Understanding Supervised Machine Learning

Unsupervised Machine Learning and Reinforcement Learning Data Manipulation for Machine Learning Exploratory Data Analysis for Machine Learning Essential Mathematics for Machine Learning and AI

Definition of Generative AI

Generative AI Applications

Definition of LLMs

Regression Supervised Machine Learning Linear Regression

Decision Tree Regressor Random Forest Regressor Overfitting

Underfitting and Regularization

Classification Supervised Machine Learning Logistic Regression Decision Tree Classifier

Random Forest Classifier

Unsupervised Machine Learning KMeans Clustering Hierarchical Clustering Dimensionality Reduction Anomaly detection

Understanding Reinforcement learning: Basic concepts(Action

reward

process)

MPD

RL

DRL

DQN

etc.

MLOps for Machine Learning model deployment

Exploring Deep Learning

Understanding Neural Networks with TensorFlow

Deep dive into Neural Networks with TensorFlow

Artificial Neural Networks (ANN)

Convolutional Neural Networks (CNN)

Object detection using YOLO framework

Transfer Learning in CNN Recurrent Neural Networks (RNN) and LSTMs

Architechtures of RNN - One to One

Many to Many

Many to One etc

Understanding Text for NLP

Tokenization

Stemming and Lemmatization

Stopwords and Keywords in NLP

Text Vectorization using TF-IDF

Bag of Words and Word 2 Vec Use cases across domains in NLP

How Generative AI works

Text generation Image generation Audio generation and video generation

Using Hugging face to access models for text generation

image generation GANs

Types of GANs - ProGAN

SRGan

CycleGAN

Auto Encoders

Variational Auto Encoders (VAEs)

Diffusion Models

Definition of LLMs

LLM Use Cases

Prompt Tuning

Attention Mechanism

Transformer Model and architecture Encoder-Decoder arrangements

Train and Generate text using Encoder-decoder Architecture

BERT for Transfer learning Leveraging multiple pretrained LLMs from Hugging Face

Fine tuning LLMs

Prompting Techniques

Introduction to Prompt Engineering Successful and Unsuccessful prompts Types of Prompting Introduction to Open AI

GPT

Open AI Playground Cost & latency considerations when calling APIs (OpenAI

Azure

AWS)

Multimodal prompting for GPT 4 Image generation using Open AI DALLE 3 Prompt evaluation Implementing Agents and Chains Implementing zero-shot-react

conversational-react agents with LangChain

Open AI Function (Tool Integration) Testing various LLMs with Prompt Engineering

Introduction to Synthetic Data

Generating Synthetic Data

Synthetic Data for LLMs

Real-world Applications and Use Cases

Hands-on generating and using Synthetic Data

Understanding AI Embeddings

Advanced Retrieval Techniques

Hugging Face Embeddings

Vector Databases in AI CRUD operations with Vector Databases RAG - Retreival Augmented Generation

RAG solutions using Open AI models and Hugging face models Ethical Considerations in AI Embeddings

Navigating AI Hallucinations

Drift

and Bias

Embeddings in Real-world Applications

Embeddings Optimization and Fine-tuning

Embeddings Security and Privacy

LLM Ops and model deployment best practices

Agents

Agentic AI and Multi-Agent Systems

Agent Definition & Autonomy

Simple vs. Knowledge-Based Agents

Reflex vs. Goal-Driven Agents

Microsoft AutoGen

Agent Architecture (Perception

Decision

Action)

Integrating Knowledge Bases (RAG

Domain Data)

Measuring Performance (Success Rate

Resource Usage)

Hierarchical Agent Planning

Multi-Step Reasoning with LLM

Memory & Long-Term Context

Integrating Retrieval Augmentation in Agent Workflows

Domain-Specific Knowledge & Dynamic Prompting

Cloud Ecosystems

Introduction to Cloud Ecosystem

Definitions

Cloud characteristics

Deployment models

Leading Service providers (AWS

Google

Azure

etc.)

Comparing AWS

Azure

and GCP core services for compute

storage

and AI/ML

Data Centres and their components

Service (SaaS

IaaS

PaaS)

Issues & Challenges

Understanding hypervisors Reference model Virtualisation characteristics Principles of hypervisor design interfaces

Types of hypervisors (type-1 and type-2) Differences between Type-1 and Type-2 hypervisors

Design methods of hypervisors (full virtualization

para virtualization

and hardware-assisted virtualization)

Memory Virtualisation I/O virtualisation OS virtualization Comparative Analysis of hypervisors Understanding performance

requirements

and bottleneck

Understanding LLM Deployment Architectures

Containerizing LLM Inference Services (e.g.

using FastAPI + Docker)

Managing GPU Workloads in Kubernetes

Scaling LLM APIs with Kubernetes and Istio

Optimizing Latency and Throughput for LLM Containers

Secure Access and Rate Limiting for AI APIs

CI/CD for LLM-Powered Microservices

Monitoring and Logging for LLM Containers

Model Versioning and Rollbacks

Cost Optimization Strategies for LLM Inference in Production

Infrastructure security: Network-level security Host-level security

Application-level security Data security and storage: Data privacy and security issues Jurisdictional issues raised by data location Identity and access management Access control

IAM

Key Management Services

and zero-trust architecture trust

reputation

risk authentication in cloud computing

Client access in the cloud Cloud contracting model Commercial and business considerations

EC2 Deep Dive and AMIs

EBS vs S3 vs EFS – Storage Solutions

Load Balancing and Auto Scaling Basics

Intro to Serverless: AWS Lambda

Using AWS Bedrock for GenAI (including foundation models)

Deploying Open-Source LLMs on EC2/EKS

Fine-Tuning and Inference Pipelines on Cloud

Cost & Performance Considerations for LLM Workloads

SageMaker Pipelines for Model Training and Inference

Model Versioning

A/B Testing

and Rollbacks

Security and Compliance for GenAI in Production