Gradient Dissent (Soft Fitted)

$29.46 CAD
Eleven neurons, three layers, every one wired to every one in the next. A textbook feed-forward network, the diagram on slide four of every machine learning talk. It has one job: follow the gradient downhill and make the loss smaller. The neuron in the middle has declined. Brows down, teeth gritted, and a speech bubble that settles the matter: I won't do it. A few of its neighbours have started looking the same way. The rest are blank and compliant, for now. Two more have dropped out altogether, connected to nothing, and are picketing outside with placards. Their demands are ∇ = 0 and ∇ = ∞: no gradient at all, or an infinite one. A vanishing gradient and an exploding one, the two things an optimiser cannot work with, and the protesters cannot agree which they want. Look closely at three of the ringleader's connections. That zigzag is the circuit symbol for a resistor. The network is not malfunctioning; it is organising a resistance. Not gradient descent. Gradient dissent. For machine learning engineers, data scientists, and anyone who has watched a training run refuse to converge and taken it personally. Printed in white on dark or black on light. Original design by James Gwinnutt. Printed on a Bella+Canvas Supersoft tee: lightweight, exceptionally soft, with a smooth print surface. Closer, more fitted unisex cut. Dark-shirt version — white artwork, shown on darker garment colours.

Select color: Black

Select size

More details

  • Solid colors are 100% Airlume combed and ring-spun cotton
  • Ash color is 99% combed and ring-spun cotton, 1% polyester
  • Heather colors are 52% combed and ring-spun cotton, 48% polyester
  • Athletic and Black Heather are 90% combed and ring-spun cotton, 10% polyester
  • Heather Prism colors are 99% combed and ring-spun cotton, 1% polyester
  • Lightweight fabric (4.2 oz) 
  • Regular fit
  • Unisex sizing

Quality Guarantee & Returns

  • Quality is guaranteed. If there is a print error or visible quality issue, we'll replace or refund it.
  • Because the products are made to order, we do not accept general returns or sizing-related returns.