PMC

CAD model vs. SLM-manufactured prototype: (a) CAD model of the partial RKA endoprosthesis working prototype with the biomimetic MSC-Scaffold; (b) SLM-manufactured partial RKA endoprosthesis working prototype with the biomimetic MSC-Scaffold.

Scatter plots indicate the relative exemplar vs. prototype model fits for each subject. Fits are given in terms of negative log likelihood (i.e., model error) such that lower values reflect better model fit. Each dot represents a single subject and the trendline represents equal prototype and exemplar fit. Dots above the line have better exemplar relative to prototype model fit. Dots below the line have better prototype relative to exemplar model fit. Pie charts indicate the percentage of individual subjects classified as best fit by the prototype model (in blue), the exemplar model (in red), and those similarly fit by the two models (in grey). Model fits were computed separately for the 1^st half of the learning phase (interim tests 1–2, A,D), the 2^nd half of the learning phase (interim tests 3–4, B,E), and the final test (C,F). Source data for all phases can be found in .
Figure 4—source data 1.Behavioral model fits - all phases.

(a) Tensile specimen printed with the pozzolan composite. (b) 3D model of the prototype for precision irrigation. (c) Longitudinal section of the sliced prototype. (d) Prototype sample 3D printed with neat HDPE. (e) Prototype sample 3D printed with composite at 20% pozzolan.

Structure of the prototype-based open deep network (P-ODN) in the initial training phase. The CNN takes knowns as input, and a classification loss is applied to train the initial classification model. Two major modules, the prototype module and the prototype radius module. The prototype module takes the features extracted by CNN as input and learns prototypes for categories. And the prototype radius module takes the prototype-based distances as input, where the distances are calculated in the prototype module, and learns the scope of each category prototype. Finally, the initial training phase outputs an initial model, trained prototypes and prototype radiuses for the incremental training phase later.