Connect 4 AI Solver

Recurrent algorithms C++ and Python

I have been working on recurrent algorithms. They’re a bunch of examples in which you can implement these algorithms. However, we usually see that they are efficient.

Connect 4 is a simple game that can be easily programmed and solved to win every time. I have made in Python an AI that solves and wins. It is not programmed in C++ because I wanted a GUI.

Continue reading “Connect 4 AI Solver”

Lane Line Recognition

Lane line recognition algorithms

The Hough Transform has been broadly used in many fields, including autonomous cars. It is used to detect straight and curved lines with high accuracy.

 

This is the result of the Lane Line program I have designed to detect edges on the road.

The algorithm used, it is used to detect edges on images. Then, we discard using analytics and probability the ones which overlap each other and the less probable.

It is very efficient and can be used in parallel computing for rather good optimizations. The results are quite astonishing.

Continue reading “Lane Line Recognition”

Spacecraft Trajectory Optimization

Trajectory optimization using AI

Spacecraft mission will become more common. There are relevant open projects such that Mars colonization and exploring missions outside the Solar System.

These missions require high accuracy calculations because the error propagates in time and would be able to modify the trajectory.

There are many ways to face this problem: analytical or numerical approaches.

The analytical approaches could only be used for simplified problems, and thus it is really restrictive.

The numerical approaches commonly used and include metaheuristics and nonlinear programming. I have used genetic algorithms to solve a basic problem which consists of optimizing trajectory to travel to Mars from the Earth.

Continue reading “Spacecraft Trajectory Optimization”

Nuclear Fusion + AI

Fusion Reactor Simulations + Deep learning

Fusion power is a proposed form of power generation that would generate electricity by using heat from nuclear fusion reactions.

There are many methods to achieve the fusion: magnetic confinement, inertial confinement, electric pinches, inertial electrostatic confinement, …

magnetic confinement – tokamak

Pulsotron is a Tokamak fusion power reactor. It is an evolutionary prototype that was designed by Javier Luis López. The simulations were made using C++ and OpenGL.

Continue reading “Nuclear Fusion + AI”

CPU vs GPU | Neural Network

GPU vs CPU neural network

I have done two libraries for AI,

  • CPU with Eigen 1 2
  • GPU with CUDA 1 2

They are optimized and work properly. However, there are significant differences in performance.

The GPU library can adapt to other Nvidia graphic card and furthermore improve the time that I obtain within my circumstances. In addition, the graphics card industry is constantly improving their models and we have recently seen the clusters of the graphics card in the business.

The CPU library is stable and can work on any computer because it does not rely on Nvidia hardware, it is a completely cross-platform library that only needs Eigen library which is compatible with every OS.

I have used for the test: i7-7700k vs Nvidia GeForce GTX 1070

Continue reading “CPU vs GPU | Neural Network”