Search Results for "concept"

...Distributed performance (efficiency) is the core technical difficulty of the deep learning framework. OneFlow focuses on performance improvement and heterogeneous distributed expansion. It adheres to the core concept and architecture of static compilation and streaming parallelism and solves the memory wall challenge at the cluster level. world-leading level. Provides a variety of services from primary AI talent training to enterprise-level machine learning lifecycle integrated management (MLOps), including AI training and AI development, and supports three deployment modes of public cloud, private cloud and hybrid cloud.

TurboPilot is a self-hosted copilot clone that uses the library behind llama.cpp to run the 6 Billion Parameter Salesforce Codegen model in 4GiB of RAM. It is heavily based and inspired by on the fauxpilot project. This is a proof of concept right now rather than a stable tool. Autocompletion is quite slow in this version of the project. Feel free to play with it, but your mileage may vary.

LifeAI is an artificial intelligence system that can be applied to robotics, games, or business. It simulates key processes of our minds, such as organizing data into concepts and categories, planning actions based on their predicted outcome, and communication. LifeAI was designed to be simple, but powerful and flexible enough to have many applications.

...We’ll provide you with all the tools you need, including easy to follow guides, software samples such as TensorRT code, and even pre-trained network models including ImageNet and DetectNet examples. Follow these directions to integrate deep learning into your platform of choice and quickly develop a proof-of-concept design.

...The simulator is optimized for high-performance rendering, achieving thousands of frames per second to enable efficient large-scale training of RL agents. House3D has served as the foundation for several influential research projects such as RoomNav (for concept-based navigation) and Embodied Question Answering (EQA).

Recent progress in ubiquitous computing, ambient intelligence and Internet of Things has resulted in several prototypes of smart environments. The smart spaces concept and its open source implementation - Smart-M3 - provide methods and tools for constructing such environments. The SmartRoom project aims at development of a set of smart services to assist in conferences, meetings, lectures, and other educational/research/business events. The project applies the advanced Smart-M3 SDK and inherits the FRUCT groundwork on SmartConference and SmartScribo systems. ...

This is the Sourceforge reposository of the EU project Xperience. We work on developing a Cognitive Architecture for humanoid robots using a combination of developmental approaches and structural bootstrapping - a concept from language learning.

ARCOS (Asynchronous Reasoning with COntexts and Streams) is a software system which implements the concept of Asynchronous Multi-Context Systems, which where recently proposed as another generalisation of Multi-Context Systems and Reactive Multi-Context Systems.

Bayesline is a Bayesian Network Framework based on the Valuation Concept of Shenoy and Shafer.

This is proof-of-concept type of project with not much to look at yet. I'm checking some ideas I find interesting about neural nets and genetic algorithms.

IRC bot based on the concept of (re-)loadable user-coded Lua modules, editable by anyone, which handle all the bot's functions. The project's main goal is to create a full written-language interface with no special predefined commands.