Chapters

Every chapter, grouped by Part. Use the card metadata to calibrate how much trust to place in a chapter's specific claims.

Foundations

  1. Week 1 implemented

    Linear ODEs as state-space systems

    Continuous-time linear systems, the matrix exponential as fundamental solution, the damped oscillator as canonical example, and the eigenvalue classification of phase portraits.

  2. Week 2 implemented

    Stability theory: Lyapunov, A-stability, BIBO

    Three distinct notions of stability — Lyapunov (eigenvalue criterion + QR-based computation), A-stability (regions of absolute stability for ODE integrators), and BIBO (bounded-input bounded-output for LTI systems).

  3. Week 3 implemented

    Linear algebra for sequence models: structured matrices and conditioning

    Eigenvalue and SVD decompositions, condition number, the four structured-matrix families (Toeplitz, Vandermonde, Cauchy, semiseparable), low-rank updates, and a Krylov-subspace primer — the linear-algebra vocabulary later chapters assume.

  4. Week 4 implemented

    Discretization theory: ZOH, bilinear, exponential families

    One-step discretizations of linear ODEs — zero-order hold, bilinear (Tustin), and exponential-trapezoidal — with the Lax equivalence theorem as the unifying convergence criterion.

  5. Week 5 implemented

    Stability regions, Butcher tableau, and order conditions

    Runge–Kutta theory, the Butcher tableau formalism, order conditions, stability regions in the complex plane, A-stability and L-stability, and the Dahlquist barrier — applied to the Chapter 4 discretization atlas.

  6. Week 6 implemented

    Implicit methods, stiff systems, symplectic integration

    When explicit methods fail — backward Euler, BDF, DIRK as A-stable alternatives; exponential integrators as the family of choice for selective SSMs; Hamiltonian mechanics and symplectic integration as the natural geometric language for hidden-state dynamics.

SSM Core

  1. Week 7 implemented

    HiPPO theory: orthogonal-basis projection operators

    Online function approximation by projection onto orthogonal polynomial bases — the HiPPO-LegS operator, its lower-triangular structure and exact spectrum, discretization to the S4 recurrence, and the basis-conditioning question.

  2. Week 8 implemented

    LTI SSMs: S4, S4D, S5 as discretized continuous systems

    The S4 architecture as a discretized HiPPO LTI system — the convolution–recurrence duality and its FFT kernel, the diagonal-plus-low-rank structure behind S4's fast kernel, S4D's diagonal restriction with by-construction stability, and S5's parallel associative scan.

  3. Week 9 implemented

    Selective SSMs: Mamba-1, Mamba-2, and the SSD framework

    Making the SSM parameters input-dependent — selectivity breaks linear time-invariance, collapses the convolution–recurrence duality, and leaves the associative scan as the only route; the structured state-space duality then re-reads the selective scan as a semiseparable matrix and, for scalar state, as masked linear attention.

  4. Week 10 implemented

    Mamba-3 and the exponential-trapezoidal integrator

    How Mamba-3 keeps selectivity and changes two things — a second-order exponential-trapezoidal integrator and a complex state — turning the dynamical-systems lens of Chapters 4-6 onto a production sequence model.

Beyond SSMs

  1. Week 11 implemented

    Linear attention and Hyena: long convolution and gated recurrence

    Linear attention read as a matrix-state linear recurrence — the dual of Chapter 9's scan, entered from the attention side — then gated into the LTV/selectivity face (GLA, RetNet), pivoted to Hyena's implicit LTI long convolution, and landed honestly on the associative-recall capacity limit of any finite state.

  2. Week 12 implemented

    Delta-rule lineage: DeltaNet, Gated DeltaNet, Kimi Linear

    The delta rule read as one gradient step on an associative-recall loss — DeltaNet (explicit Euler) and Longhorn (backward Euler) as the textbook explicit/implicit discretization pair, the stability dichotomy that follows, chunkwise parallelization via the WY trick, and gated forgetting from Gated DeltaNet to Kimi Linear.

  3. Week 13 implemented

    Exponential gates and matrix memory: xLSTM and RWKV-7

    One generalized linear recurrence whose transition is diagonal-plus-rank-one — RWKV-7's generalized delta rule (rank-one removal in a learned direction, not the key) and xLSTM's matrix memory with exponential gating (and the log-domain stabilizer state that overflow forces) — extending Chapter 12's delta-rule lineage to matrix memories with their own stability questions.

Integration

  1. Week 14 implemented

    Hybrid architectures and gating mechanisms

    Hybrids read through the two-timescale lens — attention as the boundary layer (exact on fast, token-local structure), the decaying state as the slow manifold (compressed carried context), and composition and gate granularity as the design variables; with the production lineup as of May 2026, the MAD methodology, and the two-timescale benchmark seed for pilot B.

  2. Week 15 implemented

    Counter-evidence and diagnostic tools: where SSMs fail

    The prosecution's file — what fixed-state and SSM-heavy designs provably cannot do (the TC⁰ ceiling, the illusion of state, the copying separation) and the diagnostic toolkit that measures stability and capacity on real systems, from an architecture-agnostic information-counting bound through the Benettin–QR Lyapunov estimator and its resolution limit to effective state size as a regime diagnostic, all validated against known ground truth.

  3. Week 16 implemented

    Empirical methodology: benchmark protocols and evaluation

    Benchmarks as measurement instruments — the discriminative-regime principle for synthetic probes (tokenized MQAR with exact readers), length stress that pads with distractors rather than blanks (L90/AUC), the statistics of honest comparison (paired SEs, selection inflation), and the two-timescale protocol — composite predictor and probe signature — where pilot B's book-side prerequisites close.

Synthesis

  1. Week 17 implemented

    Niche-pilot integration: from curriculum to research output

    The crown-jewel chapter — how the 17-chapter curriculum composes into the two research pilots (C1 symplectic integrators, B two-timescale benchmarks) and the broader 13-niche portfolio, with the instruments of Chapters 6, 10, 14, 15, and 16 run end-to-end on idealized systems as the reproducible template the pilots fill with trained-model data.