GithubHelp home page GithubHelp logo

neuralfm's Introduction

                 _   _                      _  _________  ___
                | \ | |                    | | |  ___|  \/  |
                |  \| | ___ _   _ _ __ __ _| | | |_  | .  . |
                | . ` |/ _ \ | | | '__/ _` | | |  _| | |\/| |
                | |\  |  __/ |_| | | | (_| | |_| |   | |  | |
                \_| \_/\___|\__,_|_|  \__,_|_(_)_|   \_|  |_/
                                                             
                          AI Information Radio

NeuralFM

NeuralFM's mission is to put you in control of the AI's feeding you information.

Say goodbye to factory farmed algorithms from megacorps that destroy your life. NeuralFM offers a novel solution to the biggest invisible problem: algorithm bias.

Some Google or Facebook engineer is probably going to decide the next President of the United States. It's bad enough when megacorps purposefully bias algorithms (it really is). What's shocking though, is even with small algorithms, and even when unintended, human bias infects AI. Even worse, AI are "black boxes"—many of the creators don't fully understand what's happening inside.

Neural Networks ("AI") are shaping our reality, but they're increasingly out-of-reach. AI is too powerful be left to the megacorps.

NeuralFM puts an AI in your pocket and it puts you in control. It creates an open market for the best AI for all the information channels you care about. And it puts everything on the blockchain, so you can be sure about exactly what's going into your algorithms.

Now, you might be thinking.... creating your own AI sounds pretty difficult... But it's not! In fact you'd be shocked how easy it is.

Creating an AI in NeuralFM is as simple as clicking a button. Seriously, that's it.

NerualFM is three things:

  • An information feed giving you the best information on topics you care about
  • A radio station to discover channels from the best curators
  • A neural studio, to create your own AI with a few clicks (or modify someone else's)

Try it out -> https://neural.fm

Getting Started

git clone ...

npm install

Creating Plugins

If you're a developer, you may be interested in doing more than just classification, you may be interested in adding new data sources, training on different features, normalizing in a different way, or using a different neural network.

Plugins are easy to build, they're just Javascript functions: they come in 4 types

  1. Scrapers
  2. Feature Extractors
  3. Normalizers
  4. Networks

To create a new plugin, view the existing plugins and copy it to your new plugin filename.

Replace all the metadata like description, author and paymail with your information.

Test your code locally, and when you're ready, submit it to the NeuralFM market.

You can offer your plugin for free or charge. Welcome to the NeuralFM AI Marketplace.

What are the different plugins you can build?

Scrapers

Scrapers pull in data to the system. Here's an example of a simple scraper:

Feature Extractors

Feature Extractors decide which parts of the data are important.

Normalizers

Normalizers convert those data features into a similar format.

Networks

Networks are Neural Networks, they're plug-and-play.

Author

@synfonaut

Public repo but copyright is privately held, code is currently UNLICENSED

neuralfm's People

Contributors

synfonaut avatar

Forkers

infinitegame-co

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.