Parallel Reinforcement Evolutionary ANN v.1.0

Advertisement
Advertisement

Parallel Reinforcement Evolutionary Artificial Neural Networks (PREANN) is a framework of flexible multi-layer ANN's with reinforcement learning based on genetic algorithms and a parallel implementation (using XMM registers and NVIDIA's CUDA).

Parallel Reinforcement Evolutionary Artificial ...

 
  • Parallel Reinforcement Evolutionary ANN
  • 1.0
  • Jorge Timón
  • Windows
  • Freeware
  • 152
  • Free
 
 

Review Parallel Reinforcement Evolutionary ANN

  • captcha
 
 
New Science software
  • Match n Freq  v.6.573Pulse shaping filter program that finds the pole-zero locations of a transfer function, H(s), for a matched filter. H(s) equals a -desired- signal (Yout) divided by a given input signal (Yin). Y's are in freq. Another improved productivity example.
  • Photovoltaic System  v.8.12Simulate the amortization of a Photovoltaic System over 20..40 years, including Prosumer Electricity Network Trading. Fine-tune as many cost-driving, efficiency, and sales parameters as you want. See Total Amortization, RoI and Net Profit.
  • Nature Simulations  v.7.78Nature Simulations is a collection of Small Business Planners around Nature, Humans, Plants and Animals. It starts with a children's model simulating a small river from Black to Caspian Sea, at 0 m above ground. See Trees around Aral Sea, diplomacy.
  • GHC Timetables generator EN  v.19.2.86Penalara GHC is an automatic software to generate timetables for schools of different levels: primary schools, high schools, vocational schools, universities and all other academic institutions.
  • Optex Analyzer  v.1.0Optex Analyzer is a software to analyze and compare algorithms to solve approximately optimization problems. It has a GUI that allows select a set of input files containing raw algorithm results. The analysis is shown with tables and charts.
  • PhiWeave  v.1.0PhiWeave is a machine learning library for structured prediction via factor graphs. It is part of an ongoing effort to implement and improve on the current state-of-the-art in inference and parameter estimation for graphical models.