Welcome to Aqwam’s DataPredict™ Neural Library!

Commercial Use Information

Terms And Conditions Information

  • By using or possessing any copies of this library or its assets (including the icons), you agree to our Terms And Conditions.

    • Small developers and non-B2B organizations earning ≤3K USD within 365 days (not per 365 days) can use DataPredict™ for free!

    • Standard and White-Label tiers available for commercial projects.

  • For information regarding potential license violations and eligibility for a bounty reward, please refer to the Terms And Conditions Violation Bounty Reward Information.

DataPredictNeuralIconSmall

Version Current Version Number
Release 1.17
Beta 1.13.0

DataPredict™ Neural is an advanced deep learning library for Roblox and Pure Lua.

This project is created to address the lack of deep learning features and inflexibility of the API design from the DataPredict™ library.

If there are any suggestions or issues for this library, don’t be afraid to reach out to me at my Discord server, DevForum thread or my LinkedIn.

In addition, if you are interested in Roblox tutorials and future projects by me, then you can subscribe to me in YouTube.

Features

  • Take advantage of calculations combining both automatic differentiation and manual differentiation, simplifying complex calculations while maintaining high performance.

  • Take advantage of model and data parallelism capabilities as well as static computational graph for extremely fast training, prediction and experimentation.

  • Build singular models that are interconnected between servers and clients through distributed training.

  • Build models that handles multi-dimensional tensor inputs and outputs to solve any demands of your projects.

  • Dive into user-friendly API designed for you to learn in a couple of minutes.

  • Built for production-grade and research-grade applications.

  • Cross-compatible with DataPredict library.

The API

API Reference

Tutorials

Installation

The Model Basics

The Tensor Basics

The Advanced Blocks

Deep Reinforcement Learning

Repository

Version History