Index Ai Academy
Foundation · Shapes, angles and waves

Coordinates and distance

Points as (x, y), Pythagoras, distance in any number of coordinates, and nearest neighbors.

About 42 minutes · Free lesson

What it covers6

Why it matters

Geometry in AI comes down to two questions: where is a point, and how far apart are two points? Coordinates answer the first with numbers, and Pythagoras answers the second. The same distance formula works with three coordinates, or three hundred, which is how a model decides that two pictures, two words or two customers are similar: their lists of numbers are close. This lesson builds that distance and uses it to make a first prediction. Along the way Python gets the tuple, a small fixed group of values that suits a point exactly, and you'll meet the catch that every distance-based model has to handle: the units of each number decide what "close" means.

What you'll be able to do

  • Place points with coordinates, (x, y), over then up, in all four quadrants
  • Find the distance between two points with Pythagoras, in two coordinates or more
  • Store points as tuples in Python, write a distance function for any number of coordinates, and graph a distance
  • Predict from the nearest neighbor: in ML, "similar" means "close"
Quick check
Have a guess before you start. You walk 3 blocks east, then 4 blocks north. How far are you from where you started, in a straight line?
  1. 5 blocks
  2. 12 blocks
  3. 7 blocks
  4. 1 block
Show the answer

5 blocks

The walk makes a right triangle with sides 3 and 4. The straight line is the long side: √(3² + 4²) = √25 = 5.

The math: where, and how far

Purpose. Turn "where" and "how far" into numbers.

A point on a flat grid is written (x, y): go over x, then up y, from the origin (0, 0). Negative x is left and negative y is down, so the two axes cut the plane into four quadrants. (3, 4) is up and right; (−2, 1) is up and left.

Pythagoras. In a right triangle with short sides a and b, the long side c satisfies

a2+b2=c2a^2 + b^2 = c^2

In plain words: square the two short sides and add them; the square root of that is the long side.

The 3-4-5 triangle is the classic: 9 + 16 = 25, and √25 = 5.

Quick check
From an earlier lesson: what is √(6² + 8²)?
  1. 14
  2. 48
  3. 100
  4. 10
Show the answer

10

6² + 8² = 36 + 64 = 100, and √100 = 10. Roots undo squares, as lesson 10 showed.

The distance between two points. Any two points sit at the corners of a right triangle: the difference in x is one short side, the difference in y the other. So their distance is Pythagoras on the differences. Watch it for (1, 2) and (4, 6). The picture draws each step on a grid with the same scale across and up: the difference across and the difference up become the two short sides of a right triangle, and last comes the straight line between the points, its long side.

Try it now

Then set the first point to 0, 0, 0 and the second to 1, 2, 2 and press Use these numbers: three coordinates, the same steps. A flat picture has no room for a third direction, so that one runs without it.

Symbols and formula. For points (x₁, y₁) and (x₂, y₂):

d=(x2−x1)2+(y2−y1)2d = \sqrt{(x_2 - x_1)^2 + (y_2 - y_1)^2}

In plain words: the difference across, squared, plus the difference up, squared; then the square root.

More coordinates, same idea. A point in space has three coordinates, (x, y, z), and the distance just gets a third square under the root. With any number of coordinates, the rule is the same: square each difference, add them all, take the root. That's called the Euclidean distance.

Quick check
What's the distance from (−2, 1) to (1, −3)?
  1. 1
  2. 25
  3. 5
  4. 7
Show the answer

5

Differences: 1 − (−2) = 3 and −3 − 1 = −4. Squared: 9 and 16, adding to 25. √25 = 5.

Quick check
Which quadrant is (−3, −5) in?
  1. Bottom right: x positive, y negative
  2. Top right: both positive
  3. Top left: x negative, y positive
  4. Bottom left
Show the answer

Bottom left

Negative x is left of the origin and negative y is below it: the bottom-left quadrant.

Three facts that always hold. A distance is never negative, because it's a square root of squares. It's 0 only when the two points are the same point. And it doesn't matter which point you start from: (1, 2) to (4, 6) is 5, and (4, 6) to (1, 2) is 5 too, because each difference only flips its sign and the squares don't change.

Check with a walk. The straight-line distance is never longer than going across and then up: from (1, 2) to (4, 6) the walk along the grid is 3 + 4 = 7, and the straight line is 5. If your answer is longer than the walk, something went wrong.

In your own words
In your own words: why does squaring the differences mean it doesn't matter which point you start from?

Write a sentence or two, then compare it with a good answer in the lesson.

In Python: points as tuples

Purpose. Store a point as one value, and measure between any two.

A tuple is a fixed list of values in round brackets. It's the natural way to hold a point:

p = (3, 4)
print(p[0], p[1], len(p))
x, y = p
print(x, y)
It runs right here in your browser, with nothing to install.

p[0] and p[1] read the coordinates, like a list. The line x, y = p unpacks the tuple, giving each coordinate its own name. Unlike a list, a tuple can't be changed after it's made, which suits a point that should stay put. A distance function takes two of them:

import math

def distance(p, q):
    return math.sqrt((q[0] - p[0]) ** 2 + (q[1] - p[1]) ** 2)

print(distance((1, 2), (4, 6)), distance((-2, 1), (1, -3)))

Any number of coordinates. A loop over the coordinates handles points of any size, two or two hundred:

import math

def dist(p, q):
    total = 0
    for i in range(len(p)):
        total = total + (q[i] - p[i]) ** 2
    return math.sqrt(total)

print(dist((0, 0, 0), (1, 2, 2)), dist((1, 2, 3, 4), (2, 3, 4, 5)))

Now step through the same function, called twice: once on the flow's two points, once on two points in space, with three coordinates each. Press Next and watch total grow by one squared difference on each pass of the loop; the return then hands back its square root, the distance. The points p and q show as rows of boxes, like the cells in the flow above.

A named mistake: *2 for **2. Writing (q[i] - p[i]) * 2 doubles a difference instead of squaring it. It runs without an error and gives a wrong distance. The 3-4-5 check catches it: dist((0, 0), (3, 4)) must be 5.

Worked example

Worked example: the nearest of five points

Find which of five points is nearest to the target (3, 3).

import math

def dist(p, q):
    total = 0
    for i in range(len(p)):
        total = total + (q[i] - p[i]) ** 2
    return math.sqrt(total)

pts = [(1, 7), (4, 4), (6, 1), (2, 1), (5, 6)]
target = (3, 3)
best = 0
for i in range(len(pts)):
    if dist(pts[i], target) < dist(pts[best], target):
        best = i
print(best, pts[best], round(dist(pts[best], target), 3))
In the lesson you can change this and run it.

A list of tuples holds the five points. The search is lesson 19's hand-written search: keep the position of the best so far, and update it whenever a point is closer. Point 1, (4, 4), wins at √2 ≈ 1.414 away. (2, 1) looks close too, but it's √5 ≈ 2.236 away, because it's off by 2 in y.

Quick check
What does this print?
p = (2, 7)
x, y = p
print(y - x, p[1])
  1. 7 5
  2. -5 7
  3. 5 2
  4. 5 7
Show the answer

5 7

Unpacking gives x = 2 and y = 7, so y − x = 5. p[1] is the second value, 7.

Quick check
Which line squares the difference in coordinate i?
  1. (q[i] - p[i]) ** 2
  2. (q[i] - p[i]) * 2
  3. (q[i] - p[i]) ^ 2
  4. q[i] - p[i] ** 2
Show the answer

(q[i] - p[i]) ** 2

** 2 squares the whole difference, which the brackets keep together.

A distance as a graph. The worked example measured five points, one at a time. A graph shows a whole row of distances at once. The trail club's path runs along the x-axis, and one of its signs stands off the path at (3, 4). Each spot on the path is a point (x, 0), so its differences from the sign are x − 3 and 0 − 4. The loop below works out the distance from seven spots, and Matplotlib, as in lesson 19, draws them:

import math
import matplotlib.pyplot as plt
xs = [0, 1, 2, 3, 4, 5, 6]
ds = []
for x in xs:
    ds.append(math.sqrt((x - 3) ** 2 + (0 - 4) ** 2))
plt.plot(xs, ds)
plt.xlabel("x, a spot on the path")
plt.ylabel("distance to the sign")
plt.show()

The curve falls as you walk toward the sign and rises again once you've passed it.

Quick check
Read the graph. Where on the path are you nearest the sign, and how far away is it there?
  1. At x = 3, 4 away
  2. At x = 0, 5 away
  3. At x = 3, 0 away
  4. At x = 4, 3 away
Show the answer

At x = 3, 4 away

The curve is lowest at x = 3, straight under the sign, where only the 4 up is left: √(0² + 4²) = 4. It can't reach 0, because the sign is off the path. At x = 0 and x = 6 it's √(3² + 4²) = 5, the 3-4-5 triangle again.

Drill

A distance for any number of coordinates

Fix dist(p, q) so it gives the Euclidean distance for points of any length, then set d2 and d3 to two distances.

import math

def dist(p, q):
    total = 0
    for i in range(len(p)):
        total = total + (q[i] - p[i]) * 2
    return total

d2 = dist((0, 0), (3, 4))
d3 = dist((1, 1, 1), (3, 4, 7))
print(d2, d3)
In the lesson, your code is checked as you write it.
In your own words
Why is a tuple a good fit for a point?

Write a sentence or two, then compare it with a good answer in the lesson.

In AI and ML: similar means close

Purpose. Many models judge similarity by distance: two things are alike if their lists of numbers are close.

Describe each day at the tent shop by two numbers, (temperature, humidity). On four days the shop rented 22, 41, 59 and 47 tents. To predict a new day, find the nearest neighbor, the old day closest to it, and predict that day's rentals. This is the k-nearest-neighbors idea with k = 1.

y^=yj,where day j minimizes d(xj,xnew)\hat{y} = y_j, \quad \text{where day } j \text{ minimizes } d(x_j, x_{\text{new}})

In plain words: the prediction is the answer of whichever known example is nearest.

import math

def dist(p, q):
    total = 0
    for i in range(len(p)):
        total = total + (q[i] - p[i]) ** 2
    return math.sqrt(total)

days = [(10, 80), (20, 50), (30, 30), (25, 60)]
new = (22, 55)
for i in range(len(days)):
    print(days[i], round(dist(days[i], new), 2))
Quick check
From the distances above, which day is the new day's nearest neighbor, and what does it predict?
  1. (25, 60), predicting 47 tents
  2. (20, 50), predicting 41 tents
  3. (30, 30), predicting 59 tents
  4. (10, 80), predicting 22 tents
Show the answer

(20, 50), predicting 41 tents

(20, 50) is 5.39 away, the smallest. Its 41 rentals become the prediction.

The picture. Here are the four old days and the new one on a grid, temperature across and humidity up, with a dashed line from the new day to each. Two days are far off; two sit close. To fit all five, this first view squeezes the humidity: a step up is drawn shorter than a step across, so read the far days by their numbers. Press Next to zoom in on the two close days, drawn to the same scale across and up, so each line's length is its true distance.

In the real tools. In PyTorch, the library most models are built with, the four days go in one table, a tensor, and one line measures the new day's distance to every row at once, with no loop:

A catch: units matter. Distance treats every coordinate the same. If one were in dollars and another in cents, the cents would swamp the distance, and the nearest neighbor would be chosen by the cents alone. That's why ML code usually scales each coordinate first, as in lesson 20, so a step of 1 means about the same in each. Distance is simple, but which numbers go into it decides what "similar" means.

Here the same two days are described by temperature and by the day's takings in cents. A 10-degree difference in weather barely registers next to a 100-cent difference in money.

Quick check
What does this print?
import math

a = (20, 5000)
b = (30, 5100)
print(round(math.sqrt((b[0] - a[0]) ** 2 + (b[1] - a[1]) ** 2), 1))
  1. 110.0
  2. 10.0
  3. 100.5
  4. 14.1
Show the answer

100.5

The differences are 10 and 100, so the distance is √(100 + 10000) ≈ 100.5. Almost all of it comes from the cents column.

Drill

Predict from the nearest day

Fix the search so best is the position of the day nearest to new, and prediction is that day's rentals.

import math

def dist(p, q):
    total = 0
    for i in range(len(p)):
        total = total + (q[i] - p[i]) ** 2
    return math.sqrt(total)

days = [(10, 80), (20, 50), (30, 30), (25, 60)]
rentals = [22, 41, 59, 47]
new = (28, 36)
best = 0
for i in range(len(days)):
    if dist(days[i], new) > dist(days[best], new):
        best = i
prediction = rentals[0]
print(best, prediction)
In the lesson, your code is checked as you write it.
In your own words
How does a nearest-neighbor model decide what to predict, and what does it need distance for?

Write a sentence or two, then compare it with a good answer in the lesson.

Goes deeper in

Practice what you just read

  • 6 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

What's the distance from (2, 3) to (5, 7)?

  1. 5
  2. 7
  3. 25
  4. 4

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

Before this lesson

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