Index Ai Academy
Foundation · Transposition of formulas

Review: rearrange anything (algebra)

Broken rearrangements to fix, mixed practice from the whole algebra block, a strategy chart, and its formula sheet.

About 35 minutes · Free lesson

What it covers6

Why it matters

Rearranging slips are quiet. A 5 taken from one side only, a ± that goes missing, a planning answer rounded down: each still gives a number, and the number looks fine. This review plants the ten slips learners really make, shows the quick check that catches each one, mixes problems from all ten algebra lessons of the Transposition subcourse, and ends with a strategy chart and a formula sheet you can use on any formula.

What you'll be able to do

  • Spot the ten slips of rearranging: one-sided moves, layers in the wrong order, split roots, logs and reciprocals, lost flips and ±, a letter left on both sides, dropped brackets and answers not rounded up
  • Catch each slip with a quick check: numbers back in, a round trip, a number on each side, or a law tested with easy numbers
  • Choose the right move for any formula with the strategy chart: count the letter, peel or collect, undo in reverse, write the conditions, check
  • Mix rearrangements from every algebra lesson of the subcourse, from peeling to combining formulas
  • Use the subcourse's formula sheet: each formula, its rearranged form, its condition and its Python line
Quick check
Have a guess before you start. A learner makes P the subject of A = P + Prt and writes P = A − Prt. What's wrong?
  1. Nothing: it's finished
  2. P is still on both sides
  3. A sign was lost: P = A + Prt
  4. They should divide by r first
Show the answer

P is still on both sides

P appears twice, so peeling can't free it. Collect and factor: A = P(1 + rt), so P = A/(1 + rt). A finished answer has the letter on one side only.

Find the slip

Purpose. Each rearranging slip breaks a quick check, so knowing the checks is how you catch them:

  • Put numbers back in. Work the answer out, put it into the original formula, and see if both sides agree.
  • Round trip. Go forward with a number, then back with your rearranged formula. You should land where you began.
  • Count the letter. A finished answer has the letter you want on one side only.
  • Try a number on each side. For an inequality, one value your answer allows must pass, and one it rules out must fail.
  • Test a law with easy numbers. Unsure whether a root, a log or a fraction splits? Try 6 and 8, or 2 and 3.

Below are two sets of worked lines, written as Python with a comment saying what each should give. Each set has five slips and three right lines.

Try it now

How the checks caught them. Putting the answer back exposes the first two at once: 3 × 6.67 + 5 is about 25, and 2 × 2.5 + 3 is 8, so neither equals what it should. Testing a law with easy numbers settles the next one: 1/(2 + 3) is 0.2, far from 0.83. Counting the letter catches P = A − Prt, since P is on both sides. And 6, 8, 10 is a right triangle you can check by hand: 36 + 64 = 100, so the long side is 10. The second set comes from the later lessons.

How the checks caught them. Putting 0 back into 2(x − 3)² + 1 gives 19 too, so a second answer was lost. Easy numbers settle the log: 2 + 8 = 10, and log₁₀ 10 is exactly 1. Trying x = 3, which the slip allows, fails 5 − 2x > 1, so the sign had to flip. For the circle, a round trip through r = 5, with π = 3.14, gives C = 31.4 and A = 78.5, not 493. And 1.05⁸ ≈ 1.477 is still short of 1.5. Python can run the ± check for you.

Quick check
What does this print?
import math

for x in [3 + math.sqrt(9), 3 - math.sqrt(9)]:
    print(x, 2 * (x - 3) ** 2 + 1)
  1. 6.0 19.0 0.0 1.0
  2. 6.0 19.0
  3. 6.0 19.0 0.0 -17.0
  4. 6.0 19.0 0.0 19.0
Show the answer

6.0 19.0 0.0 19.0

Both roots put back give 19: (6 − 3)² and (0 − 3)² are both 9. That's why undoing a square keeps the ±.

Slips that hide in code. In code, a rearranging slip raises no error. C ** 2 / 4 * math.pi divides by 4 and then multiplies by π, when the formula divides by 4π. math.sqrt gives only the positive root, so the − answer has to be written by hand. And round goes to the nearest whole number, which can land below a target: a planning answer that says "at least" needs math.ceil, which always rounds up ("at most" needs math.floor). Each runs and prints a confident wrong number.

Quick check
$1,000 grows as 1000 × 1.05ⁿ. A learner says it passes $1,500 after 8 whole years. Which check shows the slip?
  1. Try n = 0: it gives 1,000
  2. Put 8 back: 1000 × 1.05⁸ is 1,500
  3. Check the units: n is in years
  4. Put 8 back: 1000 × 1.05⁸ ≈ 1,477
Show the answer

Put 8 back: 1000 × 1.05⁸ ≈ 1,477

n = ln 1.5 ÷ ln 1.05 ≈ 8.31. After 8 years it's $1,477, still short, so the first whole year past $1,500 is 9: round up.

Drill

The circle's area is far too big

circle_area(C) should give a circle's area from its circumference, A = C²/(4π), from putting r = C/(2π) into A = πr². It runs, but it's ten times too big. Find the one slip and fix it.

import math

def circle_area(C):
    return C ** 2 / 4 * math.pi

C = 2 * math.pi * 5
print(circle_area(C), math.pi * 5 ** 2)
In the lesson, your code is checked as you write it.
In your own words
Which quick check caught the most slips in the two sets, and why does it work so well?

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

Mixed practice

Purpose. The problems below come from all ten algebra lessons of the subcourse, roughly hardest last. Each one asks you to rearrange, then put the numbers in. Before you start, name the move it needs: peeling, clearing a fraction, collecting the letter, a root, the quadratic formula, logs, an inequality, an inverse, a sequence or combining. The strategy chart after the ladder gives you the order to decide in.

The strategy chart. For any formula and any letter:

  1. Where is the letter, and how many times does it appear?
  2. Twice or more: collect every copy on one side and factor it out. If it's both squared and plain, make it a quadratic, ax² + bx + c = 0.
  3. Once: list the layers around it, in the order they were put on.
  4. Undo them in reverse with the matching opposite:
done to the letterundone by
+ k, − k− k, + k
× k, ÷ k÷ k (k ≠ 0), × k
square, nth power± square root, nth root
a power bˣ, eˣlog base b, ln
log base b, lnb to the power, e to the power
1 ÷ it1 ÷ it again
  1. Write the conditions: no zero divisors, ± from even roots, logs of positive numbers only, a flipped sign.
  2. Check: numbers back in, a round trip, and units. A whole count rounds the safe way: up for "at least", down for "at most".
Quick check
Step 1 of the chart: a can's surface area is S = 2πr² + 2πrh. Which move frees h, and which frees r?
  1. h: peel; r: a quadratic
  2. h: a quadratic; r: peel
  3. Both: collect and factor
  4. Both: peel in reverse
Show the answer

h: peel; r: a quadratic

h appears once, so peel it: h = (S − 2πr²)/(2πr). r appears squared and plain, so it's a quadratic: 2πr² + 2πhr − S = 0.

Worked example

Worked example: the chart on k = m/(m + 4)

m appears twice (step 1), so clear the fraction, collect and factor (step 2): km + 4k = m gives m(1 − k) = 4k, so m = 4k/(1 − k). The condition is k ≠ 1 (step 5). Step 6 runs the checks in code.

def k_of(m):
    return m / (m + 4)

def m_of(k):
    if k == 1:
        return None
    return 4 * k / (1 - k)

print(m_of(0.75), k_of(12))
for m in [12, 0.5, -2]:
    print(m, m_of(k_of(m)))
print(m_of(1))
It runs right here in your browser, with nothing to install.

Numbers back in: m_of(0.75) is 12.0, and k_of(12) gives back 0.75. The round trips bring 12, 0.5 and −2 home, an ordinary number, a fraction and a negative, so a slip would have to fool all three. The last line is the condition. k = 1 would need m = m + 4, which never happens, so no m gives k = 1, and m_of says so with None instead of dividing by 0.

Quick check
What does this print?
import math

n = 0.9 * (1 - 0.9) / 0.04 ** 2
print(round(n), math.ceil(n))
  1. 56.25 57
  2. 56 57
  3. 57 57
  4. 56 56
Show the answer

56 57

n ≈ 56.25. round goes to the nearest whole number, 56; math.ceil always rounds up, 57. A test set of 56 misses the error bar, so 57 is the answer.

Drill

The test set comes out one short

test_size(p, E) should give the smallest test set whose error bar √(p(1 − p)/n) is at most E. It returns 56 for p = 0.9 and E = 0.04, and that set's error bar is just over 0.04. Find the one slip and fix it.

import math

def test_size(p, E):
    return round(p * (1 - p) / E ** 2)

n = test_size(0.9, 0.04)
print(n, math.sqrt(0.9 * 0.1 / n))
In the lesson, your code is checked as you write it.
In your own words
Which problem in the mixed ladder made you stop and think about the move? What in the formula told you which one to use?

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

The formula sheet

Purpose. The algebra lessons of the subcourse on one sheet: each formula, the letter made the subject, the condition that goes with it, and its Python line. Lessons 30 to 35:

lessonformularearrangedconditionin Python
30y = 3(x − 2)/4 + 5x = 4(y − 5)/3 + 2none: the divisors are numbers4 * (y - 5) / 3 + 2
30v = u − gtt = (u − v)/gg ≠ 0(u - v) / g
311/R = 1/R₁ + 1/R₂R = R₁R₂/(R₁ + R₂)R₁ + R₂ ≠ 0R1 * R2 / (R1 + R2)
31y = a/(b + x)x = a/y − by ≠ 0a / y - b
32A = P + PrtP = A/(1 + rt)1 + rt ≠ 0A / (1 + r * t)
33A = πr²r = √(A/π)keep + for a lengthmath.sqrt(A / math.pi)
33T = 2π√(l/g)l = g(T/2π)²square the whole bracketg * (T / (2 * math.pi)) ** 2
34ax² + bx + c = 0x = (−b ± √(b² − 4ac))/(2a)a ≠ 0, b² − 4ac ≥ 0(-b + math.sqrt(b ** 2 - 4 * a * c)) / (2 * a)
35A = P(1 + r)ⁿn = ln(A/P)/ln(1 + r)A/P > 0, r > −1, r ≠ 0math.log(A / P) / math.log(1 + r)
35p = 1/(1 + e^(−z))z = ln(p/(1 − p))0 < p < 1math.log(p / (1 - p))
Quick check
Which row of the sheet fixes the slip P = A − Prt?
  1. Lesson 35: n = ln(A/P)/ln(1 + r)
  2. Lesson 31: x = a/y − b
  3. Lesson 30: t = (u − v)/g
  4. Lesson 32: P = A/(1 + rt)
Show the answer

Lesson 32: P = A/(1 + rt)

P appears twice, so it needs collecting and factoring: A = P(1 + rt), then divide by the bracket.

Lessons 36 to 39:

lessonformularearrangedconditionin Python
36√(p(1 − p)/n) ≤ En ≥ p(1 − p)/E²1 over both sides flips the sign; round upmath.ceil(p * (1 - p) / E ** 2)
36lr₀γᵗ ≤ targett ≥ ln(target/lr₀)/ln γflips: ln γ < 0 for γ < 1; round upmath.ceil(math.log(target / lr0) / math.log(gamma))
37f(x) = (2x + 3)/5f⁻¹(x) = (5x − 3)/2f one-to-one(5 * x - 3) / 2
37z = (x − μ)/σx = μ + zσσ ≠ 0mu + z * sigma
38uₙ = a + (n − 1)dn = (uₙ − a)/d + 1d ≠ 0; n a positive whole number(u - a) / d + 1
38uₙ = a·rⁿ⁻¹n = log(uₙ/a)/log r + 1uₙ/a > 0, r > 0, r ≠ 1; n wholemath.log(u / a) / math.log(r) + 1
39C = 2πr and A = πr²A = C²/(4π)keep the brackets: π(C/(2π))²C ** 2 / (4 * math.pi)
39v = u + at and s = ut + ½at²v² = u² + 2asu² + 2as ≥ 0; v = ±√(u² + 2as)math.sqrt(u ** 2 + 2 * a * s)

Each row is also a check: if an answer breaks a row's condition, the slip is in that step.

Quick check
A learning rate starts at 0.1 and is multiplied by 0.9 each step. Which row finds the first step where it's at most 0.01, and what is it?
  1. Lesson 36: t ≥ 21.85, so step 22
  2. Lesson 36: t ≤ 21.85, so step 21
  3. Lesson 36: t ≥ 21.85, so step 21
  4. Lesson 38: n = (uₙ − a)/d + 1
Show the answer

Lesson 36: t ≥ 21.85, so step 22

0.1 × 0.9ᵗ ≤ 0.01 gives t ≥ ln(0.1)/ln(0.9) ≈ 21.85: dividing by ln 0.9, a negative, flips ≤ to ≥. Round up: step 22.

Coming up. The next Foundation module, shapes, angles and waves, opens with distances: √((x₂ − x₁)² + (y₂ − y₁)²), a root of a sum, the very slip from the first set. After it, the subcourse continues with Angles, triangles and waves: rearranging with sin, cos and tan, which adds new rows to the table of opposites: arcsin undoes sin, with its own condition, the principal angle.

In your own words
Pick the row of the sheet whose condition you're most likely to forget. What check would catch it?

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

Goes deeper in

Practice what you just read

  • 1 code example 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

A learner makes x the subject of y = 2x + 3 and writes x = y/2 − 3. What's the slip?

  1. Layers undone in the wrong order
  2. A sign was lost on the 3
  3. Nothing: it's right
  4. The 2 should multiply y

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.

Part of a free course 19 lessons

Transposition of Formulas: algebraic manipulation in every topic

Learn to make any letter of any formula the subject: layers undone in reverse order, fractions, a letter that appears twice, powers, roots, quadratics, logs, inequalities, trigonometry, vectors, matrices, calculus, probability, statistics and the formulas inside AI models, each checked in Python.

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