Artificial Intelligence (AI) Professional Training in Amritsar

Definition and Scope of AI
History and Evolution of AI
Applications of AI in Real Life
Types of AI: Narrow, General, Super
Weak AI vs Strong AI
AI vs Machine Learning vs Deep Learning
Symbolic AI and Classical Approaches
Intelligent Agents
Turing Test and Rational Agents
Ethics and Social Implications of AI

Introduction to Python Programming
Data Types, Variables, and Operators
Control Structures and Loops
Functions and Lambda Expressions
Lists, Tuples, Dictionaries, Sets
File Handling in Python
Exception Handling
Modules and Packages
Object Oriented Programming
Introduction to Virtual Environments

Introduction to NumPy and Its Importance
Creating and Working with ndarrays
Array Indexing, Slicing, and Iteration
Array Operations
Mathematical and Statistical Functions
Reshaping, Stacking, and Splitting Arrays
Linear Algebra Operations (Dot Product, Matrix Inversion, Determinants)
Random Module – Generating Random Numbers
Vectorization for Performance Optimization
Real-world Examples: Image Representation, Computation Tasks

Introduction to Pandas: Series and DataFrames
Importing and Exporting Data (CSV, Excel, JSON)
Indexing, Slicing, and Subsetting Data
Data Cleaning: Handling Missing Values, Duplicates, Outliers
Data Transformation: Apply, Map, Lambda Functions
Filtering and Conditional Selection
Merging, Joining, and Concatenating DataFrames
Grouping and Aggregation (GroupBy)
Pivot Tables and Crosstabs
Time Series Handling
Basic Descriptive Statistics and EDA

Introduction to Data Visualization and Matplotlib
Basic Plots: Line, Bar, Scatter, Histogram, Pie
Customizing Plots: Titles, Labels, Legends, Colors, Styles
Multiple Plots and Subplots
Working with Figures and Axes Objects
Annotations and Texts
Plot Styling and Themes
Saving Figures in Various Formats
3D Plotting (Optional: mpl_toolkits)
Integrating Matplotlib with NumPy and Pandas

Linear Algebra Basics (Vectors, Matrices)
Matrix Multiplication & Inversion
Calculus Basics (Derivatives & Integrals)
Partial Derivatives and Chain Rule
Probability and Statistics
Descriptive vs Inferential Statistics
Mean, Variance, Standard Deviation
Bayes’ Theorem
Gradient and Gradient Descent
Eigenvalues and Eigenvectors

Understanding Structured and Unstructured Data
Data Collection Methods
Data Cleaning and Imputation
Feature Engineering
Feature Scaling (Normalization, Standardization)
Handling Missing and Outlier Values
Encoding Categorical Variables
Data Splitting: Train/Test/Validation
Data Visualization for EDA
Data Pipelines and Automation

Machine Learning Introduction
Feature Extraction
Fine Tuning Hyperparameters
Semi-Supervised
Gradient descent
Overfitting and Underfitting
Learning Curves and Model Diagnostics
Regression
GoogleColab

Introduction to Supervised Learning
Linear Regression
Logistic Regression
Decision Trees
Support Vector Machines (SVM)
K-Nearest Neighbors (KNN)
Naive Bayes Classifier
Random Forests
Gradient Boosting Machines (XGBoost, LightGBM)

Introduction to Unsupervised Learning
K-Means Clustering
Hierarchical Clustering
DBSCAN
Principal Component Analysis (PCA)
t-SNE for Dimensionality Reduction
Anomaly Detection
Association Rule Mining
Recommendation Systems
Evaluation of Clustering

Basics of RL and Agents
Environment and Reward System
Markov Decision Process (MDP)
Q-Learning
Deep Q-Networks (DQN)
Policy Gradient Methods
Actor-Critic Models
Exploration vs Exploitation
OpenAI Gym Environments
Real-life Applications of RL

Introduction to Scikit-learn and Its Core Components
Data Preparation and Preprocessing
Building Supervised Learning Models
Implementing Unsupervised Learning Techniques
Evaluating Model Performance
Improving Models with Validation and Tuning
Automating Workflows with Pipelines
Saving and Loading Models for Reuse
Hands-on Mini Projects

Introduction to Deep Learning
Difference between Machine Learning and Deep Learning
Biological Inspiration: Neurons and the Human Brain
Artificial Neural Networks (ANNs)
Structure of a Neural Network (Input, Hidden, Output Layers)
Activation Functions (Sigmoid, ReLU, Tanh, Softmax)
Forward Propagation and Backpropagation
Loss Functions and Optimization
Gradient Descent and Learning Rate
Overfitting, Underfitting, and Regularization Techniques

Building Neural Networks from Scratch (NumPy)
Introduction to Deep Learning Frameworks (TensorFlow & PyTorch)
Creating and Training Models in TensorFlow
Creating and Training Models in PyTorch
Hyperparameter Tuning
Model Evaluation and Metrics
Saving and Loading Models
Batch Normalization and Dropout
Early Stopping and Callbacks
Practical Implementation on Simple Datasets

Introduction to TensorFlow Ecosystem
Tensors, Variables, and Operations
Building Neural Networks with Keras API
Model Compilation, Training, and Evaluation
Callbacks (EarlyStopping, ModelCheckpoint)
TensorBoard for Visualization
Implementing CNNs, RNNs, and Transfer Learning
Hyperparameter Tuning (KerasTuner)
Saving & Loading Models (SavedModel, H5)
Hands-on Projects using TensorFlow

Introduction to PyTorch Framework
Tensors, Autograd, and Computational Graph
Building Neural Networks using nn.Module
Optimizers and Loss Functions
Training Loops and Backpropagation
GPU Acceleration (CUDA)
Implementing CNNs, RNNs, and Transformers
Using torchvision and torchtext
Model Saving, Loading, and Evaluation
Real-World Projects with PyTorch

Introduction to CV and Image Processing
Image Representation and Color Models
Image Filtering and Edge Detection
Object Detection (Haar, HOG)
CNNs for Image Classification
Image Augmentation Techniques
Face Detection and Recognition
Transfer Learning with CNNs
Image Segmentation
OCR (Optical Character Recognition)

Convolutional Neural Networks (CNNs) – Theory and Architecture
Applications of CNNs (Image Classification, Object Detection)
Recurrent Neural Networks (RNNs)
Long Short-Term Memory (LSTM) and GRU Networks
Autoencoders and Variational Autoencoders (VAEs)
Generative Adversarial Networks (GANs)
Transfer Learning and Pretrained Models
Attention Mechanism
Transformers Overview
Practical Implementation with Real-World Use Cases

Introduction to NLP
NLP Pipeline and Text Preprocessing
Tokenization, Stopwords Removal, Stemming, and Lemmatization
Bag of Words and TF-IDF
Word Embeddings (Word2Vec, GloVe, FastText)
Part-of-Speech (PoS) Tagging and Named Entity Recognition (NER)
Language Models and Probability-Based NLP
Text Classification and Sentiment Analysis
Sequence-to-Sequence Models
Evaluation Metrics in NLP
Introduction to BERT
Introduction to GPT Models
Hugging Face NLP Pipelines
Modern Tokenization: BPE, WordPiece, SentencePiece
NLP Evaluation Metrics

Embedding Layers in Deep Learning
RNNs, LSTMs, and GRUs for Text Data
Encoder-Decoder Architecture
Attention Mechanism in NLP
Transformer Models (BERT, GPT, T5)
Fine-tuning Pretrained Models for NLP Tasks
Text Generation and Summarization
Machine Translation
Chatbot and Question-Answering Systems

Gradient Descent Variants (SGD, Momentum, RMSProp, Adam)
Learning Rate Scheduling
Weight Initialization Techniques
Dropout and Early Stopping
Batch Normalization and Layer Normalization
Data Augmentation as Regularization
Loss Function Selection (MSE, Cross-Entropy, Huber, etc.)
Dealing with Overfitting and Underfitting
Practical Tips for Training Stability
Tuning and Debugging Deep Models

What is Artificial Intelligence?
What is Generative AI?
Generative vs Discriminative Models
Attention Mechanism
Transformer Architecture
Encoder, Decoder, and Encoder-Decoder Models
Autoencoders and Variational Autoencoders (VAEs)
Latent Space Representations
Generative Adversarial Networks (GANs)
Diffusion Models (Stable Diffusion concepts)
Evolution of Generative Models over Time

What is Prompt Engineering?
Components of an Effective Prompt
Zero-Shot, One-Shot, Few-Shot Prompting
Chain-of-Thought (CoT) Prompting
Role Prompting and Contextual Prompting
ReAct: Reasoning + Acting
Retrieval-Augmented Prompting
Self-Consistency Prompting
Tree of Thought (ToT) Prompting
Guardrails, Safety Prompts, and Fail-safe Design
Prompt Injection and Defense Strategies
Designing Prompts for Code, Reasoning, and Creativity

What is an LLM?
LLM Architecture
Attention and Multi-Head Attention
Token Embeddings, Positional Embeddings
LLM Parameters and Scaling Laws
Popular LLM Architectures: GPT, Claude, LLaMA, Gemini
LoRA, QLoRA, and PEFT Techniques
RLHF: Reinforcement Learning from Human Feedback
LLM Distillation
Evaluation of LLM Outputs
Using LLM APIs (OpenAI, Hugging Face, Gemini)
Understanding Context Length and Window Limitations

Concept of RAG in AI Systems
When and Why to Use RAG
RAG Architecture and Workflow
Embeddings for Retrieval
Vector Databases Overview
Document Splitting and Chunking
Query Engines and Retriever Types
RAG with LangChain
RAG with LangGraph
Multimodal RAG (text → image/video)
Evaluation of RAG Systems
Optimizing RAG for Latency and Accuracy

What is Agentic AI?
Traditional AI Pipelines vs Agentic Systems
Agent Architecture (planner, memory, executor)
Types of Memory (episodic, long-term, summarization)
Action Execution with External Tools
Multi-Agent Collaboration
Agent-to-Agent Communication Patterns
Model Context Protocol (MCP)
Popular Agent Frameworks
Designing Safe and Stable Agent Behavior

Introduction to CrewAI
Crew Roles and Task Distribution
Tool Usage in CrewAI
Creating Custom Tools
Memory in CrewAI (short-term, long-term)
Embeddings inside Crew Framework
Knowledge Systems in CrewAI
Planning, Reasoning, and Delegation
CrewAI CLI for Automation
CrewAI Flow for Workflow Design
Case Study: Fraud Detection Using CrewAI
Building Multi-Agent Teams for Real Use-Cases

Introduction to Modern GenAI Frameworks
LangChain: Prompts, Chains, Agents & Memory
Retrieval-Augmented Generation (RAG) Pipelines
Vector DB Integration: FAISS, Pinecone, Chroma
LangGraph: Nodes, State & Multi-Agent Orchestration
Workflow Guardrails, Error Handling & State Machines
LangFlow: No-Code Visual RAG & Agent Design
LlamaIndex: Index Types, Contexts & Query Engines
Advanced RAG Techniques (Fusion, Re-Ranking, Hybrid Search)
Hands-On: Build a Production-Ready Multi-Agent RAG System

Introduction to OpenAI Function Calling (GPT-4 & Tools API)
Designing structured functions for tool usage
JSON schema, argument parsing, function routing
Comparison: LangChain Tools vs. OpenAI Tools vs. ReAct
Calling APIs like weather, calculator, search with LLM
Multi-function invocation
Tool selection strategies and error handling
Introduction to OpenAI Assistants API
Using tools within context and chaining multiple calls
Common tool-using LLM applications: Retrieval, Execution, Summarization

Overview of reasoning strategies in LLMs
ReAct (Reasoning + Acting) pattern
Plan-and-Execute architecture (LangChain, Meta's implementation)
Task decomposition with LLMs
Using LLMs for planning tasks (To-do lists, workflows, subtasks)
Handling intermediate outputs, tool feedback
Agent decision flow: IF-THEN conditions, tool selection, fallback logic
Integrating external APIs and knowledge bases
Multi-agent orchestration and communication
Limitations of LLM-based reasoning (hallucinations, context loss)

Bias in AI and Generative Models
Dataset Bias Mitigation and Fairness Metrics
Explainable AI (XAI) and Model Transparency
Data Privacy, Protection, and Secure AI Practices
Global AI Governance and Compliance (EU AI Act, India, Worldwide)
Adversarial Attacks, Deepfakes, and Synthetic Media Risks
Prompt Injection & Jailbreak Attacks in LLMs
Safety Protocols, Red-Teaming, and Risk Assessment
Responsible AI Frameworks and Ethical Deployment
Ongoing Monitoring, Auditing, and Human Oversight

Evaluation Metrics for Classification & Regression
Confusion Matrix, ROC-AUC, Precision-Recall & F1-Score Analysis
Cross-Validation Techniques and Model Generalization
Bias–Variance Tradeoff and Error Diagnostics
Hyperparameter Tuning (Grid, Random, Bayesian Search)
Handling Imbalanced Data (SMOTE, Class Weights, Resampling)
Model Comparison, Benchmarking & Ensemble-Based Selection
Experiment Tracking (MLflow, Weights & Biases)
Model Interpretability and Trustworthiness
Reproducibility, Documentation & Model Testing Best Practices

Model Serialization and Packaging (Pickle, Joblib, SavedModel)
Building REST APIs with Flask and FastAPI
Deploying Interactive Apps using Streamlit and Gradio
Containerization and Deployment with Docker
Cloud Deployment Strategies (AWS, GCP, Azure)
Agent Lifecycle and Agentic RAG Deployment (LlamaIndex, LangChain)
Workflow Automation using n8n for ML/GenAI Pipelines
CI/CD for Model and Agent Deployments
Monitoring, Logging, and Observability (LangSmith, PromptLayer)
Model/Agent Versioning, Rollbacks, Safety, and Human-in-the-Loop Oversight

Defining Project Objectives and Success Criteria
Problem Formulation for ML, DL, GenAI, and Agentic Systems
Data Collection, Cleaning, Labeling, and Knowledge Base Preparation
Model Selection (ML, Deep Learning, LLMs, RAG, Agents)
Training, Fine-Tuning, Prompt Engineering & Optimization
Evaluation and Metrics for Predictive, Generative & Agentic Tasks
Deployment Strategy (APIs, Apps, RAG Pipelines, Agentic Workflows)
Feedback Loop, Monitoring, and Continuous Improvement
Documentation, Reporting, and Experiment Tracking
End-to-End Case Study Development (ML → DL → GenAI → Agents)