This paper starts by introducing a trick to reduce the variance of stochastic gradient variational Bayes (SGVB) estimators. In neural networks, SGVB consists in learning a variational (e.g. diagonal Gaussian) posterior over the weights and biases of neural networks, through a procedure that (for the most part) alternates between adding (Gaussian) noise to the model's parameters and then performing a model update with backprop. 

The authors present a local reparameterization trick, which exploits the fact that the Gaussian noise added into the weights could instead be added directly into the pre-activation (i.e. before the activation fonction) vectors during forward propagation. This is due to the fact that computing the pre-activation is a linear operation, thus noise at that level is also Gaussian. The advantage of doing so is that, in the context of minibatch training, one can efficiently then add independent noise to the pre-activation vectors for each example of the minibatch. The nature of the local reparameterization trick implies that this is equivalent to using one corrupted version of the weights for each example in the minibatch, something that wouldn't be practical computationally otherwise. This is in fact why, in normal SGVB, previous work would normally use a single corrupted version of the weights for all the minibatch. 

The authors demonstrate that using the local reparameterization trick yields stochastic gradients with lower variance, which should improve the speed of convergence.

Then, the authors demonstrate that the Gaussian version of dropout (one that uses multiplicative Gaussian noise, instead of 0-1 masking noise) can be seen as the local reparameterization trick version of a SGVB objective, with some specific prior and variational posterior. In this SGVB view of Gaussian dropout, the dropout rate is an hyper-parameter of this prior, which can now be tuned by optimizing the variational lower bound of SGVB. In other words, we now have a method to also train the dropout rate! Moreover, it becomes possible to tune an individual dropout rate parameter for each layer, or even each parameter of the model.

Experiments on MNIST confirm that tuning that parameter works and allows to reach good performance of various network sizes, compared to using a default dropout rate. 


##### My two cents

This is another thought provoking connection between Bayesian learning and dropout. Indeed, while Deep GPs have allowed to make a Bayesian connection with regular (binary) dropout learning \cite{journals/corr/GalG15}, this paper sheds light on a neat Bayesian connection for the Gaussian version of dropout. This is great, because it suggests that Gaussian dropout training is another legit way of modeling uncertainty in the parameters of neural networks. It's also nice that that connection also yielded a method for tuning the dropout rate automatically.

I hope future work (by the authors or by others) can evaluate the quality of the corresponding variational posterior in terms of estimating uncertainty in the network and, in particular, in obtaining calibrated output probabilities.

Little detail: I couldn't figure out whether the authors tuned a single dropout rate for the whole network, or used many rates, for instance one per parameter, as they suggest can be done.

The main contribution of this paper is introducing a new transformation that the authors call Batch Normalization (BN). The need for BN comes from the fact that during the training of deep neural networks (DNNs) the distribution of each layer’s input change. This phenomenon is called internal covariate shift (ICS).

#### What is BN?
Normalize each (scalar) feature independently with respect to the mean and variance of the mini batch. Scale and shift the normalized values with two new parameters (per activation) that will be learned. The BN consists of making normalization part of the model architecture.

#### What do we gain?
According to the author, the use of BN provides a great speed up in the training of DNNs. In particular, the gains are greater when it is combined with higher learning rates. In addition, BN works as a regularizer for the model which allows to use less dropout or less L2 normalization. Furthermore, since the distribution of the inputs is normalized, it also allows to use sigmoids as activation functions without the saturation problem.

#### What follows?
This seems to be specially promising for training recurrent neural networks (RNNs). The vanishing and exploding gradient problems \cite{journals/tnn/BengioSF94} have their origin in the iteration of transformation that scale up or down the activations in certain directions (eigenvectors). It seems that this regularization would be specially useful in this context since this would allow the gradient to flow more easily. When we unroll the RNNs, we usually have ultra deep networks.

#### Like
* Simple idea that seems to improve training.
* Makes training faster.
* Simple to implement. Probably.
* You can be less careful with initialization.

#### Dislike
* Does not work with stochastic gradient descent (minibatch size = 1).
* This could reduce the parallelism of the algorithm since now all the examples in a mini batch are tied.
* Results on ensemble of networks for ImageNet makes it harder to evaluate the relevance of BN by itself. (Although they do mention the performance of a single model).

Mask RCNN takes off from where Faster RCNN left, with some augmentations aimed at bettering instance segmentation (which was out of scope for FRCNN). Instance segmentation was achieved remarkably well in *DeepMask* , *SharpMask* and later *Feature Pyramid Networks* (FPN).

Faster RCNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is most evident in how RoIPool , the de facto core operation for attending to instances, performs coarse spatial quantization for feature extraction. Mask RCNN fixes that by introducing RoIAlign in place of RoIPool.

#### Methodology

Mask RCNN retains most of the architecture of Faster RCNN. It adds the a third branch for segmentation. The third branch takes the output from RoIAlign layer and predicts binary class masks for each class.

##### Major Changes and intutions

**Mask prediction**

Mask prediction segmentation predicts a binary mask for each RoI using fully convolution - and the stark difference being usage of *sigmoid* activation for predicting final mask instead of *softmax*, implies masks don't compete with each other. This *decouples* segmentation from classification. The class prediction branch is used for class prediction and for calculating loss, the mask of predicted loss is used calculating Lmask.

Also, they show that a single class agnostic mask prediction works almost as effective as separate mask for each class, thereby supporting their method of decoupling classification from segmentation

**RoIAlign**

RoIPool first quantizes a floating-number RoI to the discrete granularity of the feature map, this quantized RoI is then subdivided into spatial bins which are themselves quantized, and finally feature values covered by each bin are aggregated (usually by max pooling). Instead of  quantization of the RoI boundaries
or bin bilinear interpolation is used to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and aggregate the result (using max or average).

**Backbone architecture**

Faster RCNN uses a VGG like structure for extracting features from image, weights of which were shared among RPN and region detection layers. Herein, authors experiment with 2 backbone architectures - ResNet based VGG like in FRCNN and ResNet based [FPN](http://www.shortscience.org/paper?bibtexKey=journals/corr/LinDGHHB16) based. FPN uses convolution feature maps from previous layers and recombining them to produce pyramid of feature maps to be used for prediction instead of single-scale feature layer (final output of conv layer before connecting to fc layers was used in Faster RCNN) 

**Training Objective**

The training objective looks like this 
![](https://i.imgur.com/snUq73Q.png)

Lmask is the addition from Faster RCNN. The method to calculate was mentioned above

#### Observation

Mask RCNN performs significantly better than COCO instance segmentation winners *without any bells and whiskers*. Detailed results are available in the paper

Everyone has been thinking about how to apply GANs to discrete sequence data for the past year or so. This paper presents the model that I would guess most people thought of as the first-thing-to-try:

1. Build a recurrent generator model which samples from its softmax outputs at each timestep.
2. Pass sampled sequences to a recurrent discriminator model which distinguishes between sampled sequences and real-data sequences.
3. Train the discriminator under the standard GAN loss.
4. Train the generator with a REINFORCE (policy gradient) objective, where each trajectory is assigned a single episodic reward: the score assigned to the generated sequence by the discriminator.

Sounds hacky, right? We're learning a generator with a high-variance model-free reinforcement learning algorithm, in a very seriously non-stationary environment. (Here the "environment" is a discriminator being jointly learned with the generator.)

There's just one trick in this paper on top of that setup: for non-terminal states, the reward is defined as the *expectation* of the discriminator score after stochastically generating from that state forward. To restate using standard (somewhat sloppy) RL syntax, in different terms than the paper: (under stochastic sequential policy $\pi$, with current state $s_t$, trajectory $\tau_{1:T}$ and discriminator $D(\tau)$)

$$r_t = \mathbb E_{\tau_{t+1:T} \sim \pi(s_t)} \left[ D(\tau_{1:T}) \right]$$

The rewards are estimated via Monte Carlo — i.e., just take the mean of $N$ rollouts from each intermediate state. They claim this helps to reduce variance. That makes intuitive sense, but I don't see any results in the paper demonstrating the effect of varying $N$.

---

Yep, so it turns out that this sort of works.. with a big caveat:

## The big caveat

Graph from appendix:

![](https://www.dropbox.com/s/5fqh6my63sgv5y4/Bildschirmfoto%202016-09-27%20um%2021.34.44.png?raw=1)

SeqGANs don't work without supervised pretraining. Makes sense — with a cold start, the generator just samples a bunch of nonsense and the discriminator overfits. Both the generator and discriminator are pretrained on supervised data in this paper (see Algorithm 1).

I think it must be possible to overcome this with the proper training tricks and enough sweat. But it's probably more worth our time to address the fundamental problem here of developing better RL for structured prediction tasks.

Sharif et al. study the effectiveness of $L_p$ norms for creating adversarial perturbations. In this context, their main discussion revolves around whether $L_p$ norms are sufficient and/or necessary for perceptual similarity. Their main conclusion is that $L_p$ norms are neither necessary nor sufficient to ensure perceptual similarity. For example, an adversarial example might be within a specific $L_p$ bal, but humans might still identify it as not similar enough to the originally attacked sample; on the other hand, there are also some imperceptible perturbations that usually extend beyond a reasonable $L_p$ ball. Such transformatons might for example include small rotations or translation. These findings are interesting because it indicates that our current model, or approximation, or perceptual similarity is not meaningful in all cases.

Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

### What is BN:
  * Batch Normalization (BN) is a normalization method/layer for neural networks.
  * Usually inputs to neural networks are normalized to either the range of [0, 1] or [-1, 1] or to mean=0 and variance=1. The latter is called *Whitening*.
  * BN essentially performs Whitening to the intermediate layers of the networks.

### How its calculated:
  * The basic formula is $x^* = (x - E[x]) / \sqrt{\text{var}(x)}$, 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.
  * Covariate Shift is undesirable, because the later layers have to keep adapting to the change of the type of distribution (instead of just to new distribution parameters, e.g. new mean and variance values for gaussian distributions).
  * BN reduces effects of exploding and vanishing gradients, because every becomes roughly normal distributed. Without BN, low activations of one layer can lead to lower activations in the next layer, and then even lower ones in the next layer and so on.

### Practical effects:
  * BN reduces training times. (Because of less Covariate Shift, less exploding/vanishing gradients.)
  * BN reduces demand for regularization, e.g. dropout or L2 norm. (Because the means and variances are calculated over batches and therefore every normalized value depends on the current batch. I.e. the network can no longer just memorize values and their correct answers.)
  * BN allows higher learning rates. (Because of less danger of exploding/vanishing gradients.)
  * BN enables training with saturating nonlinearities in deep networks, e.g. sigmoid. (Because the normalization prevents them from getting stuck in saturating ranges, e.g. very high/low values for sigmoid.)


![MNIST and neuron activations](https://raw.githubusercontent.com/aleju/papers/master/neural-nets/images/Batch_Normalization__performance_and_activations.png?raw=true "MNIST and neuron activations")

*BN applied to MNIST (a), and activations of a randomly selected neuron over time (b, c), where the middle line is the median activation, the top line is the 15th percentile and the bottom line is the 85th percentile.*

-------------------------

### Rough chapter-wise notes

* (2) Towards Reducing Covariate Shift
  * Batch Normalization (*BN*) is a special normalization method for neural networks.
  * In neural networks, the inputs to each layer depend on the outputs of all previous layers.
  * The distributions of these outputs can change during the training. Such a change is called a *covariate shift*.
  * If the distributions stayed the same, it would simplify the training. Then only the parameters would have to be readjusted continuously (e.g. mean and variance for normal distributions).
  * If using sigmoid activations, it can happen that one unit saturates (very high/low values). That is undesired as it leads to vanishing gradients for all units below in the network.
  * BN fixes the means and variances of layer inputs to specific values (zero mean, unit variance).
  * That accomplishes:
    * No more covariate shift.
    * Fixes problems with vanishing gradients due to saturation.
  * Effects:
    * Networks learn faster. (As they don't have to adjust to covariate shift any more.)
    * Optimizes gradient flow in the network. (As the gradient becomes less dependent on the scale of the parameters and their initial values.)
    * Higher learning rates are possible. (Optimized gradient flow reduces risk of divergence.)
    * Saturating nonlinearities can be safely used. (Optimized gradient flow prevents the network from getting stuck in saturated modes.)
    * BN reduces the need for dropout. (As it has a regularizing effect.)
  * How BN works:
    * BN normalizes layer inputs to zero mean and unit variance. That is called *whitening*.
    * Naive method: Train on a batch. Update model parameters. Then normalize. Doesn't work: Leads to exploding biases while distribution parameters (mean, variance) don't change.
    * A proper method has to include the current example *and* all previous examples in the normalization step.
    * This leads to calculating in covariance matrix and its inverse square root. That's expensive. The authors found a faster way.

* (3) Normalization via Mini-Batch Statistics
  * 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)
  * 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).

* (3.1) Training and Inference with Batch-Normalized Networks
  * During test time, E and Var of each component can be estimated using all examples or alternatively with moving averages estimated during training.
  * During test time, the BN formulas can be simplified to a single linear transformation.

* (3.2) Batch-Normalized Convolutional Networks
  * Authors recommend to place BN layers after linear/fully-connected layers and before the ninlinearities.
  * They argue that the linear layers have a better distribution that is more likely to be similar to a gaussian.
  * Placing BN after the nonlinearity would also not eliminate covariate shift (for some reason).
  * Learning a separate bias isn't necessary as BN's formula already contains a bias-like term (beta).
  * For convolutions they apply BN equally to all features on a feature map. That creates effective batch sizes of m\*pq, where m is the number of examples in the batch and p q are the feature map dimensions (height, width). BN for linear layers has a batch size of m.
  * gamma and beta are then learned per feature map, not per single pixel. (Linear layers: Per neuron.)

* (3.3) Batch Normalization enables higher learning rates
  * BN normalizes activations.
  * Result: Changes to early layers don't amplify towards the end.
  * BN makes it less likely to get stuck in the saturating parts of nonlinearities.
  * BN makes training more resilient to parameter scales.
  * Usually, large learning rates cannot be used as they tend to scale up parameters. Then any change to a parameter amplifies through the network and can lead to gradient explosions.
  * With BN gradients actually go down as parameters increase. Therefore, higher learning rates can be used.
  * (something about singular values and the Jacobian)

* (3.4) Batch Normalization regularizes the model
  * Usually: Examples are seen on their own by the network.
  * With BN: Examples are seen in conjunction with other examples (mean, variance).
  * Result: Network can't easily memorize the examples any more.
  * Effect: BN has a regularizing effect. Dropout can be removed or decreased in strength.

* (4) Experiments
* (4.1) Activations over time
** They tested BN on MNIST with a 100x100x10 network. (One network with BN before each nonlinearity, another network without BN for comparison.)
** Batch Size was 60.
** The network with BN learned faster. Activations of neurons (their means and variances over several examples) seemed to be more consistent during training.
** Generalization of the BN network seemed to be better.

* (4.2) ImageNet classification
** They applied BN to the Inception network.
** Batch Size was 32.
** During training they used (compared to original Inception training) a higher learning rate with more decay, no dropout, less L2, no local response normalization and less distortion/augmentation.
** They shuffle the data during training (i.e. each batch contains different examples).
** Depending on the learning rate, they either achieve the same accuracy (as in the non-BN network) in 14 times fewer steps (5x learning rate) or a higher accuracy in 5 times fewer steps (30x learning rate).
** BN enables training of Inception networks with sigmoid units (still a bit lower accuracy than ReLU).
** An ensemble of 6 Inception networks with BN achieved better accuracy than the previously best network for ImageNet.

* (5) Conclusion
** BN is similar to a normalization layer suggested by Gülcehre and Bengio. However, they applied it to the outputs of nonlinearities.
** They also didn't have the beta and gamma parameters (i.e. their normalization could not learn the identity function).

FaceNet directly maps face images to $\mathbb{R}^{128}$ where distances directly correspond to a measure of face similarity. They use a triplet loss function. The triplet is (face of person A, other face of person A, face of person which is not A). Later, this is called (anchor, positive, negative).

The loss function is learned and inspired by LMNN. The idea is to minimize the distance between the two images of the same person and maximize the distance to the other persons image.

## LMNN

Large Margin Nearest Neighbor (LMNN) is learning a pseudo-metric

$$d(x, y) = (x -y) M  (x -y)^T$$

where $M$ is a positive-definite matrix. The only difference between a pseudo-metric and a metric is that $d(x, y) = 0 \Leftrightarrow x = y$ does not hold.

## Curriculum Learning: Triplet selection

Show simple examples first, then increase the difficulty. This is done by selecting the triplets.

They use the triplets which are *hard*. For the positive example, this means the distance between the anchor and the positive example is high. For the negative example this means the distance between the anchor and the negative example is low.

They want to have

$$||f(x_i^a) - f(x_i^p)||_2^2 + \alpha < ||f(x_i^a) - f(x_i^n)||_2^2$$

where $\alpha$ is a margin and $x_i^a$ is the anchor, $x_i^p$ is the positive face example and $x_i^n$ is the negative example. They increase $\alpha$ over time. It is crucial that $f$ maps the images not in the complete $\mathbb{R}^{128}$, but on the unit sphere. Otherwise one could double $\alpha$ by simply making $f' = 2 \cdot f$.

## Tasks

* **Face verification**: Is this the same person?
* **Face recognition**: Who is this person?

## Datasets

* 99.63% accuracy on Labeled FAces in the Wild (LFW)
* 95.12% accuracy on YouTube Faces DB

## Network

Two models are evaluated: The [Zeiler & Fergus model](http://www.shortscience.org/paper?bibtexKey=journals/corr/ZeilerF13)  and an architecture based on the [Inception model](http://www.shortscience.org/paper?bibtexKey=journals/corr/SzegedyLJSRAEVR14).

## See also

* [DeepFace](http://www.shortscience.org/paper?bibtexKey=conf/cvpr/TaigmanYRW14#martinthoma)

This paper presents a combination of the inception architecture
with residual networks. This is done by adding a shortcut connection
to each inception module. This can alternatively be seen as a resnet where
the 2 conv layers are replaced by a (slightly modified) inception module.
The paper (claims to) provide results against the hypothesis that adding residual
connections improves training, rather increasing the model size is what makes the difference.

3D Image Classification is one of the utmost important requirements in healthcare. But due to huge size of such images and less amount of data, it has become difficult to train traditional end-to-end models of classification such as AlexNet, Resnet, VGG. Major approaches considered for 3D images use slices of the image and not the image as whole. This approach at times leads to loss of information across third axis. 

The paper uses the complete 3D image for training, and since the number of images are less we use unsupervised techniques for weights initialization and fine tune the fully connected layers using supervised learning for classification. The major contribution of the paper is the extension of 2D Convolutional Auto-encoders to 3D Domain and taking it further for MRI Classification which can be useful in numerous other applications.

**Algorithm**

1. Train 3D Convolution Auto-encoders using [CADDementia dataset](https://grand-challenge.org/site/caddementia/home/) 
2. Extract the encoder layer from the trained auto-encoders and add fully connected layers to it, followed by softmax
3. Train and test the classification model using [ADNI data](http://adni.loni.usc.edu/)

**3D CAN Model**

This model is 3D extension of [2D Convolutional Auto-encoders](http://people.idsia.ch/~ciresan/data/icann2011.pdf) (2D CAN)

![3D Convolutional Auto-encoders](http://i.imgur.com/66y52uQ.png)

Each convolution in encoder is a 3D Convolution followed by ReLU and maxpool, while in decoder, each convolution is a maxunpool followed by 3D Full Convolution and ReLU. In the last decoder block, instead of ReLU, Sigmoid will be used.

Here the weights were shared in the decoder and encoder as specified in [2D CAN](http://people.idsia.ch/~ciresan/data/icann2011.pdf)

**3D Classification model**

![Classification of MRIs using 3D Convolutional Auto-encoders](http://i.imgur.com/3hOeR8o.png)

The weights of the classification model are initialized using the trained 3D-CAN model as mentioned in algorithm.

**Loss Function**

Weighted negative log likelihood for Classification and Mean Squared Error for Unsupervised learning

**Training algorithm**

[Adadelta](https://arxiv.org/abs/1212.5701)

**Results**

Obtained 89.1% on 10-fold cross validation on dataset of 270 patients for classification of MRI into Mild Cognitive Impairment (MCI), Normal Control (NC) and Alzheimer's disease (AD)

**Image Source**

All images are taken from the [paper](https://arxiv.org/abs/1607.00455) itself.

Hein and Andriushchenko give a intuitive bound on the robustness of neural networks based on the local Lipschitz constant. With robustness, the authors refer a small $\epsilon$-ball around each sample; this ball is supposed to describe the region where the neural network predicts a constant class. This means that adversarial examples have to compute changes large enough to leave these robust areas. Larger $\epsilon$-balls imply higher robustness to adversarial examples.

When considering a single example $x$, and a classifier $f = (f_1, \ldots, f_K)^T$ (i.e. in a multi-class setting), the bound can be stated as follows. For $q$ and $p$ such that $\frac{1}{q} + \frac{1}{p} = 1$ and $c$ being the class predicted for $x$, the it holds

$x = \arg\max_j f_j(x + \delta)$

for all $\delta$ with

$\|\delta\|_p \leq \max_{R > 0}\min \left\{\min_{j \neq c} \frac{f_c(x) – f_j(x)}{\max_{y \in B_p(x, R)} \|\nabla f_c(y) - \nabla f_j(y)\|_q}, R\right\}$.

Here, $B_p(x, R)$ describes the $R$-ball around $x$ measured using the $p$-norm. Based on the local Lipschitz constant (in the denominator), the bound essentially measures how far we can deviate from the sample $x$ (measured in the $p$-norm) until $f_j(x) > f_c(x)$ for some $j \neq c$. The higher the local Lipschitz constant, the smaller deviations are allowed, i.e. adversarial examples are easier to find. Note that the bound also depends on the confidence, i.e. the edge  $f_c(x)$ has in comparison to all other $f_j(x)$.

In the remaining paper, the authors also provide bounds for simple classifiers including linear classifiers, kernel methods and two-layer perceptrons (i.e. one hidden layer). For the latter, they also propose a new type of regularization called cross-Lipschitz regularization:

$P(f) = \frac{1}{nK^2} \sum_{i = 1}^n \sum_{l,m = 1}^K \|\nabla f_l(x_i) - \nabla f_m(x_i)\|_2^2$.

This regularization term is intended to reduce the Lipschitz constant locally around training examples. They show experimental results using this regularization on MNIST and CIFAR, see the paper for details.

Also view this summary at [davidstutz.de](https://davidstutz.de/category/reading/).