Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Launch a Blind AI App on the Nillion Testnet #6

Open
oceans404 opened this issue Aug 2, 2024 · 3 comments
Open

Launch a Blind AI App on the Nillion Testnet #6

oceans404 opened this issue Aug 2, 2024 · 3 comments

Comments

@oceans404
Copy link
Member

Bounty Objective

The Nillion community wants to see more Blind AI Apps. Create and launch a Blind AI application on the Nillion Testnet and provide a live link so anyone can try it. Your Blind AI App should use at least 1 Nada program with the Nada AI library to provide predictions while ensuring data privacy.

Bounty Requirements

Create a new Bind AI App using the following workflow:

  1. Pick an Interesting Data Set:

    Choose a dataset that is suitable for your AI project. The dataset should be relevant and provide meaningful insights.

  2. Train a Plaintext Model:

    Use your preferred AI tools to train a model on the chosen dataset. Check out examples and Google Colab links in nada-ai examples. Here are the available models:

    • Multilayer Perceptron: Available layers include Linear, Conv2d, AvgPooling2d, DotProductSimilarity, ReLU, Flatten
    • Linear Regression Model: Linear model
    • Logistic Regression Model: Linear model implementation with cleartext sigmoid and potential multiclass classification
    • Prophet: Time series forecasting model
  3. Write at Least One Nada Program that utilizes the nada-ai library

    Ensure that your program integrates the trained model and is capable of making predictions.

  4. Store your AI Program on the Nillion Testnet

  5. Build a Blind App:

    Build a blind app that uses the compiled Nada program to obtain live, privacy-preserving predictions from your model.

    Ensure the app securely computes predictions without revealing sensitive data.

  6. Host this web app demo and provide a live link so we can try it

How to Submit

Review the Terms and Conditions for Nillion Builder Bounties here.

Open source your repo and submit your bounty by creating a new discussion in Nillion’s “Show and Tell” Github Discussions Forum. For project type, choose “Builder Bounty Submission”

@pbkompasz
Copy link

@oceans404 Hi, this is my submission.

@thu142857
Copy link

Hi @oceans404 , please check my submission

@tonytrandevv
Copy link

tonytrandevv commented Sep 7, 2024

HI @oceans404 , i have few small steps to submit. Do I am allowed to do that ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Under review
Development

No branches or pull requests

4 participants