Expert-written ML curriculum

Learn ML.
Actually keep it.

QuiddityML is for anyone who wants to truly understand machine learning and AI, not just passively watch videos and forget everything a week later. Whether you're a developer, student, or just AI-curious, QuiddityML takes you from zero to deep understanding through structured tracks, hands-on coding exercises, and built-in spaced repetition that makes sure what you learn actually sticks.

Download free on iOS See the curriculum →

Why QuiddityML

Zero to deep understanding.

Not just watching and forgetting. QuiddityML takes you through structured tracks, hands-on coding exercises, and built-in spaced repetition that makes sure what you learn actually sticks.

11 Types of Hands-On Exercises

Reading or watching videos is passive. QuiddityML makes you actually do the work. Progress through 4 tiers of difficulty, from recognizing concepts to implementing models from scratch, with live feedback on every answer.

Spaced Repetition Built In

QuiddityML tracks how well you know each concept and reminds you to review at exactly the right moment. No more forgetting what you learned last week.

Beginner Friendly, Research Depth

Every concept is explained with clear analogies, rich visuals, and real math. Understand gradient descent, backpropagation, attention mechanisms, and more, deeply enough to be able to read research papers and build your own models.

How a session works

Learn it. Test it. Keep it.

Every concept follows the same pattern: understand it first, get tested on it, then review it before you forget. Nothing skips ahead.

Study the concept

Each concept starts with slides: clear explanations, diagrams, equations, and worked code examples. Real depth, not bullet points. You read and understand before anything gets tested.

Diagrams & figures Math notation Worked examples Code walkthroughs

Do the exercises

After each concept, exercises push you past basic recall. Spot bugs, fill in implementations, write code from scratch. You can't just skim your way through.

11 exercise types 4 tiers of demand Real PyTorch code

Review before you forget

Spaced repetition schedules each concept based on how well you actually did, not just that you finished it. Struggled on an exercise? It comes back in a day. Nailed it? It waits weeks. Your review queue is built entirely from your own results.

Performance-driven scheduling Unique to you Daily review queue

Expert-written curriculum

The full ML stack, built to grow.

Every track is written by ML practitioners from industry and research. We cover everything from core fundamentals to the latest methods, and add new tracks regularly.

ML Foundation

The core of modern ML. Optimization, neural networks, backpropagation, and the fundamentals every ML engineer needs.

Advanced NLP

Fine-tuning, alignment, PEFT, and inference optimization. The full modern NLP stack from toy GPT to production LLM.

RL Foundation

MDPs, policy gradients, Q-learning, and modern RL algorithms. The math behind how agents learn to make decisions.

Vision & Generative Models

CNNs, diffusion models, and everything in between. Computer vision and generative modeling.

Multimodal

Vision-language models and cross-modal AI. Systems that work across text, images, and more.

Retrieval & Search

Embeddings, dense retrieval, and the infrastructure behind semantic search

Interpretability & Alignment

Mechanistic interpretability, probing, circuits, and alignment. Understanding what models actually learn inside.

Audio & Speech

Speech recognition, synthesis, and audio understanding. From spectrograms to modern audio models.

Agents & Agentic Systems

Building AI agents that plan, use tools, and take real actions in real environments.

Retrieval-Augmented Generation

How to ground language models in real knowledge. Retrieval, context injection, and evaluation.

Prompt Engineering

Few-shot, chain-of-thought, and structured prompting. Practical techniques for getting reliable output from LLMs.

AI Safety & Red Teaming

Model robustness, safety testing, and alignment under adversarial conditions.

Continual Learning

Teaching models to pick up new tasks without dropping what they already know.

Classical ML

SVMs, tree ensembles, and the fundamentals of statistical learning that still power production systems.

FAANG interview prep

Walk into your next ML interview ready.

Most courses stop at theory. QuiddityML ends every unit with real interview questions from the material you just covered. The same questions that show up at Google, Meta, Amazon, and other top ML teams.

✓ Questions tied to the exact unit you just finished, not a generic prep list
✓ Covers ML concepts, system design, coding, and common follow-up questions
✓ Tested while the material is still fresh, right after you finish the unit
✓ Every unit, every track. Not an add-on. Built in from the start.

Portfolio projects

Build something real. Put it on your CV.

After each track you work through a real project using what you just learned. Not a tutorial to follow along with. Something you actually built.

Real code you write

Not a notebook to copy-paste. You implement the thing from scratch using what you learned in the track.

Scoped to what you know

Each project is built around the track you just finished. You have all the context you need to actually complete it.

Built to show

Put it on GitHub, add it to your CV, talk about it in your next interview. Something you made, not something you watched.