Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit b020b7b

Browse files
WIP
1 parent 60bf2ca commit b020b7b

5 files changed

+15
-12
lines changed

‎DifferentiatingPerceptron.ipynb

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -655,7 +655,7 @@
655655
"views": {}
656656
},
657657
"kernelspec": {
658-
"display_name": "Python 3",
658+
"display_name": "Python 3 (ipykernel)",
659659
"language": "python",
660660
"name": "python3"
661661
},
@@ -669,9 +669,9 @@
669669
"name": "python",
670670
"nbconvert_exporter": "python",
671671
"pygments_lexer": "ipython3",
672-
"version": "3.6.7"
672+
"version": "3.12.1"
673673
}
674674
},
675675
"nbformat": 4,
676-
"nbformat_minor": 1
676+
"nbformat_minor": 4
677677
}

‎InformationTheoryOptimization.ipynb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -191,7 +191,7 @@
191191
"\\end{align*}\n",
192192
"where $p_1$ and $p_2$ are probability mass functions and $\\lambda \\in [0,1]$\n",
193193
"\n",
194-
"Proof: Let $X$ be a discrete random variable with possible outcomes $\\mathcal{X} := {x_i, i \\in 0,1,\\dots N-1}$ and let $u(x)$ be the probability mass function of a discrete uniform distribution on $X \\in \\mathcal{X}$. Then, the entropy of an arbitrary probability mass function $p(x)$ can be rewritten as\n",
194+
"Proof: Let $X$ be a discrete random variable with possible outcomes $\\mathcal{X} := {x_i, i \\in 0,1,\\dots N-1}$ and let $u(x)$ be the probability mass function of a discrete uniform distribution on $X \\in \\mathcal{X}$, ie $u(x_i)=\\frac{1}{N}$. Then, the entropy of an arbitrary probability mass function $p(x)$ can be rewritten as\n",
195195
"\n",
196196
"\\begin{align*} \\tag{1.2}\n",
197197
" H(X) &= - \\sum_{i=0}^{N-1} p(x_i)log(p(x_i)) \\\\\n",

‎OptimalTransportWasserteinDistance.ipynb

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -559,7 +559,7 @@
559559
"metadata": {},
560560
"source": [
561561
"### OT and statistical concepts\n",
562-
"Some of the basics to understand the following statements can be found in the notebook \"InformationTheoryOptimization\" this part is also partly a direct reproduction of Marco Cuturi famous article \"Sinkhorn Distances: Lightspeed Computation of Optimal Transport\"\n",
562+
"Some of the basics to understand the following statements can be found in the notebook \"InformationTheoryOptimization\", this part is also partly a direct reproduction of Marco Cuturi famous article \"Sinkhorn Distances: Lightspeed Computation of Optimal Transport\"\n",
563563
"\n",
564564
"I would like to stop and mention that as we now interpret $P$ as a joint probability matrix, we can define its entropy, the marginal probabiilty entropy, and KL-divergence between two different transportation matrix. These takes the form of\n",
565565
"\n",
@@ -579,7 +579,7 @@
579579
"\\begin{align*} \\tag{1.5}\n",
580580
" \\forall r,c \\in \\Sigma_d, \\forall P \\in U(r,c), h(P) \\leq h(r) + h(c)\n",
581581
"\\end{align*}\n",
582-
"ie, by using log-sum inequality, proved in the notebook called InformationTheoryOptimization\n",
582+
"ie, by using log-sum inequality, we proved in the notebook called InformationTheoryOptimization\n",
583583
"\\begin{align*}\\tag{1.6}\n",
584584
" \\sum_{i=0}^{N-1} a_i log\\left(\\frac{a_i}{b_i}\\right) &\\geq \\left(\\sum_{i=0}^{N-1} a_i\\right) log\\left(\\frac{\\sum_{i=0}^{N-1}a_i}{\\sum_{i=0}^{N-1}b_i}\\right)\n",
585585
"\\end{align*}\n",

‎RegularizationByDenoising.ipynb

Lines changed: 8 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
"\n",
1616
"## Introduction\n",
1717
"\n",
18-
"This notebook intends to show what are the next steps in terms of regularized image reconstruction. We will try to focus especially in a framework that allows the introduction of deep learning in a proper mathematical framework that allows for prior and data fitting mitigation called: regularization by denoising (RED).\n",
18+
"This notebook intends to show what are the next steps in terms of regularized image reconstruction. We will try to focus especially in a framework that allows the introduction of deep learning in a proper mathematical framework that allows for prior and data fitting mitigation called: regularization by denoising (RED) but not only.\n",
1919
"\n",
2020
"The following paper guided us to write this notebook:\n",
2121
"\n",
@@ -38,7 +38,10 @@
3838
"https://ieeexplore.ieee.org/document/9107406\n",
3939
"\n",
4040
"* Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition\n",
41-
"https://arxiv.org/abs/2106.03668"
41+
"https://arxiv.org/abs/2106.03668\n",
42+
"\n",
43+
"* Deep inverse\n",
44+
"https://github.com/deepinv/deepinv"
4245
]
4346
},
4447
{
@@ -51,7 +54,7 @@
5154
],
5255
"metadata": {
5356
"kernelspec": {
54-
"display_name": "Python 3",
57+
"display_name": "Python 3 (ipykernel)",
5558
"language": "python",
5659
"name": "python3"
5760
},
@@ -65,9 +68,9 @@
6568
"name": "python",
6669
"nbconvert_exporter": "python",
6770
"pygments_lexer": "ipython3",
68-
"version": "3.8.10"
71+
"version": "3.12.1"
6972
}
7073
},
7174
"nbformat": 4,
72-
"nbformat_minor": 2
75+
"nbformat_minor": 4
7376
}

‎bayesian_ab_testing.ipynb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1960,7 +1960,7 @@
19601960
"name": "python",
19611961
"nbconvert_exporter": "python",
19621962
"pygments_lexer": "ipython3",
1963-
"version": "3.8.6"
1963+
"version": "3.12.1"
19641964
}
19651965
},
19661966
"nbformat": 4,

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /