Advances in Machine Learning Lab

Course Objectives:

• 1. Explore and analyze state-of-the-art machine learning approaches.
• 2. Develop practical skills in implementing advanced ML models and solving complex AI challenges.

Course Outcomes:

• CO1 Understand the latest advancements in machine learning algorithms and techniques.
• CO2 Apply advanced ML methods to real-world problems, demonstrating proficiency in using cutting-edge tools.

List of Experiments:

1. Implement a deep neural network from scratch using TensorFlow or PyTorch, gaining hands- on experience in building complex neural architectures.
2. Utilize pre-trained models and perform transfer learning to solve real-world problems efficiently.
3. Implement a GAN to generate synthetic data and explore its applications in image generation and data augmentation.
4. Apply NLP techniques to process and analyze textual data, including sentiment analysis and named entity recognition.
5. Build RL agents and train them using OpenAI Gym or Stable Baselines to solve challenging tasks.
6. Understand the interpretability of ML models by using LIME or SHAP to explain model predictions.
7. Use AutoML and Hyperparameter tuning tools to automate the model selection and optimization process.
8. Analyze time series data, perform forecasting, and evaluate model performance using Prophet or stats models.
9. Compress and quantize large ML models to make them suitable for deployment on resource- constrained devices.
10. Explore federated learning concepts and implement distributed ML models using TensorFlow Federated.
11. Generate adversarial attacks on ML models and implement defense mechanisms to enhance model robustness.
12. Utilize Ray Tune to perform hyperparameter search and optimize ML models efficiently.