New customers can spin up VMs, build with AI, and query data at no cost.
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Start Free
Go from Code to Production URL in Seconds
Cloud Run deploys apps in any language instantly. Scales to zero. Pay only when code runs.
Skip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
Neural networks in CUDA & OpenCL with back propagation algorithm
This project is my engineering diploma. It's aim is to compare the efficiency of both technologies and to check where which hacks works better. What is more one of my tasks is to compare different ways of decomposing computations in parallel.
Developed as a final year project at Islamic University of Technology (IUT) during 2010 - 2011 academic year. This code is a simple implementation of real coded geneticalgorithm for numerical optimization. Code is written in C/C++.
This project aims to create an application to solve the job shop schedule problem using geneticalgorithm on the IBM Cell BE processor. This is useful especially using the power of Cell for the large scale job shop schedule problem.
The goal of the Rats and Mazes project is to build a simple geneticalgorithm to find general solutions to random non-cyclic single path mazes. I believe that the solutions will tend towards either the right/left-hand rule.
This is a very simple implementation of the geneticalgorithm framework presented by John Holland, based on Goldberg book Genetic Algorithms in Search, Optimization and Machine Learning.