Nathan Lamberson’s Reviews > Why Machines Learn: The Elegant Math Behind Modern AI > Status Update
Nathan Lamberson
is on page 47 of 480
Dot products and matrix multiplication, which honestly lost me.
P. 46 has an important equation and diagrams for understanding all that connection to the Perceptron, which makes some sense at least. The vector for weight, w, will always have a perpendicular line to itself (itself being hyperplane) that is what classifies this outputs as -1 or 1.
— May 21, 2026 09:44AM
P. 46 has an important equation and diagrams for understanding all that connection to the Perceptron, which makes some sense at least. The vector for weight, w, will always have a perpendicular line to itself (itself being hyperplane) that is what classifies this outputs as -1 or 1.
Like flag
Nathan’s Previous Updates
Nathan Lamberson
is on page 33 of 480
Vectors (magnitude and direction) and scalars (quantity, just a number)
Def learned this before in Physics or calc in college. It clicked again on pp. 29-30 with the graphs. The Cartesian coordinates we def used before on p. 33. Vector math is super simple too, see p. 32.
— May 19, 2026 09:45AM
Def learned this before in Physics or calc in college. It clicked again on pp. 29-30 with the graphs. The Cartesian coordinates we def used before on p. 33. Vector math is super simple too, see p. 32.
Nathan Lamberson
is on page 26 of 480
End chapter 1. Perceptrons and their ways of clumping data together to find separations (given they exist), linearly. The graph with a lime separating all triangles on the left and circles on the right of the line shows a basic example of this (p. 23)
— May 19, 2026 09:16AM
Nathan Lamberson
is on page 16 of 480
Re-read beginning. Talking about small deterministic patterns and how artificial neurons work to find those patterns to understand a computers relation to human thinking
— Apr 07, 2026 06:53PM
