YuyaoTechnology commited on
Commit
8d690dc
·
verified ·
1 Parent(s): a10a85b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -79,7 +79,7 @@ tags:
79
  <tr><th>Item</th><th>Description</th></tr>
80
  <tr><td>Architecture</td><td>Proprietary HNN hierarchical neural network (physics-reasoning-driven). Two-tier design: a shared backbone learns cross-domain material representations from the 1,035-d fingerprint; on top sit 192 second-level expert sub-models grouped under 17 first-level vertical domains, each fine-tuned on materials that exhibit the target property. Physics-informed regularization embeds symmetry, conservation laws and thermodynamic constraints as soft penalties, so the network outputs physically plausible predictions rather than pure interpolation.</td></tr>
81
  <tr><td>Material descriptors</td><td>1035</td></tr>
82
- <tr><td>Domain sub-models</td><td>192 second-level performance-variable sub-models organized under 17 first-level vertical domains: superconductivity, magnetocaloric, magneto-transport, magnetism, catalysis & surfaces, electronic transport, optics, nuclear & irradiation, mechanics, crystal structure, thermoelectrics, thermodynamics, thermal transport, phonons, ferroelectrics, barocaloric, and fabrication & cost. Each sub-model is a dedicated predictor fine-tuned on materials that exhibit the target property. See category breakdown below.</td></tr>
83
  <tr><td>Input formats</td><td>Natural-language instructions, property targets, composition formulas.</td></tr>
84
  <tr><td>Output formats</td><td>Predicted properties with uncertainty bounds, recommended compositions (Pareto-front candidates), processing parameters (sintering / annealing windows), and ranked experiment proposals.</td></tr>
85
  <tr><td>Training</td><td>Two-stage curriculum: (1) Pre-training on large-scale composition–structure–property records via self-supervised masked-fingerprint / structure reconstruction; (2) Domain fine-tuning with physics-informed loss, active-learning feedback loops, and Bayesian / NSGA-guided candidate selection.</td></tr>
 
79
  <tr><th>Item</th><th>Description</th></tr>
80
  <tr><td>Architecture</td><td>Proprietary HNN hierarchical neural network (physics-reasoning-driven). Two-tier design: a shared backbone learns cross-domain material representations from the 1,035-d fingerprint; on top sit 192 second-level expert sub-models grouped under 17 first-level vertical domains, each fine-tuned on materials that exhibit the target property. Physics-informed regularization embeds symmetry, conservation laws and thermodynamic constraints as soft penalties, so the network outputs physically plausible predictions rather than pure interpolation.</td></tr>
81
  <tr><td>Material descriptors</td><td>1035</td></tr>
82
+ <tr><td>Domain sub-models</td><td>190 second-level performance-variable sub-models organized under 17 first-level vertical domains: superconductivity, magnetocaloric, magneto-transport, magnetism, catalysis & surfaces, electronic transport, optics, nuclear & irradiation, mechanics, crystal structure, thermoelectrics, thermodynamics, thermal transport, phonons, ferroelectrics, barocaloric, and fabrication & cost. Each sub-model is a dedicated predictor fine-tuned on materials that exhibit the target property. See category breakdown below.</td></tr>
83
  <tr><td>Input formats</td><td>Natural-language instructions, property targets, composition formulas.</td></tr>
84
  <tr><td>Output formats</td><td>Predicted properties with uncertainty bounds, recommended compositions (Pareto-front candidates), processing parameters (sintering / annealing windows), and ranked experiment proposals.</td></tr>
85
  <tr><td>Training</td><td>Two-stage curriculum: (1) Pre-training on large-scale composition–structure–property records via self-supervised masked-fingerprint / structure reconstruction; (2) Domain fine-tuning with physics-informed loss, active-learning feedback loops, and Bayesian / NSGA-guided candidate selection.</td></tr>