This lab aims to familiarize with PyTorch library for Regression and Multi-Class Classification tasks using Deep Neural Networks (DNNs)/Multi-Layer Perceptrons (MLPs).
- Understand and visualize the dataset to gain insights.
- Implement a DNN architecture using PyTorch for regression.
- Use GridSearch from sklearn to find optimal hyperparameters.
- Plot Loss and Accuracy against Epochs for both training and test data.
- Apply various regularization techniques and compare with the initial model.
- Clean and standardize/normalize the data.
- Explore and visualize the dataset.
- Apply techniques to balance the dataset.
- Design a DNN architecture using PyTorch for multi-class classification.
- Utilize GridSearch to find optimal hyperparameters.
- Plot Loss and Accuracy against Epochs for both training and test data.
- Evaluate metrics like accuracy, sensitivity, and f1 score on training and test datasets.
- Apply various regularization techniques and compare with the initial model.
- Regression: NYSE Dataset
- Multi-Class Classification: Machine Predictive Maintenance Dataset