Commit
·
fca085d
1
Parent(s):
2e084df
Update app.py
Browse files
app.py
CHANGED
|
@@ -103,6 +103,7 @@ iface = gr.Interface(fn=infer,
|
|
| 103 |
description='''This is a demo of PFNs as we describe them in our recent paper (https://openreview.net/forum?id=KSugKcbNf9).
|
| 104 |
Lines represent means and shaded areas are the confidence interval (68.2% quantile). In green, we have the ground truth GP posterior and in blue we have our approximation.
|
| 105 |
We provide three models that are architecturally the same, but with different training budgets.
|
|
|
|
| 106 |
''',
|
| 107 |
article="<p style='text-align: center'><a href='https://arxiv.org/abs/2112.10510'>Paper: Transformers Can Do Bayesian Inference</a></p>",
|
| 108 |
inputs=[
|
|
|
|
| 103 |
description='''This is a demo of PFNs as we describe them in our recent paper (https://openreview.net/forum?id=KSugKcbNf9).
|
| 104 |
Lines represent means and shaded areas are the confidence interval (68.2% quantile). In green, we have the ground truth GP posterior and in blue we have our approximation.
|
| 105 |
We provide three models that are architecturally the same, but with different training budgets.
|
| 106 |
+
The GP (approximated) uses an RBF Kernel with a little noise (1e-4), 0 mean and a length scale of 0.1.
|
| 107 |
''',
|
| 108 |
article="<p style='text-align: center'><a href='https://arxiv.org/abs/2112.10510'>Paper: Transformers Can Do Bayesian Inference</a></p>",
|
| 109 |
inputs=[
|