Teaching Thread Part B: Multi-Class Perceptron Rule Derived on the Board
alfcnz · x · 2026-09-24
Part B of @alfcnz's teaching thread derives the multi-class perceptron: from s = wᵀx with w ← w + (y − ỹ)x, extending to competing directions s = Wx where the prediction is one-hot on the highest score, with update rule W ← W + (y − ỹ)xᵀ — the same formula with lists. Includes a worked example of one wrong guess.
More from Research
- Benchmark run finds "arjunomics in the weights", raising misalignment concerns — kenbwork · 2026-09-24
- Arena opens Fall 2026 academic program with $50K per AI evaluation project — arena · 2026-09-24
- RSA-896 Factored With Claude Orchestrating 2,048 GPUs Over 10 Days, 30 GPU-Years — matthew_d_green · 2026-09-24
- Dario touts Claude-led gene editing discovery, but biologists call it overhyped — ccerrato147 · 2026-09-24
- Jev Is an Architecture Bet, Not a Product: Could LLMs Specialize Beyond Generation? — tenkei_01 · 2026-09-24
- Mathematician proposes nonlinear variant of Komlós conjecture, inspired by AI proof — burny_tech · 2026-09-24