Neural Network Learning Proccess to Be Shown As Evolution
Evolution simulator clearly shows how neural network learns on the example of simplest virtual creatures evolution
10 September 2018
Keiwan Donyagard published Evolution simulator, in which the user creates a creature from bones, muscles and joints in the form of lines and dots, and the creature develops using a neural network as the brain. This is reported by The Next Web.
The creature evolves, performing the simplest actions: running, jumping and climbing up. The process clearly demonstrates the stage-by-stage learning of the neural network: it learns to analyze the distance to the ground and the number of points of contact, the direction of movement of the individual and speed, location in space and other parameters.
AI takes into account the position of the object in space, the direction of motion and speed, the distance to the ground, as well as the number of points of contact with it. During attempts, copies of the creature appear, from which the neural network chooses the two most successful ones, based on the conditions of the problem. Parameters are used to create new creatures and the loop is repeated until the task is executed correctly.
SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019
NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.
Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.
Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.
To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.