Build and train own Neural Network from scratch to predict the number of bikeshare users on a given day.
In this project, you'll get to build a neural network from scratch to carry out a prediction problem on a real dataset! By building a neural network from the ground up, you'll have a much better understanding of gradient descent, backpropagation, and other concepts that are important to know before we move to higher-level tools such as PyTorch. You'll also get to see how to apply these networks to solve real prediction problems!
Process of project contains:
- Implement Forward Pass
- Implement Backward Pass
- Set proper Hyperparameters
The data comes from the UCI Machine Learning Database.
Waiting for results...Done!
Test Result Summary
- Produces good results when running the network on full data .
- The activation function is a sigmoid .
- The backpropagation implementation is correct .
- The forward pass implementation is correct .
- The learning_rate is reasonable .
- The number of epochs is reasonable .
- The number of hidden nodes is reasonable .
- The number of output nodes is correct .
- The run method is correct .
- The update_weights implementation is correct .
- The weights are updated correctly on training .
Congratulations! It looks like your network passed all of our tests.