Module-13-Neural-Networks-Challenge

In this module, I'll explore and implement neural networks using the TensorFlow platform and Keras in Python. I’ll learn about the history of computational neurons, how neural networks apply to deep learning and what the cost and benefits of neural networks are. I will also learn how to implement neural networks across a range of datasets and how to store and retrieve trained models.

I work as a risk management associate at Alphabet Soup, a fictitious venture capital firm. The Alphabet Soup business team receives manyfunding applications from startups every day. This team has asked me to help them create a model that predicts whether applicants will become successful if funded by Alphabet Soup. The team has given me a CSV file containing more than 34,000 organizations that have received funding from Alphabet Soup over the years. This file contains various types of information about the organizations, including whether they ultimately became successful. With my knowledge of machine learning and neural networks, I decide to use the features in the provided dataset to create a binary classifier model that will predict whether an applicant will become successful.

• Prepare the Data for Use on a Neural Network Model
• Compile and Evaluate a Binary Classification Model Using a Neural Network
• Optimize the Neural Network Model

Instructions on how to use

1. Launch venture_funding_with_deep_learning.ipynb from JuypterLab to run JupyterLab version

• Run through each line of code to view the output

2. Launch Colab_venture_funding_with_deep_learning.ipynb and upload into your Google Colab:

• download the resource files in this repository to upload using the Google Colab prompts within the code

3. Load saved models from AlphabetSoup folder if desired

• three models are saved: AlphabetSoup, AlphabetSoup_A1, AlphabetSoup_A2