ARTIFICIAL INTELLIGENCE

---

Goal:  To equip students with the knowledge and practical skills required to understand, design, and implement AI-based solutions. 

 Introduction to AI

• What is AI? History & evolution
• AI vs Machine Learning vs Deep Learning vs Data Science
• Real-world applications: Healthcare, Finance, Education, Robotics
• Ethics in AI: Bias, fairness, privacy

Python for AI

• Python basics: Variables, loops, functions
• Data structures: List, Dict, Tuple
• Numpy & Pandas introduction
• Jupyter Notebooks
• Matplotlib & Seaborn for visualizations

 Linear Algebra

• Vectors, matrices
• Dot product & matrix multiplication
• Eigenvalues & eigenvectors (intuitive explanation)

Calculus & Statistics

• Derivatives, gradients
• Cost functions
• Mean, median, variance
• Probability basics
• Distributions
• Correlation & covariance

 Data Preprocessing

• Data cleaning: Handling missing data
• Normalization & standardization
• Train-test split
• Feature engineering
• Encoding categorical data

 Supervised Learning (Regression) 

• Linear Regression
• Polynomial Regression
• Evaluation metrics: MAE, MSE, R²

 Supervised Learning (Classification) 

• Logistic Regression
• KNN
• Naive Bayes
• Decision Trees
• Random Forest

 Unsupervised Learning 

• K-Means
• Hierarchical Clustering
• PCA for dimensionality reduction

 Introduction to Neural Networks

• Neuron model
• Activation functions
• Forward and backward propagation
• Gradient descent

 Deep Learning Frameworks

• TensorFlow basics
• Keras sequential models
• Hyperparameters: learning rate, epochs, batch size

 Convolutional Neural Networks (CNNs) 

• Filters, kernels, pooling
• Famous architectures: LeNet, AlexNet, ResNet
• Transfer Learning

 Recurrent Neural Networks (RNNs)

• Sequential data
• RNN, LSTM, GRU
• Time series forecasting

 NLP Basics 

• Tokenization
• Stemming & Lemmatization
• Bag-of-Words
• TF-IDF
• Word embeddings (Word2Vec, GloVe)

 Modern NLP with Transformers

• Attention mechanism
• Transformer architecture
• BERT, GPT basics
• Fine-tuning language models

  Computer Vision 

• Object detection (YOLO)
• Image segmentation
• Face recognition basics

 Robotics & AI

• Path planning
• Reinforcement Learning (Intro)
• Simulation environments (OpenAI Gym)

 Generative AI 

• GANs: Generator + Discriminator
• Image generation
• Deepfakes (Ethics discussion)

• Model evaluation & monitoring
• Saving and loading models
• Flask/FastAPI deployment
• Cloud deployment basics (AWS/GCP)
• Streamlit for AI apps

• Practical
• Interview Preparation