JimmyVS/Math_Solver_AI

This script builds, trains, evaluates, and tests a neural network for simple arithmetic operations. It loads data from a CSV file containing arithmetic problems, preprocesses it by scaling the features, and splits it into training and testing sets.

Math Solver AI

Math Solver AI

Math Solver AI is a neural network designed to solve simple arithmetic operations. It is built using PyTorch and includes functionalities to train, evaluate, and test the model. The model can be trained on a dataset of arithmetic problems, and its performance can be evaluated on a test set. Additionally, users can input their own arithmetic problems to see the model's predictions.

Features

• Train the Model: Train the neural network on a dataset of arithmetic problems.
• Evaluate the Model: Evaluate the model's performance on a test set.
• Test Custom Inputs: Input your own arithmetic problems to see the model's predictions.
• Save and Load Checkpoints: Save the model's progress and load it later to resume training.

Requirements

• Python 3.6+
• PyTorch 1.6.0+
• pandas
• scikit-learn
• matplotlib

Usage

1. Clone the repository:

   git clone https://github.com/JimmyVS/Math_Solver_AI.git
   cd Math_Solver_AI

2. Install the required packages:

   pip install torch pandas scikit-learn matplotlib

3. Prepare your dataset as a CSV file with columns Number A, Operation, Number B, and Solution. An example dataset is provided below:

   Number A	Operation	Number B	Solution
   1	+	1	2
   2	-	1	1
   3	*	2	6
   4	/	2	2

4. Run the script:

   python math_solver.py

5. Follow the on-screen instructions to train, evaluate, or test the model.

License

This repository is under a MIT license. This repository was made by JimmyVS. Please do not claim as your's.