Advances in Data Science Lab

List of Experiments:

1. To implement and train deep learning models (e.g., CNN, RNN) on real-world datasets for various applications.
2. To perform text classification tasks using NLP techniques and compare different algorithms for accuracy and efficiency.
3. To process large-scale datasets using Spark's distributed computing capabilities and run machine learning algorithms on them.
4. To build and train GAN models for generating realistic images and evaluate the quality of the generated samples.
5. To implement and train sequence-to-sequence models for language translation tasks using attention mechanisms.
6. To apply various anomaly detection techniques on time series data and evaluate their effectiveness.
7. To assess and mitigate bias in machine learning models using fairness indicators and AIF360.
8. To interpret and explain the predictions of complex machine learning models using LIME and SHAP techniques.
9. To design and train reinforcement learning agents to play games and achieve high scores.
10. To apply differential privacy techniques to protect sensitive information while performing data analysis.