Search Results for "deep learning ai"

Conversation as a platform (CaaP) is the future, so it's perfect that we're already offering the whole toolkits to our .NET developers using the BotSharp AI BOT Platform Builder to build a CaaP. It opens up as much learning power as possible for your own robots and precisely control every step of the AI processing pipeline. BotSharp is an open source machine learning framework for AI Bot platform builder. This project involves natural language understanding, computer vision and audio processing technologies, and aims to promote the development and application of intelligent robot assistants in information systems. ...

Thalamus is a framework for creating modular interactive characters. Its goal is to make it possible to create interactive characters out of a set of different independent modules, each of which has a designated role in the behavior of the character. Unlike most the other interactive character frameworks, there is no specific module to act as the Mind, neither as the Body. It supports and is largely based on the architecture of SAIBA/BML. Acknowledgements: GAIPS/INESC-ID: (Intelligent...

Application allowing convenient experimentation in Reinforcement Learning - a Machine Learning domain. Project goals are: - keep adding new environments and agents as simple as possible - provide a rich set of state-of-art algorithms and problems - integrate with other existing Reinforcement Learning platforms If you found this application useful please cite this work: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6643987

Full ring Texas Hold'em poker game built around an intelligent AI system. The AI uses players' betting actions to calculate a probability distribution of their hole cards and uses it to evaluate hand strength and the best possible action. Small random changes are made to mimic human behavior and make the AI less predictable. Future versions will include adaptive opponent modeling using neural networks to improve the AI's strength. The AI code can be easily adapted for input from screen scrapers.

Library for creation of artificial neural networks in C#. Library supports Hopfield nets, Kohonen nets, feedforward networks, several learning techniques (differential evolution, back propagation, quick propagation, resilient propagation etc.)

Platform supporting machine learning on different objects by different modification of the JSM method (for now). Predicates for the JSM method are written in CLIPS.Objects and modification of the JSM method have to written on one of .NET languages.