Fazah
Start free
A full month, every feature.
$0
for 30 days
Includes:
- Every feature in every plan
- Your first course, end to end
- No card required
- Cancel any time
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
The loop
Ask · Think · Create
Create.Ask.Think.Create.
Create an exam on “Intro to AI” from Week 1–14 slides.
Ask Fazah or create something from your course…Create an exam on “Intro to AI” from Week 1–14 slides.0:00
Options
Speak it in one sentence. Finding the right materials is Fazah's job.
Create an exam on “Intro to AI” from Week 1–14 slides.
Syllabus.pdf
Week 1 slides.pdf
Week 2 slides.pdf
⋯ 11 more decks
Week 14 slides.pdf
Midterm rubric.pdf
Thinking…
Searching your course
Choosing what matters“Week 1–14” → Lectures · 14 decks
Reading the 14 decks
Writing the exam questions
Checking level and answers
فزعةFazahD
✦
Courses
Materials
Students
Library
Deep Learning
Mon 9:00 AM
Create an exam on “Intro to AI” from Week 1–14 slides.
✦FAZAH · Course-grounded
✓Used 14 course files · Prepared exam setup · 26s
From your course materials
TypeQuizExamAssignment⋯
TopicIntro to AI✦
Total questionsQuickStandardDetailedComprehensiveCustom
Sources selected14 sources· of 14 filesChange
Exam of 24 questions worth 60 marks, from 14 sources.Advanced optionsGenerate exam
Using sources:Lectures · 14 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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
The loop
Review · Share
Review.Review.Share.
Create a quiz, slides, notes and an assignment from this week's materials.Working from Week 5 materials.pdf
Thinking…
Reading closely
Used 1 course file · Prepared 4 cards · 12s
QuizNeeds reviewGenerating
Self-attention and scaling
10 questions · 13 marks
Review quizEdit
SlidesNeeds reviewGenerating
Transformer architecture
12 slides
Review deckEdit
Student NotesNeeds reviewGenerating
Attention, in plain terms
6 sections
Review notesEdit
AssignmentNeeds reviewGenerating
Positional encoding
3 tasks
Review assignmentEdit
Working from Week 5 materials.pdf
Ask Fazah or create something from your course…
Options
0:00
Transcribing your voice…
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 now
StudentStatusScoreTimeliness
AHAmal H.GradedNot gradedQueued11 / 1384.6%On time
LMLina M.GradedNot gradedQueued10 / 1376.9%Submitted late
SKSami K.GradedNot gradedQueued13 / 13100%On time
NANoor A.GradedNot gradedQueued12 / 1392.3%On time
OROmar R.GradedNot gradedQueued9 / 1369.2%On time
HSHana S.GradedNot gradedQueued8 / 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 work is graded
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
The loop
Grade · Feedback
Feedback.Grade.Feedback.
Create a quiz, slides, notes and an assignment from this week's materials.Working from Week 5 materials.pdf
Thinking…
Reading closely
Used 1 course file · Prepared 4 cards · 12s
QuizNeeds reviewGenerating
Self-attention and scaling
10 questions · 13 marks
Review quizEdit
SlidesNeeds reviewGenerating
Transformer architecture
12 slides
Review deckEdit
Student NotesNeeds reviewGenerating
Attention, in plain terms
6 sections
Review notesEdit
AssignmentNeeds reviewGenerating
Positional encoding
3 tasks
Review assignmentEdit
Working from Week 5 materials.pdf
Ask Fazah or create something from your course…
Options
0:00
Transcribing your voice…
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 now
StudentStatusScoreTimeliness
AHAmal H.GradedNot gradedQueued11 / 1384.6%On time
LMLina M.GradedNot gradedQueued10 / 1376.9%Submitted late
SKSami K.GradedNot gradedQueued13 / 13100%On time
NANoor A.GradedNot gradedQueued12 / 1392.3%On time
OROmar R.GradedNot gradedQueued9 / 1369.2%On time
HSHana S.GradedNot gradedQueued8 / 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 work is graded
The shelf
Everything a course needs.
Eight kinds of artifact, drafted from your materials. Every one passes through you.
✓ ApprovedFrom Week 5 materials.pdf · p. 4
Self-attention and scaling10 questions · 13 marks
Why is the dot product scaled before the softmax?
To make training faster
✓To keep the softmax stable
To reduce the parameter count
✓ Approved
Midterm examWeeks 1–5
Variant 01Variant 02Variant 03Variant 04Variant 05Variant 06Variant 07Variant 08Variant 09Variant 10
30 safe variants · same difficulty✓ ApprovedDue: In 1 week
Positional encoding3 tasks
✓Explain why the transformer needs position information
✓Compare sinusoidal and learned encodings
Apply the encoding to a short sequence
✓ Approved
Transformer architecture12 slides
Working from Week 5 materials.pdf
✓ Approved
Attention, in plain terms6 sections
Key concepts highlighted
✓ ApprovedEvery claim cited to its page
Where does attention go wrong?12 sources
✓Vaswani et al., 2017 · the original paper
✓2025 survey of attention variants
✓Your notes · Week 5, p. 4
✓ ApprovedAgainst your rubric. You release them
Week 5 Quiz42 of 42 marked
Amal H.11/13
Sami K.13/13
Lina M.7/13
✓ Approved
Personalized feedback42 of 42
Amal11 / 13
What went wellNext step
One approval gate for all of it
Ten grounded questions, each cited to the page it came from.
One exam, thirty safe variants: one per student, same difficulty.
Tasks with rubrics and a deadline, ready to send.
A teaching deck from this week's chapter, in your voice.
The key concepts, written for the student who missed class.
Beyond your slides: sources found, read, and cited to the page.
Every submission marked against your rubric. You release the marks.
A personal note for every student: what went well, what's next.
In every courseFrom your course
From your course
to every student.
Fazah drafts. You decide.
01 / 05
01Teacher
You approve.
✓Approved
02Student
Each student gets feedback.
Amal0 / 13
What went wellNext step
03Back to you
The class comes back to you.
76%Class average88%Pass rate
↩ Reteach
Week
Time back
Class
Approved
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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 materials.pdf
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
Thinking…Mapping the concepts
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 materials.pdf
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
Thinking…Mapping the concepts
Pricing
Pick the size of your teaching week.
Every plan makes the same materials. The bigger the plan, the more of the work Fazah takes off you.
Start free
Faculty Starter
Fazah preps. You teach.
$8/month
Save $24 a year
$96 billed yearly
- 1 course
- 200 credits / mo
Includes
- Quizzes, exams & assignments
- Slides and student notes
- Live Deck
Faculty Standard
Most chosenFazah preps and grades.
$16/month
Save $48 a year
$192 billed yearly
- 3 courses
- 800 credits / mo4× Starter
Everything in Faculty Starter, plus
- 4× Starter credits
- Fazah grades for you
- Thorough mode
- Deep research
- Fazah emails your students
Faculty Plus
Fazah runs your whole term.
$40/month
Save $120 a year
$480 billed yearly
- Unlimited courses
- 2,400 credits / mo12× Starter
Everything in Faculty Standard, plus
- 12× Starter credits
- Every section you coordinate
University
Fazah runs the department.
Custom
Priced to your faculty size. Pooled credits, agreed with you.
- Unlimited teachers
- Credits: Custom
Everything in Faculty Plus, plus
- Every teacher, every course
- Pooled credits
- Admin dashboard
Free 30-day trial · No card required · Change or cancel any time
USD prices exclude sales tax.
Before you decide
Questions faculty ask.
Four answers, straight. The rest are on the pricing page.
How is Fazah different from ChatGPT?
ChatGPT is a general-purpose assistant. Fazah is built for higher education: grounded in approved course materials, designed around academic workflows, and controlled by the instructor at every step.
Can faculty start before a university-wide rollout?
Yes. Institutions can begin with a small faculty group, department, or paid pilot, measure the results, and expand when ready.
Does Fazah train public AI models on your content?
No. Uploaded institutional content is not used to train public models. Data handling, retention, and provider policies are configurable per agreement.
What happens if a plan is not the right size?
Move between plans at any time: up for a heavy term, down for a light one. You keep every file you have already made, in the format you made it in.
Bring your course. Keep your evenings.
Free 30-day trial · Arabic & English