Free trial
A full month, every feature.
$0
for 30 days
- Every feature
- 50 credits to try it
For Faculty
Fazah.
Create a Quiz, Send It, Give Feedback. The Same Day.
From your course files. You approve each step.
No account needed.
Create.Approve.Send.Feedback.Next class.
Week 5 slides.pptx
@Week 5 slides.pptx
Needs reviewApproved10 questions · 13 marks+28Week 5 slides.pptxEditApproveSent to 42 students
Fazah.+28YouApproveFeedback sent to 42
Question mastery · 42 students
Create a quiz on self-attention from @Week 5 slides.pptx. 10 questions · 13 marks, cited to Week 5 slides.pptx. Waiting for your approval. Personalized feedback: Amal H., 11 / 13, 1 of 42. Question mastery · 42 students: Common slip, Q7. Start next class with One worked example on positional encoding.Q1Q2Q3Q4Q5Q6Q7Q8Q9Q10Common slip
Start next class withOne worked exampleon positional encodingWhy Fazah
A general AI chat stops at a reply. Fazah finishes the teaching week.
Without Fazah
General-purpose AI
- Re-upload Files
- Copy to LMS
- Send Manually
- No Personal Feedback
Fazah.
Upload Files Once
- 1Create Quiz
- 2Send to Students
- 3Same-Day Feedback
- 4Next Class Adapts
↺ And again next week.
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
1 · Create from your files
Create from your files
Create.Ask.Create.
Create a quiz on self-attention from the Week 5 lecture slides.
Ask Fazah or create something from your course…Create a quiz on self-attention from the Week 5 lecture slides.0:00
Options
Create a quiz on self-attention from the Week 5 lecture slides.
Syllabus.pdf
Week 4 slides.pptx
Week 5 slides.pptx
Week 5 notes.pdf
Week 5 reading.pdf
Week 6 slides.pptx
Finding Week 5
Reading 3 files
Writing the quiz
FazahD
✦
Courses
Files
Students
Library
Deep Learning
Mon 9:00 AM
Create a quiz on self-attention from the Week 5 lecture slides.
✦FAZAH · Course-grounded
✓Used 3 course files · Prepared quiz setup
From your course materials
TypeQuizExamAssignment⋯
TopicSelf-attention and scaling✦
Total questionsQuickStandardDetailedComprehensiveCustom
Sources selected3 sources· of 18 filesChange
Quiz of 10 questions worth 13 marks, from 3 sources.Advanced optionsGenerate quiz
Using sources:Week 5 · 3 files
Ask Fazah or create something from your course…
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
2 · Send, grade and give feedback
Send, grade and give feedback
Feedback.Send.Grade.Feedback.
Create a quiz, slides, notes and an assignment from this week's materials.Working from Week 5 slides.pptx
Used 1 course file · Prepared 4 cards · 12s
QuizNeeds review
Self-attention and scaling
10 questions · 13 marks
Review quizEdit
SlidesNeeds review
Transformer architecture
12 slides
Review deckEdit
Student NotesNeeds review
Attention, in plain terms
6 sections
Review notesEdit
AssignmentNeeds review
Positional encoding
3 tasks
Review assignmentEdit
Working from Week 5 slides.pptx
Ask Fazah or create something from your course…
Options
0:00
Question 1 of 10
Why is the dot product scaled before the softmax?
A
B
C
D
Approve
Approved
Ready to publish
Live with students
Publish to students
View live assignment
Publish to students
CS 471 · Deep Learning · 42 students
Deadline
Tomorrow
In 3 days
In 1 weekIn 1 week
Pick a time in the future
Students
AHLMSKCourse roster+39 more
Accept late submissions
Send to 42 students
Published to students
Students in CS 471 have been emailed their private submission link.
View live assignment
FFazah for Dr. Al-Rashidnow
Self-attention and scaling
10 questions · 13 marks · Due Thu 3 Sep, 23:59
Open quizPrivate link, yours only
Self-attention and scaling42Submitted39Graded3Pending2LateGrade nowRelease 3 grades
StudentStatusScoreTimeliness
AHAmal H.ReleasedNot gradedQueuedGrading…Ready to release11 / 1384.6%On time
LMLina M.ReleasedNot gradedQueuedGrading…Ready to release10 / 1376.9%Submitted late
SKSami K.ReleasedNot gradedQueuedGrading…Ready to release13 / 13100%On time
NANoor A.ReleasedNot gradedQueuedGrading…Ready to release12 / 1392.3%On time
OROmar R.ReleasedNot gradedQueuedGrading…Ready to release9 / 1369.2%On time
HSHana S.ReleasedNot gradedQueuedGrading…Ready to release8 / 1361.5%On time
Class results
82%Class average93%Pass rate
Well understoodWhy the dot product is scaled before the softmax.
Common slipPositional encodings are added to the embeddings, not concatenated.
TryReteach positional encoding from the Week 5 notes, §3; 14 students slipped there.
Self-attention and scaling11 / 13 · 4 Sep
Overall feedback
Amal: a solid grasp of scaled attention. Positional encoding needs one more pass.
Strengths
Explained why √dₖ keeps the softmax gradients healthy.
Areas for improvement
Positional encodings are added to the embeddings, not concatenated.
Question-by-question feedback
Q1: 1/1
Correct: scaling stops the dot products from saturating the softmax.
Q7: 0/2
Misconception:Concatenating the encoding onto the embedding.
Next step:Week 5 notes, §3: Positional encoding.
Amal H. has been emailed that their grade is released
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
Assignment
Positional encoding
3 tasks
Slides
Transformer architecture
12 slides
Explained why √dₖ keeps the softmax gradients healthy.
Positional encodings are added to the embeddings, not concatenated.
×0:03
Thought for 4sCorrect: scaling stops the dot products from saturating the softmax.
Working from Week 5 slides.pptx
Create a quiz, slides, notes and an assignment from this week's materials.
Student Notes
Attention, in plain terms
6 sections
Quiz
Self-attention and scaling
10 questions · 13 marks
82%Class average93%Pass rate
Positional encodings are added to the embeddings, not concatenated.
Live with studentsCS 471 · Deep Learning · 42 students
Sources usedWeek 3 lecture notes
What you get
Three things, every week, from your course files.
Quizzes and exams from your files
Each draft shows the course file it came from.
Week 5 slides.pptx10 questionsWeek 5 notes.pdfQuizSyllabus.docxMidtermFeedback for every student
A mark and a personal note for each one, released by you.
Amal H. · 11 / 13Needs review, only youFeedback releasedReleaseWhere your class struggled
The common slips and what to try, ready for your next class.
Class results · 42 studentsCommon slipQ7, positional encodingTryOne worked example first
Your files and your students' work are never used to train AI models. Governance or procurement questions? Contact us
Pricing
Pick the size of your teaching week.
Faculty Starter
Fazah preps. You teach.
$8/month
$96 billed yearly
- 1 course
- 200 credits a month
Faculty Standard
RecommendedFazah preps and grades.
$16/month
$192 billed yearly
- 3 courses
- 800 credits a month
Faculty Plus
Every course, every cohort.
$40/month
$480 billed yearly
- Unlimited courses
- 2,400 credits a month
University
One plan for your department.
Custom
Priced to your faculty size. Pooled credits, agreed with you.
- Unlimited teachers
- Credits: Custom
Free 30-day trial · No card required · Change or cancel any time
USD prices exclude sales tax.
Before you decide
Questions faculty ask.
What if Fazah marks an answer wrong?
Every mark arrives as a draft beside the student's answer. Change any mark or comment first. Students see nothing until you release it.
How do my students get it?
Each student gets a private link by email and signs in the first time they open it. When you release marks, each student is emailed that their feedback is ready.
Does it work with Blackboard, Moodle or Canvas?
It works alongside them. Upload the files you already teach from, share work with students by link, and download quizzes and exams as Word or PDF. Fazah does not connect to your LMS.
Can students copy answers during a quiz?
Turn on Prevent copying and pasting. It blocks copy and paste, warns the student, and records each attempt and each time they leave the page.
Bring your course. Send feedback this week.
Quizzes, exams and assignments from your course files, marked with feedback for every student.
Free for 30 days. No card.