Applied Artificial Intelligence and ML & DL
Duration – 5 Days
Objectives
To enable faculty members to gain hands-on exposure to core AI/ML concepts, tools, and implementation techniques, empowering them to guide students effectively and integrate data science modules in engineering curriculum and research.
Tools & Platforms
- Python
- NumPy
- Pandas
Pre-requisites
- Basic knowledge of Python
- Interest in AI/ML and data handling
- Familiarity with math basics (like averages, graphs) is helpful
Take away
- Strong foundation in AI/ML concepts and workflows
- Hands-on experience with Python, Scikit-learn, and TensorFlow
- Ability to build and evaluate ML, DL, and NLP models
- Skills to work with real-world datasets
- Confidence to start projects and explore AI tools independently
Day 2: Machine Learning Techniques – Supervised Learning
- Linear Regression, Polynomial Regression
- Logistic Regression, K-Nearest Neighbors
- Decision Trees, Random Forests
- Overfitting, Underfitting, Cross-validation
- Hands-On:
- Model training and evaluation using Scikit-learn
- Hyperparameter tuning
Day 3: Unsupervised Learning & Advanced ML Models
- Clustering: K-Means, Hierarchical
- Dimensionality Reduction: PCA
- Advanced ML Algorithms: XGBoost, Ensemble Methods
- Hands-On:
- Building clustering models
- PCA visualization
- Comparing model performance
Day 4: Deep Learning & Neural Networks
- Introduction to Deep Learning
- Artificial Neural Networks (ANN) basics
- Activation functions, Backpropagation
- CNN for image classification
- Hands-On:
- Building ANN and CNN models using TensorFlow/Keras
- Training and evaluation using image datasets (e.g., MNIST)
Day 5: Natural Language Processing & Project Wrap-Up
- NLP Fundamentals: Tokenization, Lemmatization
- Text classification using RNN/LSTM
- Pre-trained models & Transfer Learning (BERT basics)
- Real-world case study: Computer Vision or Sentiment Analysis
- Hands-On:
- Basic NLP pipeline
- Mini project discussion and capstone planning
