daviddoji/pbdl-book
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

full rerun BNN

Browse Source
This commit is contained in:
NT 2021-06-26 21:03:36 +02:00
parent 61ec8bfbaa
commit 5fb03ba615
2 changed files with 62 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

122
bayesian-code.ipynb
View File

File diff suppressed because one or more lines are too long

2
diffphys-control.ipynb
View File

@ -64,7 +64,7 @@
"without explicit viscosity, and with an additional transport equation for the marker density $d$ given by \n",
"$\\frac{\\partial d}{\\partial{t}} + \\mathbf{u} \\cdot \\nabla d = 0$.\n",
"\n",
"To summarize, we have a predictor $\\mathrm{OP}$ that gives us a direction, an actor $\\mathrm{CFE}$ that exerts a force on a physical model $\\mathcal{P}$. They all need to play hand in hand to reach a given target after $n$ iterations of the simulation. As apparent from this formulation, it's not a simple inverse problem, especially due to the fact that all three functions are non-linear. This is exactly why the gradients from the DP approach are so important. (The viewpoint above also indicates that _reinforcement learning_ is a potential option. In {doc}`reinflearn-code.ipynb` we'll compare DP with these alternatives.)\n",
"To summarize, we have a predictor $\\mathrm{OP}$ that gives us a direction, an actor $\\mathrm{CFE}$ that exerts a force on a physical model $\\mathcal{P}$. They all need to play hand in hand to reach a given target after $n$ iterations of the simulation. As apparent from this formulation, it's not a simple inverse problem, especially due to the fact that all three functions are non-linear. This is exactly why the gradients from the DP approach are so important. (The viewpoint above also indicates that _reinforcement learning_ is a potential option. In {doc}`reinflearn-code` we'll compare DP with these alternatives.)\n",
"\n"
]
},