 0 2 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

There is a visualization of hard maze solving by all agents until winner is found. The initial agent position is at the bottom-left and maze exit at the top-left of the maze. The agents is color coded based on species they belong.

0 0 1 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

After 109 generations of population was found near optimal winner genome configuration able to guide maze solving agent through hard maze and approach the maze exit with spatial error of 2.5%. The artificial #NeuralNetwork produced by this genome has only 17 units (#neurons).

0 0 3 0 1

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

Applying Novelty Search optimization with #NEAT algorithm we was able to find near optimal configuration of Artificial #NeuralNetwork able to control hard maze solving agent.

1 0 0 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

The solution was found only after 16 111 agents evaluations, which is really fast compared to the error backpropagation based methods requiring hundreds of thousands evaluations to find solution in similar setup.

1 0 3 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

The top plot shows final destinations of the most fit agents (fitness >= 0.8) and bottom is the rest. The results is given for experimental run with winner genome configuration presented above. At that experiment was produced 32 species among which the most fit ones has amounted

0 0 1 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

We have visualized it by color coding agents depending on which species belongs its source organism. The fitness of agent is measured as a relative distance between it's final destination and maze exit after running simulation for particular number of time steps (400 in our setup

0 0 0 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

We have conducted series of experiments and found another optimal genome configuration with only 16 nodes which was found after 64 generations. It's interesting to examine plot with final destinations of maze solving agents controlled by ANNs generated from population of organism

0 0 1 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

During the experiment novelty search optimization resulted in growing three additional hidden units (neurons) and introducing recurrent link at one of the output neurons (#13). Introduced genome was able to solve maze and find exit with spatial error about 0.8% at the exit point.

0 0 3 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

After 281 generations was found near optimal winner genome configuration able to control maze solving agent. The #ArtificialNeuralNetwork produced by this genome has only 17 units (neurons) with three hidden neurons.

0 0 1 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

The maze solving agent has six range finder sensors, four slice radar sensors, and two effectors controlling linear and angular velocity.

0 0 0 0 0

View Details

Vitalii Bilokon @NewgroundAI

7 years ago

Reducing drop off age of population's species its possible to stimulate more optimal winner solutions generation. This can be explained by the fact that more novel species has less complexity than older ones and as a result different less complex topologies are examined.