Bendtorch.linf_b3: def of bendtorch@1.3.0.0
Import: import bendtorch@1.3.0.0/main.bend as Bendtorch
Lines 707-713 of bendtorch@1.3.0.0/main.bend: https://jend.leeeet.dev/read.txt?path=bendtorch@1.3.0.0/main.bend&start_line=707&end_line=713

import Base
import bend-ml-tensor-array@0.1.18.0/main.bend as TA

# the first layer of a model, whose input (the data) needs no gradient, as an input without requires_grad in PyTorch:
# the backward pass computes dW and db only, skipping dX = dY·W (a third of a linear layer's work), and returns zeros
# as dX. Use it only where nothing before the layer has parameters.
def linf_b3(+n: Nat, +i: Nat, +o: Nat, w: TA.Mat<o, i>, b: TA.Mat<1n, o>, gb: TA.Mat<1n, o>, r: TA.MMulTN<o, n, i>) -> Bwd<Lin<i, o>, TA.Mat<n, i>>:
  match r:
    case TA.MMulTN{dy, x, gw}:
      lin_b4(n, i, o, w, b, TA.Mat.zeros(n, i), gw, TA.Mat.col_sums_acc(n, o, dy, gb))

Uses (8):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&name=MMulTN
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&name=Mat
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&name=Mat.col_sums_acc
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&name=Mat.zeros
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=Bwd
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=Lin
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=lin_b4