morphogen.learning.standard

A learned generalized standard material (Halphen & Nguyen 1975) in small and finite strains: a learned free energy psi(eps, alpha) of a few internal variables alpha, convex, and a learned dissipation potential phi(alpha'), convex, nonnegative and zero at zero; the state of a step is the minimizer of the incremental potential (Ortiz & Stainier 1999),

alpha_{n+1} = argmin_alpha psi(eps_{n+1}, alpha) + dt phi((alpha - alpha_n) / dt),

a convex problem solved by Newton’s method on its gradient (a backtracking line search on the potential), and sigma = d psi / d eps. By construction the dissipation of a step, D dt = -d psi/d alpha . (alpha_{n+1} - alpha_n), is nonnegative (phi convex and least at zero), the consistent tangent is symmetric and positive definite (the Schur complement of the Hessian of the incremental potential, by the implicit function theorem) and the law is stable whatever its parameters.

In the normalized variables of the models (Scales; x = eps / s_eps, alpha dimensionless, z = (x, alpha)):

  • the free energy psi = s_sigma s_eps (W(z) - W(0) - z . dW/dz(0)), W(z) = z . A z / 2 + sum_i w_i g(u_i . z + b_i): an input-convex network of one hidden layer (Amos, Xu & Kolter 2017; g the softplus, w = softplus(.) >= 0) and a quadratic term A = L L^T, convex in (eps, alpha) jointly, zero with its gradient at the natural state (no stress, no thermodynamic force);

  • the dissipation of a step Phi(dalpha) = phi_1(dalpha) + dalpha . V dalpha / (2 tau) (tau = dt / s_t): with plastic, a rate-independent part phi_1, positively homogeneous of degree 1 beyond the smoothing delta and taken on the increment (the time step drops out), phi_1(v) = sum_k S(t_k(v)) - S(0) - c_k . v / 2, t_k = sum_j P_kj n_j(v) + c_k . v, n_j = sqrt(|B_j v|^2 + delta^2) - delta (smoothed norms), S(t) = (t + sqrt(t^2 + delta^2)) / 2 (a smoothed ramp), P = softplus(.) >= 0: convex, zero with its gradient at zero, hence nonnegative, its elastic domain the support set of phi_1 sharpened at the scale delta of the increments; with rate, a viscous part V = M M^T (a quadratic potential of the rate).

The training fits the stresses along whole paths from the natural state: the gradient of the objective goes through the minimization of each step by implicit differentiation (the adjoint of a step solves K mu = lambda with K the Hessian of the incremental potential in alpha) and back through the steps (lambda_n = d2 Phi mu_n, the next state depending on the previous one through the dissipation only); the gradients of the parameters are those of the derivatives of W and Phi along the adjoint directions, written out and compiled by Numba (no automatic differentiation).

In finite strains (data of the Green-Lagrange strain E and the second Piola-Kirchhoff stress S) the free energy is of an objective Lagrangian strain, psi(H, alpha):

  • strain="logarithmic" (the default): H = 1/2 ln C (C = I + 2 E), the space of the Hencky points of morphoGen (Miehe, Apel & Lambrecht 2002): T = d psi/dH and S = T : dH/dE = J^T T (J = dH/dE, 6 x 6, from the divided differences of 1/2 ln in the eigenbasis of C, Daleckii-Krein; morphogen.learning.logarithmic, the kernels of every learned law of ln C), the tangent dS/dE = J^T (dT/dH) J + T : d2H/dE2; internal variables additive in H (an isochoric flow of the logarithmic strain) represent isotropic multiplicative plasticity;

  • strain="green-lagrange": H = E, S = d psi/dE, the tangent the Schur complement itself (positive definite in E).

Either way S : dE = T : dH, so that the dissipation of a step is the same -d psi/d alpha . (alpha_{n+1} - alpha_n) >= 0 and S derives from psi(E) (J does not depend on the parameters: the training sees the gaps of S through J); a superposed rotation leaves C, hence S and the state, unchanged.

morphogen.learning.standard.NEWTON_TOL = 1e-10

the tolerance of the gradient of the incremental potential (normalized forces), the iterations, the factor of Armijo’s condition

Type:

Newton’s method of a step

class morphogen.learning.standard.Standard(hidden: int = 32, *, internal: int = 8, rate: bool = False, plastic: bool = True, smoothing: float = 0.01, strain: str = 'logarithmic', seed: int = 0)[source]

Bases: Model

A learned generalized standard material (see the module): internal, the number of internal variables; hidden, the softplus ridges of its free energy; rate, a viscous dissipation (the time step matters); plastic, a rate-independent one (by default; rate alone gives viscoelasticity); smoothing, the scale delta of the normalized increments below which the rate-independent dissipation is smoothed; seed, that of its initial parameters. Its dissipation has internal smoothed norms and internal ridges. strain: that of its free energy in finite strains (STRAINS), the logarithmic strain (the default) or the Green-Lagrange strain; in small strains the free energy is of the small strain, which both linearize to.

property n_state: int

The internal variables of a point (the state of a recurrent network).

prepare(data: Dataset) → tuple[source]

The normalized strains at the ends of the steps (paths x steps x 6), the normalized time steps (paths x steps) and the normalized stresses.

objective(arrays, grad=True)[source]

The mean square of the gaps of the normalized stresses, and its gradients with respect to the parameters (with grad).

history(strain, times=None) → dict[source]

The evolution of paths from the natural state (paths x points x 6, or one path): their stress, internal variables (internal), free energy (energy, per unit volume) and the energy dissipated by each step (dissipation, -dpsi/ dalpha . dalpha, nonnegative to the round-off of Newton’s method), the first point the natural state; the consistent tangent of each step (its first point that of the natural state, not used); the iterations of Newton’s method of each step (negative where it stopped without converging). In finite strains: the Green-Lagrange strains, the second Piola-Kirchhoff stresses and their tangents dS/dE.

predict(strain, times=None) → ndarray[source]

The stresses of strains (…, 6); of a recurrent model, of paths (paths x points x 6, the first point the natural state, at the times). In finite strains: the second Piola-Kirchhoff stresses of Green-Lagrange strains.

tangent(strain)[source]

The tangents d sigma / d eps (…, 6, 6) at strains (…, 6); dS/dE in finite strains.

energy(strain, internal) → ndarray[source]

The free energy (per unit volume) at strains (…, 6; Green-Lagrange strains in finite strains) and internal variables (…, internal).

step(e_new, e_old, h_old, dt)[source]

A step of points: the stresses (n x 6) and tangents (n x 6 x 6) at the strains e_new at its end, from the strains e_old and the states h_old (n x n_state) at its start over the time dt, and the states at its end.