**XENTORCH** _{Neural Networks Simplified}

## Introduction

The main goal of XenTorch module is to save time making neural networks in Studio, simplify the process, thus expanding the opportunity for more neural network projects on Roblox. This module is capable of creating and training fully connected architectures.

## Current Capabilities

*Note: Check marks indicate completed features, crosses indicate features which are being worked on.*

Build network according to given parameters (layer info and functions)

Linear Layers

Convolutional Layers

Biases

Activation Functions

Back Propagation: Normal/Stochastic Gradient Descent

Genetic Algorithm :

Recurrent Algorithm

Save/Load Network

**Current Activation and Cost Functions:**

ReLU

ReLU Derivative

Sigmoid

Sigmoid Derivative

Softmax

Softmax Derivative (Partial Support)

Mean Squared Error

Mean Squared Error Derivative

## Module

https://www.roblox.com/library/6784448015/XenTorch

## API

https://davoidd.github.io/XenTorch/

Please don’t hesitate to reply to this post with feedback, suggestions, or bugs!