Background woven in
The prerequisites you're missing, explained where you need them.
Private beta · AI and machine learning
Choose a topic. Scholar Quest writes lessons and research paper summaries at your level, with the background you're missing built in, sends them to your Kindle or inbox, and tracks what you've really learned.
Free during the beta. Starting with 5 to 10 readers.
Written for you: comfortable with dot products, new to transformers
Each query is compared with every key using a dot product. With 64 dimensions, those scores grow large, and softmax turns large scores into near-certain picks.
Attention(Q, K, V) = softmax(QKᵀ / √d) V
Highlight this line to mark Lesson 7 complete.
Learning a field like machine learning from papers means stopping every page to look up a term, then losing the thread. Courses are slow and generic. Summaries skip the parts you need.
Scholar Quest starts from what you know and writes the missing pieces in, so you can read the real ideas on a screen that's easy on the eyes and actually finish.
How it works
Pick a topic and take a short placement check. We note what you already know so nothing is pitched too low or too high.
Lessons and research paper summaries arrive on your Kindle, e-reader or inbox, with the background you're missing woven in.
Highlight the last line when you finish. That's the signal: your skill tree updates and the next edition is lined up.
Quick review questions bring ideas back before you forget them, and build challenges show you can use them.
What you get
The prerequisites you're missing, explained where you need them.
Crisp maths, legible figures and tables that fit the page.
Finish a book on your Kindle and the achievement unlocks itself.
Short review questions, generated from what you read, at the right intervals.
A 10-minute summary, a 30-minute overview, or a deep, annotated walkthrough.
Implement the idea yourself, checked by hidden tests.
Progress you can trust
Every skill on your path climbs the same ladder. Each rung unlocks from something you did.
We're opening the private beta to 5 to 10 people first. Starting topic: AI and machine learning.