Skip to main content
Back to All Courses
AdvancedDeep Learning & Neural Architectures Free Verifiable Certificate

Machine Learning & Deep Learning Foundations

Understand the mathematical foundations of Neural Networks, Transformers, Attention, and Fine-Tuning.

8 min of material
4 Modules (4 Lessons)
Free · no account needed to read
Access Fee
FREE100% Free Forever
Full Interactive Curriculum Access
In-Browser Prompt Studio & Code
Official Certification Exam
Verifiable PDF/PNG Certificate
Start Learning Now

The assessment unlocks once you have worked through the lessons.

Independent provider. Not an accredited awarding body. Not a regulated qualification.

What You Will Master

  • Understand forward propagation, loss functions, and gradient descent optimization
  • Deconstruct Scaled Dot-Product Attention and Multi-Head Self-Attention mathematically
  • Analyze Encoder-Only (BERT), Decoder-Only (GPT), and Encoder-Decoder (T5) architectures
  • Understand Positional Encodings (Sinusoidal, RoPE) and KV-Caching during inference
  • Compare Full Fine-Tuning against LoRA (Low-Rank Adaptation) and QLoRA

Skills Acquired

Neural Network FoundationsTransformer ArchitectureMulti-Head Attention MathRoPE & Positional EmbeddingsKV-Cache OptimizationLoRA Fine-Tuning

Prerequisites

  • Basic linear algebra (matrix multiplication, vectors)
  • High-school calculus (derivatives, chain rule)
  • Basic Python programming knowledge

Curriculum Syllabus

4 modules · 4 lessons · 8 min · one assessment

Module 1

Module 1: Neural Networks & Backpropagation

Perceptrons, activation functions (ReLU, GeLU), loss functions, and gradient descent.

Module 2

Module 2: The Transformer & Self-Attention Explained

Dissect Query, Key, Value matrices, Scaled Dot-Product, and Multi-Head Attention.

Module 3

Module 3: Positional Embeddings, RoPE & Inference Optimizations

How Transformers know word order, Rotary Position Embeddings (RoPE), and KV-Caching.

Module 4

Module 4: Parameter-Efficient Fine-Tuning (PEFT & LoRA)

Fine-tune 70B parameter models on consumer hardware using Low-Rank Adaptation (LoRA).

Course author

Md. Rajib Hawlader

Principal AI Research Scientist, NeuroLearn AI Labs

Writes and maintains the NeuroLearn AI curriculum.

Ready to Begin Machine Learning & Deep Learning Foundations?

Self-paced curriculum with free instant certificate issuance upon passing the evaluation.

Start First Lesson