Search Results for "artificial"

eANN is an implementation of several kind of neural networks written with the intention of providing a (hopefully) easy to use, and easy to modify, OOP source code. It is possible to have several different sized networks running simultaneously, each functioning independently of the others or acting as inputs between them. It also easy to modify the structure so that neurons (or even whole layers) can be created/pruned during simulation allowing dynamic expansion/contraction of the network.

This project is dedicated to developing a simulation of the financial market using multi-agent approach. This kind of simulation is often called an Artificial Stock Market (ASM).

A suite of machine learning benchmarks where each agent must solve a lot of different tasks without recompilation. This means that the programmers cannot manually specify topologies or adjust parameters to specific tasks.