Index Ai Academy
Foundation · Algebra

Rearranging a formula

Making any letter the subject, round-trip checks, and planning a training run.

About 36 minutes · Free lesson

What it covers6

Why it matters

A formula like distance = speed × time holds three letters, and any one of them can be the unknown. Rather than learning three formulas, learn one and rearrange it. It's the balance from the last lesson again, with letters on the pans instead of numbers. In machine learning the same skill turns "how many steps will this take?" into "how many examples do I need for this many steps?" Along the way, you'll write each rearranged formula as a Python function and check every pair with a round trip, a test that catches a wrong rearrangement every time. Engineers use the same habit before trusting any formula they've rearranged by hand.

What you'll be able to do

  • Make any letter of a formula its subject, with the four moves done to both sides
  • Rearrange d = s·t, y = mx + b and a = c/n for each of their letters
  • Write one function per subject in Python, and check each pair by a round trip
  • Rearrange the formulas for accuracy and training steps to answer planning questions
Quick check
Have a guess before you start. A car covers distance d = s × t. Which formula gives the time t?
  1. t = d ÷ s
  2. t = s ÷ d
  3. t = d × s
  4. t = d − s
Show the answer

t = d ÷ s

t is multiplied by s, so divide both sides by s: d ÷ s = t. 150 miles at 50 miles an hour takes 3 hours.

The math: any letter can be the subject

Purpose. One formula, any unknown.

The subject of a formula is the letter on its own on one side: in d = s·t, it's d. To make another letter the subject, treat the formula as a balance and use the four moves, always on both sides:

  • add the same thing to both sides
  • take the same thing from both sides
  • multiply both sides by the same thing (not 0)
  • divide both sides by the same thing (not 0)

It's exactly what you did with numbers in the last lesson. The letters just stay as letters.

Quick check
From the last lesson: solve 3s = 150.
  1. s = 450
  2. s = 50
  3. s = 147
  4. s = 153
Show the answer

s = 50

Divide both sides by 3: s = 50. With letters, the same move turns d = s·t into s = d/t.

Watch the balance make s the subject of 150 = s × 3, the formula d = s·t with d = 150 and t = 3. The one move, dividing both pans by 3, is the same move that turns d = s·t into s = d/t for every d and t.

In the picture, the pans keep the letters: s × t on the left, d on the right. The line above the beam carries this flow's numbers. Watch the move work on the letters, then the check put the numbers back in for them.

Try it now

Change the time and the distance and press Use these numbers: the move is always the same, divide by t.

Symbols and formula. Three everyday formulas, each rearranged for every letter:

d=st  ⇒  s=dt,  t=dsy=mx+b  ⇒  x=y−bm,  b=y−mxd = st \;\Rightarrow\; s = \frac{d}{t},\; t = \frac{d}{s} \qquad y = mx + b \;\Rightarrow\; x = \frac{y - b}{m},\; b = y - mx

In plain words: undo whatever is done to the letter you want, in reverse order, on both sides.

And for a = c/n, where c is divided by n: multiply both sides by n to get c = a·n, then divide by a to get n = c/a.

A check that always works. Put numbers in. If d = 150, s = 50 and t = 3 fit the first form, they must fit every rearranged form too: 150/3 = 50 and 150/50 = 3. A rearrangement that breaks this has a slip.

Quick check
Rearrange y = mx + b to make x the subject.
  1. x = (y + b) / m
  2. x = y / m − b
  3. x = m(y − b)
  4. x = (y − b) / m
Show the answer

x = (y − b) / m

x was multiplied by m, then b was added. Undo in reverse: take b from both sides, then divide by m.

Quick check
In a = c/n, what is n?
  1. n = c − a
  2. n = a / c
  3. n = c / a
  4. n = a × c
Show the answer

n = c / a

Multiply both sides by n: a·n = c. Then divide both by a: n = c/a. With a = 4 and c = 12, n = 3.

In your own words
In your own words: why does rearranging a formula save you from learning three formulas?

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

In Python: one function per subject

Purpose. In code, each rearrangement becomes its own function, and the functions check each other.

def distance(s, t):
    return s * t

def speed(d, t):
    return d / t

def time(d, s):
    return d / s

print(speed(distance(50, 3), 3), time(distance(50, 3), 50))
It runs right here in your browser, with nothing to install.

The last line is a round trip: work out a distance from s = 50 and t = 3, then feed it back into the rearranged formulas. You get back 50 and 3, where you started. If a rearrangement had a slip, the round trip would land somewhere else.

A round trip, one line at a time. Here is the round trip for s again, split over two lines, with the flow's numbers. distance turns s = 50 and t = 3 into d, and speed turns d and t back into s. Press Next to run one line at a time, and watch the number distance hands back go into speed.

The same round trip for y = mx + b. Go forward from x to y, then back from y to x:

def y_of(x, m, b):
    return m * x + b

def x_of(y, m, b):
    return (y - b) / m

print(x_of(y_of(4, 2.5, 1), 2.5, 1))

A named mistake: forgetting the brackets. Written as y - b / m, Python divides b alone, because dividing comes before subtracting. The round trip catches it at once: it no longer comes back to 4.

Worked example

Worked example: Fahrenheit to Celsius and back

F = 9C/5 + 32. Rearrange for C, write both directions, and check with a round trip.

def to_f(c):
    return 9 * c / 5 + 32

def to_c(f):
    return (f - 32) * 5 / 9

print(to_f(25), to_c(77))
print(to_c(to_f(25)), to_c(100))
In the lesson you can change this and run it.

To get C, undo F's steps in reverse: take 32 away, then multiply by 5, then divide by 9. The first line shows 25 degrees Celsius is 77.0 Fahrenheit, and back again. The round trip returns 25.0. The last number shows a rearranged formula working on a fresh input: 100 Fahrenheit is about 37.8 Celsius, a hot day.

Quick check
What does this print?
def x_of(y, m, b):
    return (y - b) / m

print(x_of(18, 2, 3))
  1. 16.5
  2. 9.0
  3. 10.5
  4. 7.5
Show the answer

7.5

(18 − 3) ÷ 2 = 15 ÷ 2 = 7.5. Check: 2 × 7.5 + 3 = 18.

Quick check
Which line is a round-trip check for speed(d, t) = d / t?
  1. print(distance(50, 3))
  2. print(speed(3, 50))
  3. print(speed(distance(50, 3), 3))
  4. print(speed(50, 3))
Show the answer

print(speed(distance(50, 3), 3))

Go forward with distance, then back with speed: getting 50 again shows the rearrangement is right.

When the letter appears twice. Sometimes the letter you want shows up in two places, as in y = x + x/4. Gather it first: x + x/4 is 5x/4, so y = 5x/4, and then x = 4y/5. Rearranging is always the same few moves, but gathering the letter into one place has to come first. When a letter can't be gathered, as in y = x + x², no simple rearrangement exists, and the last lesson's guess, check and adjust takes over. Computers solve many real problems exactly that way.

Drill

Two rearranged pairs

circle_c(r) returns a circle's circumference C = 2 × 3.14 × r. Write radius(c) that undoes it, and fix x_of so it undoes y_of. The round trips are checked.

def circle_c(r):
    return 2 * 3.14 * r

def radius(c):
    return c * 2 * 3.14

def y_of(x, m, b):
    return m * x + b

def x_of(y, m, b):
    return y - b / m

print(radius(circle_c(5)), x_of(y_of(4, 2.5, 1), 2.5, 1))
In the lesson, your code is checked as you write it.
In your own words
Why does a round trip catch slips that a single calculation might hide?

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

In AI and ML: planning with rearranged formulas

Purpose. Training numbers come in formulas, and the question you have is rarely the one the formula answers.

Accuracy. accuracy = correct/total, so correct = accuracy × total. A model that's 92% accurate on 500 test images got 460 right.

Steps. In training, steps = epochs × n ÷ batch, with n examples. Rearranged for n:

steps=epochs×nbatch  ⇒  n=steps×batchepochs\text{steps} = \frac{\text{epochs} \times n}{\text{batch}} \;\Rightarrow\; n = \frac{\text{steps} \times \text{batch}}{\text{epochs}}

In plain words: to find how many examples a plan needs, multiply the steps by the batch size and divide by the epochs.

def examples_for(steps_wanted, epochs, batch):
    return steps_wanted * batch / epochs

print(examples_for(1000, 5, 50))
Quick check
A model is 85% accurate and got 204 test images right. How many images were in the test?
  1. 204
  2. 240
  3. 289
  4. 173.4
Show the answer

240

total = correct ÷ accuracy = 204 ÷ 0.85 = 240. Check: 0.85 × 240 = 204.

Why rearrange instead of guessing? You could try different numbers of examples until the steps come out right, as in the last lesson's guess, check and adjust. But a rearranged formula answers in one line, and a round trip with the original formula confirms it:

def steps(epochs, n, batch):
    return epochs * n / batch

def examples_for(steps_wanted, epochs, batch):
    return steps_wanted * batch / epochs

print(steps(5, examples_for(1000, 5, 50), 50))

The plan needs 10,000 examples, and putting them back into the steps formula gives exactly the 1,000 steps asked for.

Every letter, one formula. The training formula has four letters: steps, epochs, n and batch. Rearranged, it answers four planning questions: how long training takes, how many passes fit a budget, how much data a plan needs, and which batch size hits a target. One small function per question keeps each answer to one line, and a round trip through the original formula catches any slip. Teams planning large training runs do exactly this arithmetic before they spend money on computers.

In the real tools. In PyTorch, the library most models are built with, a DataLoader cuts n examples into batches, and len(loader) counts the steps in one epoch. Here is the plan from above turned round: 10,000 examples, 5 epochs and 1,000 steps, solved for the batch size, with a round trip to check it:

Quick check
Now the same line solved for epochs. Predict both answers: what does this print?
def epochs_for(steps, n, batch):
    return steps * batch / n

print(epochs_for(1000, 10000, 50), epochs_for(3000, 48000, 64))
  1. 500.0 2250.0
  2. 5.0 4.0
  3. 5 4
  4. 0.2 0.25
Show the answer

5.0 4.0

epochs = steps × batch ÷ n: 1,000 × 50 ÷ 10,000 = 5.0, and 3,000 × 64 ÷ 48,000 = 4.0. The first is the plan above, and you'll plan the second in the drill below.

Drill

Plan a training run

Set right to the number of test images a 92%-accurate model gets right out of 500, n to the examples needed for 3,000 steps over 4 epochs in batches of 64, and back to the round trip of n through steps.

def steps(epochs, n, batch):
    return epochs * n / batch

right = 500 / 0.92
n = 3000 * 4 / 64
back = 0
print(right, n, back)
In the lesson, your code is checked as you write it.
In your own words
Give an example of a planning question in training that needs a formula rearranged.

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

Goes deeper in

  • Formulas: using and rearranging formulas in more Python.

Practice what you just read

  • 5 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

Make w the subject of A = l × w.

  1. w = A / l
  2. w = A × l
  3. w = l / A
  4. w = A − l

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