Every number a computer holds is digits in places: a price, a pixel, the size of an AI model. You already know how to add and subtract. This lesson is about what a number is: why the 4 in 4,072 is worth four thousand, and why it matters where a digit sits. You'll also run your first lines of Python, which is a calculator that never gets tired.
What you'll be able to do
Say what each digit of a number is worth from its place, and rebuild a number from its parts
Add with a carry, and say what the carry stands for
Run Python cells that add, subtract and print
Count the numbers inside a small picture, and read a model size like 7B
Quick check
Have a guess before you start. In 4,072, what is the 4 worth?
400
4
4,000
40
Show the answer
4,000
The 4 sits in the thousands place, so it's worth 4 thousands: 4,000. Where a digit sits decides what it's worth. That's the whole idea of this lesson.
The math: what a digit is worth
Purpose. We write every number, however big, with just ten digits: 0 to 9. The trick that makes it work is the place. The same digit is worth more the farther left it sits.
Read a number from the right. The first place counts ones. The next counts tens, then hundreds, then thousands. Each place is worth ten of the place to its right.
So 4,072 means:
thousands
hundreds
tens
ones
4
0
7
2
That's 4 thousands, 0 hundreds, 7 tens and 2 ones. The 0 matters: it holds the hundreds place open. Without it, 472 would be a different number.
The picture. Watch 4,072 come apart into what each digit is worth, then go back together. The picture gives each place a row of blocks, one block for each unit of its digit: in the thousands row each block is a thousand, in the tens row each is a ten. So 4,072 is 4 blocks, then an empty hundreds row where the 0 sits, then 7 and 2. The tens row has more blocks than the thousands row and is still worth far less: the place decides, not the count. Each step works out one row's worth; then the rows are added, one by one, into the total at the bottom.
Try it now
Each digit times its place's worth, then all of them added back. Type another whole number and press Use these numbers.
Symbols and formula. Any whole number is its digits times their places, added up:
4072=4×1000+0×100+7×10+2×1
In plain words: each digit times what its place is worth, all added together.
Big numbers get commas every three places, counting from the right, so you can read them at a glance: 1,000 is a thousand, 1,000,000 a million, 1,000,000,000 a billion.
Comparing. To see which of two whole numbers is bigger, count their digits first: more digits means bigger. With the same count, compare from the left. 4,072 beats 3,999 at the very first digit.
On a number line, numbers sit in order from left to right, each a step of 1 from the next. Bigger numbers sit farther right. Here are 3,999 and 4,072 on a stretch of the line around 4,000, with a tick every 10:
Quick check
Which number is 3 thousands, 5 tens and 8 ones?
3,508
30,058
3,058
358
Show the answer
3,058
3 thousands, 0 hundreds, 5 tens, 8 ones: 3,058. The hundreds place has nothing, so it holds a 0.
Quick check
Which is the biggest: 9,999 or 10,001 or 1,000,000 or 999,999?
1,000,000
999,999
10,001
9,999
Show the answer
1,000,000
1,000,000 has 7 digits; the others have 6, 5 and 4. More digits means a bigger whole number.
Adding in columns. Line the numbers up so that the places match: ones under ones, tens under tens. Add each column, starting from the right.
When a column adds up to 10 or more, it can't fit in one digit. You keep the ones digit and carry the ten to the next column on the left. The carry isn't a trick: it's ten of this place, which is one of the next place.
The picture. Watch 4,072 + 1,859 one column at a time, as a walk along the number line. Both numbers start on one line. Then each step zooms the line in to its column's place and adds that column of 1,859 as a jump, starting from 4,072: 9 ones, then 5 tens, 8 hundreds and 1 thousand. A jump that reaches or passes a round number of the next place up, a round ten while adding ones or a round hundred while adding tens, is a carry: ten of this place made one more of the next.
Subtracting in columns works the same way, right to left, with one twist. When the top digit is too small, you borrow: take one from the next place to the left and turn it into ten of this place.
For 52 − 38: 2 − 8 won't go, so borrow one ten from the 5. The ones become 12, and the tens become 4. Then 12 − 8 = 4 and 4 − 3 = 1, so the answer is 14. Borrowing is the carry run backward: one of a bigger place is always ten of the next place down.
In your own words
In your own words: what does a carry stand for when you add in columns?
Write a sentence or two, then compare it with a good answer in the lesson.
In Python: a calculator that never tires
Purpose. You can add two numbers in your head. A computer can add millions a second and never slips. Python is the language this course uses to tell it what to do.
Below is a cell: a small box of Python. Press Run and the answer appears underneath. Try it.
print(4072 + 1859)
print(5000 - 1862)
It runs right here in your browser, with nothing to install.
print( ) shows whatever is inside the brackets. + adds and - subtracts. Write numbers without commas: to Python, a comma separates two things, so 4,072 would be two numbers, 4 and 72.
Python's sign for times is a star, *. (The next lesson is all about multiplying.) That's enough to rebuild a number from its places:
# what each digit of 4072 is worthprint(4 * 1000, 0 * 100, 7 * 10, 2 * 1)
# all of them added back upprint(4 * 1000 + 0 * 100 + 7 * 10 + 2 * 1)
The lines that start with # are comments: notes for people. Python skips everything after a #.
Code flow. Now run the rebuild one line at a time. The first line prints what each digit is worth. Each line after it adds one more place to the sum, biggest place first: the thousands, then the hundreds, the tens and the ones, the way the blocks above filled their total. Press Next and watch the output grow by one line per step.
Worked example
Worked example: checking a column sum
You added 2,786 + 1,457 by hand and got 4,243. Check it, and check each carry, with a few lines of Python.
# the whole sumprint(2786 + 1457)
# the ones column: 6 + 7 is 13, so write 3 and carry 1print(6 + 7)
# the tens column, with the carry: 8 + 5 + 1print(8 + 5 + 1)
# the hundreds column, with the carry: 7 + 4 + 1print(7 + 4 + 1)
In the lesson you can change this and run it.
The first line checks the answer: 4243, which matches. The other lines check the work column by column. 13, 14 and 12 are each more than 9, so each one sends a carry left. That's three carries, which is why this sum is easy to get wrong by hand. Checking one column at a time like this is how you find exactly where a hand calculation slipped.
Quick check
What does this print?
print(300 + 40 + 7)
# print(1000)print(5000 - 1)
347
1000
4999
347 4999
300 + 40 + 7
5000 - 1
347
4999
Show the answer
347
4999
The middle line is a comment, so Python skips it. Each print shows one answer on its own line: 347, then 4999.
Quick check
Someone types print(4,072 + 1). What goes wrong?
Python prints 4,073 with a comma
Python reads 4 and 072 + 1 as two separate things
Python adds 1 to 4,072 and prints 4073
Python ignores the comma
Show the answer
Python reads 4 and 072 + 1 as two separate things
In Python a comma separates things. Write numbers without commas: 4072. (Here Python even refuses the 072 part, because a number can't start with 0.)
Drill
Fix three cells
Each line should print the number shown in its comment, but each has one slip. Fix all three.
print(4 * 100 + 7 * 10) # should print 4070print(1,000 + 500) # should print 1500print(2000 - 75 + 75 - 25) # should print 2000
In the lesson, your code is checked as you write it.
In your own words
Why can't you write 1,000 with a comma in Python?
Write a sentence or two, then compare it with a good answer in the lesson.
In AI and ML: everything is numbers
Purpose. An AI model can only work with numbers. Pictures, words and sounds all have to become numbers first. Here is how the trail club's sign reader sees a picture.
The map is the whole course in one picture, and most of its names are for later lessons. For now, only the lit one matters: everything a model does starts from numbers.
A trail sign is a tiny picture, 5 squares tall and 5 wide. Each square is a pixel. In black and white, each pixel is a number: 1 for ink, 0 for blank. Below is the tent sign, first as you see it, then as the model gets it. Press Next to swap the picture for its numbers, and again to count the ink in each row.
To the model, that sign is just those 25 numbers. Count the pixels with a multiply:
pixels=height×width
In plain words: the number of pixels is the rows times the columns.
# a 5 by 5 trail signprint(5 * 5)
# a 28 by 28 picture, the size of a classic handwritten-digit imageprint(28 * 28)
# the ink pixels in the tent sign above, row by rowprint(1 + 2 + 2 + 2 + 5)
A gray picture uses a whole number from 0 (black) to 255 (white) for each pixel, so place value is back: a pixel of 200 is 2 hundreds, 0 tens, 0 ones.
In the real tools. Most models are built with PyTorch, a Python library. It keeps a picture's numbers in a tensor: a grid of numbers that knows its own shape. Here is the tent sign going in:
Words become numbers too. A language model has a fixed list of word pieces, and each piece gets a whole number: its id, its place in the list. "tent" might be piece 4,318. A sentence reaches the model as a row of ids, never as letters.
And the model itself is numbers. Its parameters are the numbers it learned in training. Sizes are written with a letter for the place: K for thousand, M for million and B for billion. A "7B" model learned seven billion numbers.
Quick check
What does this print?
print(28 * 28)
print(5 * 5 + 5 * 5)
784
50
2828
55
784
25
56
50
Show the answer
784
50
A 28 by 28 picture has 28 × 28 = 784 pixels. Two 5 by 5 signs have 25 + 25 = 50.
Quick check
A model is described as having "7B parameters". What does 7B mean?
7 million numbers
7 billion numbers it learned
7 thousand numbers
Version 7 of the model
Show the answer
7 billion numbers it learned
B is short for billion: 7,000,000,000. A model's parameters are the numbers it learned in training, and big models have billions of them.
Drill
Count the numbers in a picture
Print three lines: the number of pixels in a 64 by 64 picture, in a 100 by 200 picture, and how many more the second has than the first.
print(64 + 64)
print(100 + 200)
print(0)
In the lesson, your code is checked as you write it.
In your own words
How does a model 'see' a trail sign?
Write a sentence or two, then compare it with a good answer in the lesson.
31Formulas with fractions: clear them firstFreeClearing denominators, cross-multiplying, a letter in the bottom, and reciprocal formulas like 1/R = 1/R₁ + 1/R₂.35 min
37Inverse functions, lines and scalingFreeUndoing a function by making x the subject, domains that allow it, line forms, and unscaling predictions.40 min
38Sequences and sums: find n, a, d and rFreeEvery letter of the arithmetic and geometric formulas as the subject, and an average's window from its decay.40 min
40Review: rearrange anything (algebra)FreeBroken rearrangements to fix, mixed practice from the whole algebra block, a strategy chart, and its formula sheet.35 min
41Coordinates and distanceFreePoints as (x, y), Pythagoras, distance in any number of coordinates, and nearest neighbors.42 min
42Angles, degrees and radiansFreeMeasuring a turn, converting units, arcs, and the angle between two arrows.36 min
43Sine and cosineFreeAcross and up: right triangles, the unit circle, and directions and rotations.42 min
44Waves: height, speed and shiftFreeAmplitude, period and phase, sampling a wave, and position codes in transformers.37 min
68Vector equations: rearranging with arrowsFreeSolving for a vector or a scale, recovering a gradient from two weight snapshots, and an angle from a dot product.40 min
87Counting: choices, orders and groupsFreeThe counting principle, factorials, ordered picks and groups, and why attention's cost grows with the square of the length.43 min
88Probability: from counts to chancesFreeEqually likely outcomes, the complement, distributions, seeded simulation, and a next-word model.43 min
89Combining events: and, or, independentFreeThe or rule, independence, probability trees, drawing with and without replacement, and chains of steps.42 min
100Maximum likelihoodFreeLikelihoods as products, log-likelihoods as sums, grid search, underflow, and the negative log-likelihood loss.45 min
101Linear regression: the best lineFreeResiduals, least squares by formula, three roads to one line, the matrix form, and train versus test error.45 min
109One neuron, start to finishFreeWeighted sum, activation, loss, slopes and update, by hand and in code, and what one straight line can and can't split.45 min
111Training a small networkFreeThe backward pass in matrix form, gradient checks, a full training loop, and reading loss curves.45 min
112The same network in PyTorchFreenn.Sequential with the NumPy weights loaded, the same loss and slopes, then SGD and mini-batches.45 min
113Attention as matrix mathFreeScaled dot-product scores, the causal mask, a row-by-row softmax, and blending value vectors.45 min
114Residual connections and layer normFreeAdding the input back and why its slope keeps learning alive, layer norm by hand, and add and norm.40 min
115A transformer block, start to finishFreeA sentence through embeddings, attention, add and norm, a small network and next-word scores, every shape named.45 min
117Final test: transpose any formulaFreeSlips to fix from every topic, mixed practice of every kind of rearranging, the strategy chart and the full sheet.45 min
Learn the math behind AI from arithmetic up: numbers, algebra, vectors and matrices, calculus, probability and statistics, each shown as numbers moving and checked in Python, ending with a network you build and train from the formulas.
See the course →
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write