Styling fixes

neural-nets/A_Neural_Algorithm_for_Artistic_Style.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: A Neural Algorithm of Artistic Style
-**Authors**: Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
-**Link**: http://arxiv.org/abs/1508.06576
-**Tags**: Neural Network, Art, VGG, Gram Matrix, Texture
-**Year**: 2015
+* **Title**: A Neural Algorithm of Artistic Style
+* **Authors**: Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
+* **Link**: http://arxiv.org/abs/1508.06576
+* **Tags**: Neural Network, Art, VGG, Gram Matrix, Texture
+* **Year**: 2015
 
 # Summary
 

neural-nets/Batch_Normalization.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
-**Authors**: Sergey Ioffe, Christian Szegedy
-**Link**: http://arxiv.org/abs/1502.03167
-**Tags**: Neural Network, Performance, Covariate Shift, Regularization
-**Year**: 2015
+* **Title**: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
+* **Authors**: Sergey Ioffe, Christian Szegedy
+* **Link**: http://arxiv.org/abs/1502.03167
+* **Tags**: Neural Network, Performance, Covariate Shift, Regularization
+* **Year**: 2015
 
 # Summary
 
@@ -14,9 +14,9 @@
   * BN essentially performs Whitening to the intermediate layers of the networks.
 
 * How its calculated:
-  * The basic formula is `x\* = (x - E[x]) / sqrt(var(x))`, where `x\*` is the new value of a single component, `E[x]` is its mean within a batch and `var(x)` is its variance within a batch.
-  * BN extends that formula further to `x\*\* = gamma \* x\* + beta`, where `x\*\*` is the final normalized value. `gamma` and `beta` are learned per layer. They make sure that BN can learn the identity function, which is needed in a few cases.
-  * For convolutions, every layer/filter/kernel is normalized on its own (linear layer: each neuron/node/component). That means that every generated value ("pixel") is treated as an example. If we have a batch size of N and the image generated by the convolution has width=P and height=Q, we would calculate the mean (E) over `N\*P\*Q` examples (same for the variance).
+  * The basic formula is `x* = (x - E[x]) / sqrt(var(x))`, where `x*` is the new value of a single component, `E[x]` is its mean within a batch and `var(x)` is its variance within a batch.
+  * BN extends that formula further to `x** = gamma * x* + beta`, where `x**` is the final normalized value. `gamma` and `beta` are learned per layer. They make sure that BN can learn the identity function, which is needed in a few cases.
+  * For convolutions, every layer/filter/kernel is normalized on its own (linear layer: each neuron/node/component). That means that every generated value ("pixel") is treated as an example. If we have a batch size of N and the image generated by the convolution has width=P and height=Q, we would calculate the mean (E) over `N*P*Q` examples (same for the variance).
 
 * Theoretical effects:
   * BN reduces *Covariate Shift*. That is the change in distribution of activation of a component. By using BN, each neuron's activation becomes (more or less) a gaussian distribution, i.e. its usually not active, sometimes a bit active, rare very active.
@@ -64,7 +64,7 @@
   * Each feature (component) is normalized individually. (Due to cost, differentiability.)
   * Normalization according to: `componentNormalizedValue = (componentOldValue - E[component]) / sqrt(Var(component))`
   * Normalizing each component can reduce the expressitivity of nonlinearities. Hence the formula is changed so that it can also learn the identiy function.
-  * Full formula: `newValue = gamma \* componentNormalizedValue + beta` (gamma and beta learned per component)
+  * Full formula: `newValue = gamma * componentNormalizedValue + beta` (gamma and beta learned per component)
   * E and Var are estimated for each mini batch.
   * BN is fully differentiable. Formulas for gradients/backpropagation are at the end of chapter 3 (page 4, left).
 

neural-nets/Deep_Residual_Learning_for_Image_Recognition.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Deep Residual Learning for Image Recognition
-**Authors**: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
-**Link**: http://arxiv.org/abs/1512.03385
-**Tags**: Neural Network, Residual, Deep Architectures
-**Year**: 2015
+* **Title**: Deep Residual Learning for Image Recognition
+* **Authors**: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
+* **Link**: http://arxiv.org/abs/1512.03385
+* **Tags**: Neural Network, Residual, Deep Architectures
+* **Year**: 2015
 
 # Summary
 

neural-nets/ELUs.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Fast and Accurate Deep Networks Learning By Exponential Linear Units (ELUs)
-**Authors**: Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter
-**Link**: http://arxiv.org/abs/1511.07289
-**Tags**: Neural Network, activation, nonlinearity, ReLU, ELU, PReLU, LeakyReLU
-**Year**: 2015
+* **Title**: Fast and Accurate Deep Networks Learning By Exponential Linear Units (ELUs)
+* **Authors**: Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter
+* **Link**: http://arxiv.org/abs/1511.07289
+* **Tags**: Neural Network, activation, nonlinearity, ReLU, ELU, PReLU, LeakyReLU
+* **Year**: 2015
 
 # Summary
 

neural-nets/Fractional_Max_Pooling.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Fractional Max-Pooling
-**Authors**: Benjamin Graham
-**Link**: http://arxiv.org/abs/1412.6071
-**Tags**: Neural Network, Pooling
-**Year**: 2015
+* **Title**: Fractional Max-Pooling
+* **Authors**: Benjamin Graham
+* **Link**: http://arxiv.org/abs/1412.6071
+* **Tags**: Neural Network, Pooling
+* **Year**: 2015
 
 # Summary
 

neural-nets/Generative_Adversarial_Networks.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Generative Adversarial Networks
-**Authors**: Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
-**Link**: http://arxiv.org/abs/1406.2661
-**Tags**: Neural Network, GAN, generative models, unsupervised learning
-**Year**: 2014
+* **Title**: Generative Adversarial Networks
+* **Authors**: Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
+* **Link**: http://arxiv.org/abs/1406.2661
+* **Tags**: Neural Network, GAN, generative models, unsupervised learning
+* **Year**: 2014
 
 # Summary
 

neural-nets/Inception_v4.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
-**Authors**: Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke
-**Link**: http://arxiv.org/abs/1602.07261v1
-**Tags**: Neural Network, Inception, Residual
-**Year**: 2016
+* **Title**: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
+* **Authors**: Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke
+* **Link**: http://arxiv.org/abs/1602.07261v1
+* **Tags**: Neural Network, Inception, Residual
+* **Year**: 2016
 
 # Summary
 

neural-nets/Weight_Normalization.md

@@ -1,10 +1,10 @@
 # Paper
 
-**Title**: Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
-**Authors**: Tim Salimans, Diederik P. Kingma
-**Link**: http://arxiv.org/abs/1602.07868
-**Tags**: Neural Network, Normalization, VAE
-**Year**: 2016
+* **Title**: Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
+* **Authors**: Tim Salimans, Diederik P. Kingma
+* **Link**: http://arxiv.org/abs/1602.07868
+* **Tags**: Neural Network, Normalization, VAE
+* **Year**: 2016
 
 # Summary