Index Ai Academy
Foundation · Numbers

Numbers and place value

What a digit's place is worth, the number line, and Python as a calculator that never tires.

About 36 minutes · Free lesson

What it covers6

Why it matters

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?
  1. 400
  2. 4
  3. 4,000
  4. 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:

thousandshundredstensones
4072

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+2×14072 = 4 \times 1000 + 0 \times 100 + 7 \times 10 + 2 \times 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?
  1. 3,508
  2. 30,058
  3. 3,058
  4. 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. 1,000,000
  2. 999,999
  3. 10,001
  4. 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 worth
print(4 * 1000, 0 * 100, 7 * 10, 2 * 1)
# all of them added back up
print(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 sum
print(2786 + 1457)
# the ones column: 6 + 7 is 13, so write 3 and carry 1
print(6 + 7)
# the tens column, with the carry: 8 + 5 + 1
print(8 + 5 + 1)
# the hundreds column, with the carry: 7 + 4 + 1
print(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)
  1. 347 1000 4999
  2. 347 4999
  3. 300 + 40 + 7 5000 - 1
  4. 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?
  1. Python prints 4,073 with a comma
  2. Python reads 4 and 072 + 1 as two separate things
  3. Python adds 1 to 4,072 and prints 4073
  4. 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 4070
print(1,000 + 500)                  # should print 1500
print(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\text{pixels} = \text{height} \times \text{width}

In plain words: the number of pixels is the rows times the columns.

# a 5 by 5 trail sign
print(5 * 5)
# a 28 by 28 picture, the size of a classic handwritten-digit image
print(28 * 28)
# the ink pixels in the tent sign above, row by row
print(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)
  1. 784 50
  2. 2828 55
  3. 784 25
  4. 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?
  1. 7 million numbers
  2. 7 billion numbers it learned
  3. 7 thousand numbers
  4. 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.

Goes deeper in

Practice what you just read

  • 4 code examples you can edit and run
  • a practice exercise that checks your code
  • a 5-question quiz
  • 9 review cards for spaced repetition

Try a quiz question

In 50,304, what is the 3 worth?

  1. 300
  2. 3,000
  3. 30
  4. 3

Answer it at the end of the lesson to see if you're right, and why.

Keep learning

Where this lesson leads.

575 lessons in thirteen phases. 176 are free without an account, and a free account opens the rest. See every lesson.

Foundation · about 96 hours of study

Foundation math

From whole numbers to the math inside a neural network: each idea by hand, in Python, and in AI 118 lessons All free
  1. Numbers and place value FreeWhat a digit's place is worth, the number line, and Python as a calculator that never tires.36 min
  2. Multiplying and dividing: groups FreeEqual groups, quotient and remainder, and cutting training data into batches.35 min
  3. Order of operations, and names for numbers FreeBrackets, powers, then multiply and divide, then add and subtract; variables hold numbers.36 min
  4. Numbers below zero FreeThe number line through zero, sign rules, distance from zero, and an error's direction and size.37 min
  5. Fractions: equal parts, equal fractions, adding FreePieces of a whole, equal fractions, and re-cutting to add; accuracy as a fraction.45 min
  6. Multiplying and dividing fractions FreeA share of a share, dividing by flipping, and why chances in a row get small.35 min
  7. Decimals and rounding FreeFractions in place value, rounding, and why 0.1 + 0.2 isn't exactly 0.3.36 min
  8. Percentages FreePer hundred, percent change, percentage points, and the accuracy and error rates of models.35 min
  9. Ratios, rates and proportion FreeSharing in a ratio, rates per unit, scaling, and splitting data 80/10/10.35 min
  10. Powers and roots FreeRepeated multiplying, the laws of exponents, square roots, and squared error.43 min
  11. Very big and very small numbers FreePowers of ten, e-notation like 3e-4, orders of magnitude, and a model's size in memory.36 min
  12. Bits, bytes and floats: how numbers are stored FreeBase 2, what n bits can hold, a float as sign, power and digits, and a tensor's memory.35 min
  13. Review: find the slip (numbers) FreeBroken calculations to fix, mixed practice from the whole module, and its formula sheet.34 min
  14. Letters for numbers FreeVariables, terms and like terms, substitution, and a model's formula as a Python function.41 min
  15. Expanding and factoring FreeBrackets as areas, pulling out common factors, and a squared error expanded into a bowl.41 min
  16. Solving equations: keep the balance FreeThe same move on both sides, undoing steps in reverse, and running a model's formula backward.41 min
  17. Rearranging a formula FreeMaking any letter the subject, round-trip checks, and planning a training run.36 min
  18. Inequalities and true-or-false FreeRanges, flipping the sign, if and elif, and the thresholds, clips and ReLU inside a model.42 min
  19. Functions: a rule from input to output Freef(x) notation, tables and graphs, domain and range, loops over lists, and loss as a function.42 min
  20. Chaining and undoing functions Freeg(f(x)), inverses that undo, scaling and unscaling, and a network as a chain.42 min
  21. Straight lines: slope and intercept FreeRise over run, the line through two points, and a model's weight and bias as slope and intercept.42 min
  22. Two equations, two unknowns FreeSubstitution and elimination, where lines cross, and why models are fitted, not solved.42 min
  23. Quadratics: bowls and their lowest point FreeRoots by factoring and by formula, the discriminant, the vertex, and the best weight of a model.42 min
  24. Exponentials: growth and decay FreeThe same factor each step, the number e, and decaying learning rates.43 min
  25. Logarithms: the power question FreeTo what power?, the laws of logs, and adding log-probabilities instead of multiplying.45 min
  26. Sequences and Σ FreeArithmetic and geometric sequences, Σ as a loop that adds, and mean squared error.40 min
  27. Weighted and moving averages FreeWeights that add to 1, a window average, the exponential moving average, and smoothing a loss curve.35 min
  28. Sets, and reading the symbols FreeSets, union and intersection, ℝⁿ and f : ℝⁿ → ℝᵐ, and reading a paper's first equation.41 min
  29. Review: find the slip (algebra) FreeBroken algebra and code to fix, mixed practice from the whole module, and its formula sheet.34 min
  30. Transposing step by step: undo in reverse order FreeA formula's layers, the opposite of each, peeling from the outside in, conditions, and round-trip checks.35 min
  31. Formulas with fractions: clear them first FreeClearing denominators, cross-multiplying, a letter in the bottom, and reciprocal formulas like 1/R = 1/R₁ + 1/R₂.35 min
  32. When the letter appears twice: collect and factor FreeGathering the letter on one side, factoring it out, dividing by the bracket, and rearranging precision and F1.35 min
  33. Squares, roots and powers FreeSquare roots with ±, squaring to undo a root, cube and nth roots, and the √d inside attention.40 min
  34. When the letter is squared and plain: quadratics FreeRearranging into ax² + bx + c = 0, the formula, completing the square, and choosing the root that fits.35 min
  35. Letters in the power: exponentials and logarithms FreeTaking logs to bring a power down, exponentiating to free a letter, and the logit that undoes the sigmoid.40 min
  36. Rearranging inequalities: when the sign flips FreeThe four moves on an inequality, negatives and reciprocals that flip it, logs below 1, and sample sizes.35 min
  37. Inverse functions, lines and scaling FreeUndoing a function by making x the subject, domains that allow it, line forms, and unscaling predictions.40 min
  38. Sequences and sums: find n, a, d and r FreeEvery letter of the arithmetic and geometric formulas as the subject, and an average's window from its decay.40 min
  39. Combining formulas: substitute and eliminate FreePutting one formula inside another to remove a letter, and sizing a training run from a time or money budget.35 min
  40. Review: rearrange anything (algebra) FreeBroken rearrangements to fix, mixed practice from the whole algebra block, a strategy chart, and its formula sheet.35 min
  41. Coordinates and distance FreePoints as (x, y), Pythagoras, distance in any number of coordinates, and nearest neighbors.42 min
  42. Angles, degrees and radians FreeMeasuring a turn, converting units, arcs, and the angle between two arrows.36 min
  43. Sine and cosine FreeAcross and up: right triangles, the unit circle, and directions and rotations.42 min
  44. Waves: height, speed and shift FreeAmplitude, period and phase, sampling a wave, and position codes in transformers.37 min
  45. Review: find the slip (shapes and waves) FreeBroken geometry and code to fix, mixed practice from the module, and its formula sheet.29 min
  46. Angles, triangles and waves: rearranging with sin, cos and tan FreeSides and angles from SOH CAH TOA, principal values, arcs, polar coordinates, and a wave's time and period.45 min
  47. Vectors: lists of numbers that point FreeA list, a point and an arrow; components, dimension, NumPy arrays, and data as vectors.42 min
  48. Adding and scaling vectors FreeComponent-wise sums, scalar multiples, mixes, and the weight update w − ηg.43 min
  49. Length and distance: norms FreeL2, L1 and max norms, unit vectors, distance, and the norms inside losses and clipping.42 min
  50. The dot product FreeMultiply in pairs and add; a·a as squared length; a @ b; one neuron as a dot product.43 min
  51. Angle, cosine similarity and projection FreeDirection without length, perpendicular vectors, shadows, and search by meaning.45 min
  52. Perpendicular directions: bases and coordinates FreeOrthonormal directions, coordinates as dot products, rebuilding a vector, and taking a direction out.35 min
  53. Matrices: tables of numbers FreeRows, columns and entries; two-dimensional arrays and slices; a data set as a matrix.41 min
  54. Adding, scaling and transposing matrices FreeEntry-by-entry sums and scalings, the transpose, mean images, and tables turned around.36 min
  55. A matrix times a vector FreeEach row dotted with the vector, the size rule, A @ x, and a layer acting on one example.42 min
  56. Matrix multiplication FreeRow meets column, the size rule, order matters, and a batch through a layer: X W + b.45 min
  57. Identity, diagonal, triangular and symmetric FreeFour patterns and their jobs: rescaling, distance tables, and the causal mask.37 min
  58. Matrices as movements of space FreeStretches, flips, shears and rotations; columns as landing spots; chaining; a layer moving data.42 min
  59. Determinant and inverse FreeThe area factor ad − bc, singular matrices, undoing a matrix, and redundant features.42 min
  60. Solving systems by elimination FreeAugmented matrices, row moves, back-substitution, the three outcomes, and fitting weights.45 min
  61. Independence, span and rank FreeRedundant vectors, span, rank, outer products, and low-rank updates like LoRA.42 min
  62. Eigenvectors: directions that only stretch FreeAv = λv, checking candidates, np.linalg.eig, and the main direction of a data cloud.41 min
  63. SVD and PCA: the important directions first FreeA matrix as pieces by size, the best rank-k copy, compression, and PCA maps of data.45 min
  64. Tensors, shapes and broadcasting FreeAxes and shapes, reshape, axis=, broadcasting, and shapes through a small model.43 min
  65. One-hot vectors and lookup tables: embeddings FreeA one-hot row picks a table's row, a sentence looked up as vectors, and a score for every word.35 min
  66. Sliding dot products: convolution FreeA small pattern slid along a list and over a grid, output sizes, stride and padding, and shared weights.40 min
  67. Review: find the slip (vectors and matrices) FreeShape slips to fix, mixed practice from the module, and its formula sheet with shapes.36 min
  68. Vector equations: rearranging with arrows FreeSolving for a vector or a scale, recovering a gradient from two weight snapshots, and an angle from a dot product.40 min
  69. Matrix equations: multiply by the inverse, on the correct side FreeNo dividing by a matrix: inverses from the left or right, order, transposes, and the normal equations.40 min
  70. Rates of change FreeChange over change, secants, rates from readings with np.diff, and reading a loss curve.41 min
  71. Limits: what a value heads toward FreeApproaching from both sides, holes, corners and jumps, epsilon, and judging activations.37 min
  72. The derivative: slope at a point FreeShrinking secants, f′(x) and dy/dx, Δy ≈ f′Δx, and which way a weight should move.45 min
  73. Derivative rules FreeConstants, powers, multiples, sums, eˣ and ln x, checked numerically, and a squared error's slope.41 min
  74. The product rule and the chain rule FreeProducts and chains of functions, forward then backward, and one neuron's dL/dw.45 min
  75. Lowest points and curvature Freef′ = 0, the second-derivative test, tables, local and global minima, and convex losses.43 min
  76. Standing in for a curve near a point FreeTangent lines, a curvature term, growing error, and why learning rates must be small.37 min
  77. Partial derivatives FreeOne input at a time, ∂, nudging in Python, and the two slopes of a line's loss.41 min
  78. The gradient FreeAll the slopes as a vector, steepest climb and descent, a numerical gradient, and the loss gradient.42 min
  79. Gradient descent FreeStepping against the gradient, the learning rate, a training loop, and fitting a line.45 min
  80. Faster descent: momentum and Adam FreeMomentum and Adam by hand, the bias correction, and three optimizers down one narrow valley.40 min
  81. The chain rule with many paths: backpropagation by hand FreeGraphs, multiply along paths and add across them, gradient checks, and a 2-2-1 network by hand.45 min
  82. Automatic differentiation: how PyTorch finds every slope FreeA tape of steps walked backward, and requires_grad, backward(), .grad, zero_grad() and no_grad().40 min
  83. Jacobians and Hessians FreeSlopes of vector functions, a layer's Jacobian, second partials, and bowls, domes and saddles.42 min
  84. Integrals: adding up thin slices FreeStrip and trapezoid sums, summing undoes differencing, probability as area, and AUC.43 min
  85. Review: find the slip (calculus) FreeCalculus slips to fix, mixed practice from the module, and its formula sheet.36 min
  86. Rearranging in calculus: slopes, steps and constants FreeSetting a slope to zero, Newton's step, the chain rule turned around, constants from a point, and learning rates.45 min
  87. Counting: choices, orders and groups FreeThe counting principle, factorials, ordered picks and groups, and why attention's cost grows with the square of the length.43 min
  88. Probability: from counts to chances FreeEqually likely outcomes, the complement, distributions, seeded simulation, and a next-word model.43 min
  89. Combining events: and, or, independent FreeThe or rule, independence, probability trees, drawing with and without replacement, and chains of steps.42 min
  90. Conditional probability and Bayes' rule FreeConditionals from tables, why P(A | B) isn't P(B | A), Bayes' rule, and precision and recall.45 min
  91. Random variables and distributions FreeUncertain numbers, the probability of a range, sampling by slices, and sampling versus argmax.42 min
  92. Expected value, variance and standard deviation FreeProbability-weighted averages, spread in the data's own units, and a training loss as an expected value.42 min
  93. Bernoulli, binomial, uniform and normal FreeYes-or-no trials, counts of yeses, the 68-95-99.7 rule, z-scores, and an accuracy's error bar.45 min
  94. Two variables at once: covariance and correlation FreeJoint tables and marginals, covariance, correlation, the covariance matrix, and features that carry the same information.45 min
  95. Review: find the slip (probability) FreeProbability slips to fix, mixed practice from the module, and its formula sheet.36 min
  96. Probability formulas: solve for the missing chance FreeConditionals, Bayes' rule for the prior, the or rule, expected values, variance, and z-scores turned around.45 min
  97. Describing data: center, spread and scale FreeMean, median and mode, variance and standard deviation, percentiles, outliers, and standardizing features.42 min
  98. Samples, the law of large numbers and the central limit theorem FreeSamples and populations, the standard error σ/√n, the bell of averages, and error bars on test scores.43 min
  99. Is the difference real? Comparing two models FreePaired differences, a bootstrap interval, what a p-value is and isn't, and why many tries make lucky wins.40 min
  100. Maximum likelihood FreeLikelihoods as products, log-likelihoods as sums, grid search, underflow, and the negative log-likelihood loss.45 min
  101. Linear regression: the best line FreeResiduals, least squares by formula, three roads to one line, the matrix form, and train versus test error.45 min
  102. Logistic regression: a line that answers yes or no FreeThe sigmoid, the log loss, its slope p − y, a training loop, and choosing a threshold.45 min
  103. Scoring a classifier: confusion table, precision, recall, F1 FreeThe four cells, accuracy, precision, recall and F1, and what moving a threshold does to each.35 min
  104. Softmax: scores into probabilities FreeExponentiate and share out, shifting and temperature, the safe softmax, and a classifier's last step.43 min
  105. Surprise, entropy and cross-entropy FreeSurprise in bits, entropy, cross-entropy and KL divergence, perplexity, and a language model's loss.45 min
  106. KL divergence: how far one distribution is from another FreeKL by hand, cross-entropy as entropy plus KL, why it isn't symmetric, and a soft-target loss.35 min
  107. Review: find the slip (statistics and information) FreeStatistics slips to fix, mixed practice from the module, and its formula sheet.38 min
  108. Statistics and information: n, z, logits and bits FreeSample sizes from error bars, inputs from probabilities, logit gaps from softmax, and chances from bits and losses.40 min
  109. One neuron, start to finish FreeWeighted sum, activation, loss, slopes and update, by hand and in code, and what one straight line can and can't split.45 min
  110. A layer and a small network as matrices FreeTwo layers on a batch, the shape of every matrix, adding a hidden unit, and XOR solved.45 min
  111. Training a small network FreeThe backward pass in matrix form, gradient checks, a full training loop, and reading loss curves.45 min
  112. The same network in PyTorch Freenn.Sequential with the NumPy weights loaded, the same loss and slopes, then SGD and mini-batches.45 min
  113. Attention as matrix math FreeScaled dot-product scores, the causal mask, a row-by-row softmax, and blending value vectors.45 min
  114. Residual connections and layer norm FreeAdding the input back and why its slope keeps learning alive, layer norm by hand, and add and norm.40 min
  115. A transformer block, start to finish FreeA sentence through embeddings, attention, add and norm, a small network and next-word scores, every shape named.45 min
  116. Planning a model: rearranging the formulas of a working network FreeLayer widths from parameter counts, sizes from memory and compute, the attention scale, and a training plan.40 min
  117. Final test: transpose any formula FreeSlips to fix from every topic, mixed practice of every kind of rearranging, the strategy chart and the full sheet.45 min
  118. Capstone: a sign reader from the formulas FreeBuild, train and test a trail-sign classifier with NumPy alone, and report its accuracy with an error bar.45 min
Part of a free course 118 lessons

The Foundation Math For Ai & ML: from arithmetic to attention

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.

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