What will I learn in the Artificial Intelligence & Machine Learning Engineering course?

From Python data foundations to cutting-edge GenAI: NumPy & Pandas dataframes, Supervised/Unsupervised Learning with Scikit-learn, Neural Networks & Deep Learning with PyTorch, LLM APIs, Vector Embeddings, Vector Databases (pgvector, Pinecone), and Retrieval-Augmented Generation (RAG). Skills gained include: NumPy Vectorized Computing & Pandas Data Wrangling, Deep Learning Architectures & PyTorch Tensors, Large Language Models (LLM) Prompt Engineering & APIs, Vector Embeddings & Semantic Cosine Similarity Search, Production Retrieval-Augmented Generation (RAG) Systems.

What are the prerequisites for Artificial Intelligence & Machine Learning Engineering?

Prerequisites: Python Fundamentals, Basic Linear Algebra.

IntermediateAI & Machine Learning

~32 Hours 16 Lessons100% Free

Artificial Intelligence & Machine Learning Engineering

Q: Is the Artificial Intelligence & Machine Learning Engineering course free?

Yes, all 16 modules and 16 lessons in Artificial Intelligence & Machine Learning Engineering are 100% free with interactive code playgrounds on KWAS Academy.

Neural networks, PyTorch, Large Language Models (LLMs), Embeddings, and RAG Architecture.

From Python data foundations to cutting-edge GenAI: NumPy & Pandas dataframes, Supervised/Unsupervised Learning with Scikit-learn, Neural Networks & Deep Learning with PyTorch, LLM APIs, Vector Embeddings, Vector Databases (pgvector, Pinecone), and Retrieval-Augmented Generation (RAG).

What You Will Learn

NumPy Vectorized Computing & Pandas Data Wrangling
Deep Learning Architectures & PyTorch Tensors
Large Language Models (LLM) Prompt Engineering & APIs
Vector Embeddings & Semantic Cosine Similarity Search
Production Retrieval-Augmented Generation (RAG) Systems

Prerequisites & Environment

Python Fundamentals
Basic Linear Algebra

Complete Course Curriculum (16 Modules)

16 In-Depth Lessons

Module 01

Module 1: AI & Machine Learning Foundations

1 Lessons

AI vs ML vs Deep Learning vs GenAI, datasets, training/test splits, and loss functions.

1.1AI & Machine Learning Foundations

16m →

Module 02

Module 2: Python Data Science Stack (NumPy & Pandas)

1 Lessons

NumPy vectorized n-dimensional arrays, matrix math, Pandas DataFrames, filtering, and aggregation.

2.1Vectorized Computing with NumPy & Pandas DataFrames

18m →

Module 03

Module 3: Data Visualization & Exploratory Analysis

1 Lessons

Matplotlib plotting, Seaborn statistical heatmaps, feature correlations, and outlier detection.

3.1Exploratory Data Analysis (EDA) & Visualization

16m →

Module 04

Module 4: Supervised Learning (Regression & Classification)

1 Lessons

Linear Regression, Logistic Regression, Decision Trees, Random Forests, and Scikit-learn.

4.1Supervised Learning: Regression, Classification & Random Forests

20m →

Module 05

Module 5: Unsupervised Learning & Clustering

1 Lessons

K-Means clustering, Principal Component Analysis (PCA) dimensionality reduction, and anomaly detection.

5.1K-Means Clustering & Dimensionality Reduction (PCA)

18m →

Module 06

Module 6: Neural Networks & Deep Learning Basics

1 Lessons

Artificial neurons, Perceptrons, activation functions (ReLU, Sigmoid), forward pass, and backpropagation.

6.1Artificial Neurons, Activation Functions & Backpropagation

22m →

Module 07

Module 7: Deep Learning with PyTorch

1 Lessons

PyTorch Tensors, GPU acceleration (CUDA), torch.nn.Module, loss functions, and Adam optimizer.

7.1PyTorch Tensors, Autograd & Building nn.Module Networks

22m →

Module 08

Module 8: Natural Language Processing & Transformers

1 Lessons

Tokenization, self-attention mechanism, transformer architecture (Encoder/Decoder), and BERT vs GPT.

8.1The Transformer Architecture & Self-Attention Mechanism

24m →

Module 09

Module 9: Large Language Models (LLMs) & Prompt Engineering

1 Lessons

Autoregressive text generation, temperature, top-p sampling, Few-Shot prompting, and Chain-of-Thought (CoT).

9.1LLM APIs, Sampling Parameters & Prompt Engineering

20m →

Module 10

Module 10: Vector Embeddings & Vector Databases (pgvector, Pinecone)

1 Lessons

Dense vector representations, cosine distance vs dot product, pgvector PostgreSQL extension, and HNSW indexes.

10.1Vector Embeddings & Vector Databases (pgvector)

22m →

Module 11

Module 11: Retrieval-Augmented Generation (RAG) Architecture

1 Lessons

Document ingestion pipelines, chunking strategies, semantic retrieval, context re-ranking, and hallucination reduction.

11.1Production Retrieval-Augmented Generation (RAG) Systems

24m →

Module 12

Module 12: Transformer Architecture: FlashAttention, RoPE & MQA

1 Lessons

Master cutting-edge Transformer architecture: FlashAttention-2 IO-awareness, Rotary Position Embeddings (RoPE), and Grouped-Query Attention (GQA).

12.1Transformer Architecture: FlashAttention & RoPE

28m →

Module 13

Module 13: LLM Quantization & Parameter-Efficient Fine-Tuning

1 Lessons

Master LLM compression and fine-tuning: GPTQ, AWQ, 4-bit NormalFloat (NF4), LoRA (Low-Rank Adaptation), and QLoRA.

13.1LLM Compression: Quantization (GPTQ, AWQ) & QLoRA

28m →

Module 14

Module 14: Vector Databases: HNSW & IVF-PQ Indexing

1 Lessons

Master vector search engine internals: Hierarchical Navigable Small World (HNSW), Inverted File Product Quantization (IVF-PQ), and cosine similarity.

14.1Vector Database Internals: HNSW & IVF-PQ Indexing

28m →

Module 15

Module 15: Agentic AI Systems: Tool Calling, ReAct & Multi-Agent Swarms

1 Lessons

Master autonomous Agentic AI: JSON Schema Tool Calling, ReAct (Reason + Act) loops, Plan-and-Solve, and Multi-Agent collaborative swarms.

15.1Agentic AI: Tool Calling, ReAct & Multi-Agent Swarms

28m →

Module 16

Module 16: High-Throughput LLM Serving: vLLM & PagedAttention

1 Lessons

Master high-throughput LLM deployment: vLLM inference engine, PagedAttention virtual memory, Continuous Batching, and Speculative Decoding.

16.1LLM Serving: vLLM, PagedAttention & Speculative Decoding

28m →