Using Deep Learning #57 (Model-Simple feed-forward neural network)

[ranamanish674zu]

I used deep learning (simple feed forward neural network) on the given datasest, but due to small size of dataset or something else model gone overfitted(training accuracy-100 %, testing accuracy-69%, Overfitting occurs when your model learns the training data too well, capturing noise and details that do not generalize to new, unseen data ) , so to resolve it i used Regularization(regularization techniques like L2 regularization (weight decay) to the model) , Dropout(Introduce dropout layers to the model to randomly set a fraction of input units to 0 at each update during training time, which helps prevent overfitting) , Early Stopping(Use early stopping to halt training when the validation loss stops improving) for balanced the training and testing accuracy. So after applying this i get training accuracy-above 80 % and testing accuracy-75%. after this i save the model into deeplearning.pkl file, if we developers want use this model then they can use by importing this file in the code. that's i solved issue #57

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
diabetes-prediction	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jun 1, 2024 7:39pm

[BamaCharanChhandogi]

Thank you for submitting your pull request! 🙌 We'll review it as soon as possible. In the meantime, please ensure that your changes align with our CONTRIBUTING.md. If there are any specific instructions or feedback regarding your PR, we'll provide them here. Thanks again for your contribution! 😊

[BamaCharanChhandogi]

I will look at this PR later.

[BamaCharanChhandogi]

Can you create a separate file for deep learning, because we do not need deep learning as of now? I want to keep separate this