* Usually GANs transform a noise vector `z` into images. `z` might be sampled from a normal or uniform distribution.
  * The effect of this is, that the components in `z` are deeply entangled.
    * Changing single components has hardly any influence on the generated images. One has to change multiple components to affect the image.
    * The components end up not being interpretable. Ideally one would like to have meaningful components, e.g. for human faces one that controls the hair length and a categorical one that controls the eye color.
  * They suggest a change to GANs based on Mutual Information, which leads to interpretable components.
    * E.g. for MNIST a component that controls the stroke thickness and a categorical component that controls the digit identity (1, 2, 3, ...).
    * These components are learned in a (mostly) unsupervised fashion.

### How
  * The latent code `c`
    * "Normal" GANs parameterize the generator as `G(z)`, i.e. G receives a noise vector and transforms it into an image.
    * This is changed to `G(z, c)`, i.e. G now receives a noise vector `z` and a latent code `c` and transforms both into an image.
    * `c` can contain multiple variables following different distributions, e.g. in MNIST a categorical variable for the digit identity and a gaussian one for the stroke thickness.
  * Mutual Information
    * If using a latent code via `G(z, c)`, nothing forces the generator to actually use `c`. It can easily ignore it and just deteriorate to `G(z)`.
    * To prevent that, they force G to generate images `x` in a way that `c` must be recoverable. So, if you have an image `x` you must be able to reliable tell which latent code `c` it has, which means that G must use `c` in a meaningful way.
    * This relationship can be expressed with mutual information, i.e. the mutual information between `x` and `c` must be high.
      * The mutual information between two variables X and Y is defined as `I(X; Y) = entropy(X) - entropy(X|Y) = entropy(Y) - entropy(Y|X)`.
      * If the mutual information between X and Y is high, then knowing Y helps you to decently predict the value of X (and the other way round).
      * If the mutual information between X and Y is low, then knowing Y doesn't tell you much about the value of X (and the other way round).
    * The new GAN loss becomes `old loss - lambda * I(G(z, c); c)`, i.e. the higher the mutual information, the lower the result of the loss function.
  * Variational Mutual Information Maximization
    * In order to minimize `I(G(z, c); c)`, one has to know the distribution `P(c|x)` (from image to latent code), which however is unknown.
    * So instead they create `Q(c|x)`, which is an approximation of `P(c|x)`.
    * `I(G(z, c); c)` is then computed using a lower bound maximization, similar to the one in variational autoencoders (called "Variational Information Maximization", hence the name "InfoGAN").
    * Basic equation: `LowerBoundOfMutualInformation(G, Q) = E[log Q(c|x)] + H(c) <= I(G(z, c); c)`
      * `c` is the latent code.
      * `x` is the generated image.
      * `H(c)` is the entropy of the latent codes (constant throughout the optimization).
      * Optimization w.r.t. Q is done directly.
      * Optimization w.r.t. G is done via the reparameterization trick.
    * If `Q(c|x)` approximates `P(c|x)` *perfectly*, the lower bound becomes the mutual information ("the lower bound becomes tight").
    * In practice, `Q(c|x)` is implemented as a neural network. Both Q and D have to process the generated images, which means that they can share many convolutional layers, significantly reducing the extra cost of training Q.

### Results
  * MNIST
    * They use for `c` one categorical variable (10 values) and two continuous ones (uniform between -1 and +1).
    * InfoGAN learns to associate the categorical one with the digit identity and the continuous ones with rotation and width.
    * Applying Q(c|x) to an image and then classifying only on the categorical variable (i.e. fully unsupervised) yields 95% accuracy.
    * Sampling new images with exaggerated continuous variables in the range `[-2,+2]` yields sound images (i.e. the network generalizes well).
    * ![MNIST examples](https://raw.githubusercontent.com/aleju/papers/master/neural-nets/images/InfoGAN__mnist.png?raw=true "MNIST examples")
  * 3D face images
    * InfoGAN learns to represent the faces via pose, elevation, lighting.
    * They used five uniform variables for `c`. (So two of them apparently weren't associated with anything sensible? They are not mentioned.)
  * 3D chair images
    * InfoGAN learns to represent the chairs via identity (categorical) and rotation or width (apparently they did two experiments).
    * They used one categorical variable (four values) and one continuous variable (uniform `[-1, +1]`).
  * SVHN
    * InfoGAN learns to represent lighting and to spot the center digit.
    * They used four categorical variables (10 values each) and two continuous variables (uniform `[-1, +1]`). (Again, a few variables were apparently not associated with anything sensible?)
  * CelebA
    * InfoGAN learns to represent pose, presence of sunglasses (not perfectly), hair style and emotion (in the sense of "smiling or not smiling").
    * They used 10 categorical variables (10 values each). (Again, a few variables were apparently not associated with anything sensible?)
    * ![CelebA examples](https://raw.githubusercontent.com/aleju/papers/master/neural-nets/images/InfoGAN__celeba.png?raw=true "CelebA examples")

The paper introduces a sequential variational auto-encoder that generates complex images iteratively. The authors also introduce a new spatial attention mechanism that allows the model to focus on small subsets of the image. This new approach for image generation produces images that can’t be distinguished from the training data.

#### What is DRAW:
The deep recurrent attention writer (DRAW) model has two differences with respect to other variational auto-encoders. First, the encoder and the decoder are recurrent networks. Second, it includes an attention mechanism that restricts the input region observed by the encoder and the output region observed by the decoder.

#### What do we gain?
The resulting images are greatly improved by allowing a conditional and sequential generation. In addition, the spatial attention mechanism can be used in other contexts to solve the “Where to look?” problem.

#### What follows?
A possible extension to this model would be to use a convolutional architecture in the encoder or the decoder. Although this might be less useful since we are already restricting the input of the network.

#### Like:
* As observed in the samples generated by the model, the attention mechanism works effectively by reconstructing images in a local way.
* The attention model is fully differentiable.

#### Dislike:
* I think a better exposition of the attention mechanism would improve this paper.

[Machine learning is a nuanced, complicated, intellectually serious topic...but sometimes it’s refreshing to let ourselves be a bit less serious, especially when it’s accompanied by clear, cogent writing on a topic. This particular is a particularly delightful example of good-natured silliness - from the dataset name HellaSwag to figures containing cartoons of BERT and ELMO representing language models - combined with interesting science.] 

https://i.imgur.com/CoSeh51.png

This paper tackles the problem of natural language comprehension, which asks: okay, our models can generate plausible looking text, but do they actually exhibit what we would consider true understanding of language? One natural structure of task for this is to take questions or “contexts”, and, given a set of possible endings or completion, pick the correct one. Positive examples are relatively easy to come by: adjacent video captions and question/answer pairs from WikiHow are two datasets used in this paper. However, it’s more difficult to come up with *negative* examples. Even though our incorrect endings won’t be a meaningful continuation of the sentence, we want them to be “close enough” that we can feel comfortable attributing a model’s ability to pick the correct answer as evidence of some meaningful kind of comprehension. As an obvious failure mode, if the alternative multiple choice options were all the same word repeated ten times, that would be recognizable as being not real language, and it would be easy for a model to select the answer with the distributional statistics of real language, but it wouldn’t prove much. Typically failure modes aren’t this egregious, but the overall intuition still holds, and will inform the rest of the paper: your ability to test comprehension on a given dataset is a function of how contextually-relevant and realistic your negative examples are.

Previous work (by many of the same authors as are on this paper), proposed a technique called Adversarial Filtering to try to solve this problem. In Adversarial Filtering, a generative language model is used to generate possible many endings conditioned on the input context, to be used as negative examples. Then, a discriminator is trained to predict the correct ending given the context. The generated samples that the discriminator had the highest confidence classifying as negative are deemed to be not challenging enough comparisons, and they’re thrown out and replaced with others from our pool of initially-generated samples. Eventually, once we’ve iterated through this process, we have a dataset with hopefully realistic negative examples. The negative examples are then given to humans to ensure none of them are conceptually meaningful actual endings to the sentence. The dataset released by the earlier paper, which used as it’s generator a relatively simple LSTM model, was called Swag. 

However, the authors came to notice that the performance of new language models (most centrally BERT) on this dataset might not be quite what it appears: its success rate of 86% only goes down to 76% if you don’t give the classifier access to the input context, which means it can get 76% (off of a random baseline of 25%, with 4 options) simply by evaluating which endings are coherent as standalone bits of natural language, without actually having to understand or even see the context. Also, shuffling the words in the words in the possible endings had a similarly small effect: the authors are able to get BERT to perform at 60% accuracy on the SWAG dataset with no context, and with shuffled words in the possible answers, meaning it’s purely selecting based on the distribution of words in the answer, rather than on the meaningfully-ordered sequence of words. 

https://i.imgur.com/f6vqJWT.png

The authors overall conclusion with this is: this adversarial filtering method is only as good as the generator, and, more specifically, the training dynamic between the generator that produces candidate endings, and the discriminator that filters them. If the generator is too weak, the negative examples can be easily detected as fake by a stronger model, but if the generator is too strong, then the discriminator can’t get good enough to usefully contribute by weeding samples out. They demonstrate this by creating a new version of Swag, which they call HellaSwag (for the expected acronym-optimization reasons), with a GPT generator rather than the simpler one used before: on this new dataset, all existing models get relatively poor results (30-40% performance). However, the authors’ overall point wasn’t “we’ve solved it, this new dataset is the end of the line,” but rather a call in the future to be wary, and generally aware that with benchmarks like these, especially with generated negative examples, it’s going to be a constantly moving target as generation systems get better. 

**Object detection** is the task of drawing one bounding box around each instance of the type of object one wants to detect. Typically, image classification is done before object detection. With neural networks, the usual procedure for object detection is to train a classification network, replace the last layer with a regression layer which essentially predicts pixel-wise if the object is there or not. An bounding box inference algorithm is added at last to make a consistent prediction (see [Deep Neural Networks for Object Detection](http://papers.nips.cc/paper/5207-deep-neural-networks-for-object-detection.pdf)).

The paper introduces RPNs (Region Proposal Networks). They are end-to-end trained to generate region proposals.They simoultaneously regress region bounds and bjectness scores at each location on a regular grid.

RPNs are one type of fully convolutional networks. They take an image of any size as input and output a set of rectangular object proposals, each with an objectness score.

## See also
* [R-CNN](http://www.shortscience.org/paper?bibtexKey=conf/iccv/Girshick15#joecohen)
* [Fast R-CNN](http://www.shortscience.org/paper?bibtexKey=conf/iccv/Girshick15#joecohen)
* [Faster R-CNN](http://www.shortscience.org/paper?bibtexKey=conf/nips/RenHGS15#martinthoma)
* [Mask R-CNN](http://www.shortscience.org/paper?bibtexKey=journals/corr/HeGDG17)

Deeper networks should never have a higher **training** error than smaller ones. In the worst case, the layers should "simply" learn identities. It seems as this is not so easy with conventional networks, as they get much worse with more layers. So the idea is to add identity functions which skip some layers. The network only has to learn the **residuals**. 

Advantages:

* Learning the identity becomes learning 0 which is simpler
* Loss in information flow in the forward pass is not a problem anymore
    * No vanishing / exploding gradient
* Identities don't have parameters to be learned

## Evaluation

The learning rate starts at 0.1 and is divided by 10 when the error plateaus. Weight decay of 0.0001 ($10^{-4}$), momentum of 0.9. They use mini-batches of size 128.

* ImageNet ILSVRC 2015: 3.57% (ensemble)
* CIFAR-10: 6.43%
* MS COCO: 59.0% mAp@0.5 (ensemble)
* PASCAL VOC 2007: 85.6% mAp@0.5
* PASCAL VOC 2012: 83.8% mAp@0.5

## See also

* [DenseNets](http://www.shortscience.org/paper?bibtexKey=journals/corr/1608.06993)

(See also a more thorough summary in [a LaTeX PDF][1].)

This paper has some nice clear theory which bridges maximum likelihood (supervised) learning and standard reinforcement learning. It focuses on *structured prediction* tasks, where we want to learn to predict $p_\theta(y \mid x)$ where $y$ is some object with complex internal structure.

We can agree on some deficiencies of maximum likelihood learning:

- ML training fails to assign **partial credit**. Models are trained to maximize the likelihood of the ground-truth outputs in the dataset, and all other outputs are equally wrong. This is an increasingly important problem as the space of possible solutions grows.
- ML training is potentially disconnected from **downstream task reward**. In machine translation, we usually want to optimize relatively complex metrics like BLEU or TER. Since these metrics are non-differentiable, we have to settle for optimizing proxy losses that we hope are related to the metric of interest.

Reinforcement learning offers an attractive alternative in theory. RL algorithms are designed to optimize non-differentiable (even stochastic) reward functions, which sounds like just what we want. But RL algorithms have their own problems with this sort of structured output space:

- Standard RL algorithms rely on samples from the model we are learning, $p_\theta(y \mid x)$. This becomes intractable when our output space is very complex (e.g. 80-token sequences where each word is drawn from a vocabulary of 80,000 words).
- The reward spaces for problems of interest are extremely sparse. Our metrics will assign 0 reward to most of the 80^80K possible outputs in the translation problem in the paper.
- Vanilla RL doesn't take into account the ground-truth outputs available to us in structured prediction.

This paper designs a solution which combines supervised learning with a reinforcement learning-inspired smoothing method. Concretely, the authors design an **exponentiated payoff distribution** $q(y \mid y^*; \tau)$ which assigns high mass to high-reward outputs $y$ and low mass elsewhere. This distribution is used to effectively smooth the loss function established by the ground-truth outputs in the supervised data. We end up optimizing the following objective:

$$\mathcal L_\text{RML} = - \mathbb E_{x, y^* \sim \mathcal D}\left[ \sum_y q(y \mid y^*; \tau) \log p_\theta(y \mid x) \right]$$

This optimization depends on samples from our dataset $\mathcal D$ and, more importantly, the stationary payoff distribution $q$. This contrasts strongly with standard RL training, where the objective depends on samples from the non-stationary model distribution $p_\theta$. To make that clear, we can rewrite the above with another expectation:

$$\mathcal L_\text{RML} = - \mathbb E_{x, y^* \sim \mathcal D, y \sim q(y \mid y^*; \tau)}\left[ \log p_\theta(y \mid x) \right]$$

### Model details

If you're interested in the low-level details, I wrote up the gist of the math in [this PDF][1].

### Analysis

#### Relationship to label smoothing

This training approach is mathematically equivalent to label smoothing, applied here to structured output problems. In next-word prediction language modeling, a popular trick involves smoothing the target distributions by combining the ground-truth output with some simple base model, e.g. a unigram word frequency distribution. (This just means we take a weighted sum of the one-hot vector from our supervised data and a normalized frequency vector calculated on some corpus.) Mathematically, the cross entropy with label smoothing is

$$\mathcal L_\text{ML-smooth} = - \mathbb E_{x, y^* \sim \mathcal D} \left[ \sum_y p_\text{smooth}(y; y^*) \log p_\theta(y \mid x) \right]$$

(The equation above leaves out a constant entropy term.)

The gradient of this objective looks exactly the same as the reward-augmented ML gradient from the paper:

$$\nabla_\theta \mathcal L_\text{ML-smooth} = \mathbb E_{x, y^* \sim \mathcal D, y \sim p_\text{smooth}} \left[ \log p_\theta(y \mid x) \right]$$

So reward-augmented likelihood is equivalent to label smoothing, where our smoothing distribution is log-proportional to our downstream reward function.

#### Relationship to distillation

Optimizing the reward-augmented maximum likelihood is equivalent to minimizing the KL divergence $$D_\text{KL}(q(y \mid y^*; \tau) \mid\mid p_\theta(y \mid x))$$

This divergence reaches zero iff $q = p$. We can say, then, that the effect of optimizing on $\mathcal L_\text{RML}$ is to **distill** the reward function (which parameterizes $q$) into the model parameters $\theta$ (which parameterize $p_\theta$).

It's exciting to think about other sorts of more complex models that we might be able to distill in this framework. The unfortunate (?) restriction is that the "source" model of the distillation ($q$ in this paper) must admit to efficient sampling.

#### Relationship to adversarial training

We can also view reward-augmented maximum likelihood training as a data augmentation technique: it synthesizes new "partially correct" examples using the reward function as a guide. We then train on all of the original and synthesized data, again weighting the gradients based on the reward function.

Adversarial training is a similar data augmentation technique which generates examples that force the model to be robust to changes in its input space (robust to changes of $x$). Both adversarial training and the RML objective encourage the model to be robust "near" the ground-truth supervised data. A high-level comparison:

- Adversarial training can be seen as data augmentation in the input space; RML training performs data augmentation in the output space.
- Adversarial training is a **model-based data augmentation**: the samples are generated from a process that depends on the current parameters during training. RML training performs **data-based augmentation**, which could in theory be done independent of the actual training process.

---

Thanks to Andrej Karpathy, Alec Radford, and Tim Salimans for interesting discussion which contributed to this summary.

[1]: https://drive.google.com/file/d/0B3Rdm_P3VbRDVUQ4SVBRYW82dU0/view

Wang et al. discuss an alternative definition of adversarial examples, taking into account an oracle classifier. Adversarial perturbations are usually constrained in their norm (e.g., $L_\infty$ norm for images); however, the main goal of this constraint is to ensure label invariance – if the image didn’t change notable, the label didn’t change either. As alternative formulation, the authors consider an oracle for the task, e.g., humans for image classification tasks. Then, an adversarial example is defined as a slightly perturbed input, whose predicted label changes, but where the true label (i.e., the oracle’s label) does not change. Additionally, the perturbation can be constrained in some norm; specifically, the perturbation can be constrained on the true manifold of the data, as represented by the oracle classifier. Based on this notion of adversarial examples, Wang et al. argue that deep neural networks are not robust as they utilize over-complete feature representations.

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

The last two years have seen a number of improvements in the field of language model pretraining, and BERT - Bidirectional Encoder Representations from Transformers - is the most recent entry into this canon. The general problem posed by language model pretraining is: can we leverage huge amounts of raw text, which aren’t labeled for any specific classification task, to help us train better models for supervised language tasks (like translation, question answering, logical entailment, etc)? Mechanically, this works by either 1) training word embeddings and then using those embeddings as input feature representations for supervised models, or 2) treating the problem as a transfer learning problem, and fine-tune to a supervised task - similar to how you’d fine-tune a model trained on ImageNet by carrying over parameters, and then training on your new task. Even though the text we’re learning on is strictly speaking unsupervised (lacking a supervised label), we need to design a task on which we calculate gradients in order to train our representations. For unsupervised language modeling, that task is typically structured as predicting a word in a sequence given prior words in that sequence. Intuitively, in order for a model to do a good job at predicting the word that comes next in a sentence, it needs to have learned patterns about language, both on grammatical and semantic levels. A notable change recently has been the shift from learning unconditional word vectors (where the word’s representation is the same globally) to contextualized ones, where the representation of the word is dependent on the sentence context it’s found in. All the baselines discussed here are of this second type. 

The two main baselines that the BERT model compares itself to are OpenAI’s GPT, and Peters et al’s ELMo. The GPT model uses a self-attention-based Transformer architecture, going through each word in the sequence, and predicting the next word by calculating an attention-weighted representation of all prior words. (For those who aren’t familiar, attention works by multiplying a “query” vector with every word in a variable-length sequence, and then putting the outputs of those multiplications into a softmax operator, which inherently gets you a weighting scheme that adds to one). ELMo uses models that gather context in both directions, but in a fairly simple way: it learns one deep LSTM that goes from left to right,  predicting word k using words 0-k-1, and a second LSTM that goes from right to left, predicting word k using words k+1 onward. These two predictions are combined (literally: just summed together) to get a representation for the word at position k. 

https://i.imgur.com/2329e3L.png

BERT differs from prior work in this area in several small ways, but one primary one: instead of representing a word using only information from words before it, or a simple sum of prior information and subsequent information, it uses the full context from before and after the word in each of its multiple layers. It also uses an attention-based Transformer structure, but instead of incorporating just prior context, it pulls in information from the full sentence. To allow for a model that actually uses both directions of context at a time in its unsupervised prediction task, the authors of BERT slightly changed the nature of that task: it replaces the word being predicted with the “mask” token, so that even with multiple layers of context aggregation on both sides, the model doesn’t have any way of knowing what the token is. By contrast, if it weren’t masked, after the first layer of context aggregation, the representations of other words in the sequence would incorporate information about the predicted word k, making it trivial, if another layer were applied on top of that first one, for the model to directly have access to the value it’s trying to predict. This problem can either be solved by using multiple layers, each of which can only see prior context (like GPT), by learning fully separate L-R and R-L models, and combining them at the final layer (like ELMo) or by masking tokens, and predicting the value of the masked tokens using the full remainder of the context. 

This task design crucially allows for a multi-layered bidirectional architecture, and consequently a much richer representation of context in each word’s pre-trained representation. BERT demonstrates dramatic improvements over prior work when fine tuned on a small amount of supervised data, suggesting that this change added substantial value.

[code](https://github.com/openai/improved-gan),
[demo](http://infinite-chamber-35121.herokuapp.com/cifar-minibatch/1/?),
[related](http://www.inference.vc/understanding-minibatch-discrimination-in-gans/)

### Feature matching
problem: overtraining on the current discriminator

solution:
$||E_{x \sim p_{\text{data}}}f(x) - E_{z \sim p_{z}(z)}f(G(z))||_{2}^{2}$

were f(x) activations intermediate layer in discriminator
### Minibatch discrimination
problem: generator to collapse to a single point

solution: for each sample i, concatenate to $f(x_i)$ features $b$ measuring its distance to other samples j (i and j are both real or generated samples in same batch):
$\sum_j \exp(-||M_{i, b} - M_{j, b}||_{L_1})$

this generates visually appealing samples very quickly
### Historical averaging
problem: SGD fails by going into extended orbits

solution: parameters revert to the mean
$|| \theta - \frac{1}{t} \sum_{i=1}^t \theta[i] ||^2$

### One-sided label smoothing
problem: discriminator vulnerability to adversarial examples

solution: discriminator target for positive samples is 0.9 instead of 1

### Virtual batch normalization
problem: using BN cause output of examples in batch to be dependent

solution: use reference batch chosen once at start of training and each sample is normalized using itself and the reference. It's
expensive so used only on generation

### Assessment of image quality
problem: MTurk not reliable

solution: use inception model p(y|x) to compute 
$\exp(\mathbb{E}_x \text{KL}(p(y | x) || p(y)))$
on 50K generated images x

### Semi-supervised learning
use the discriminator to also classify on K labels when known and
use all real samples (labels and unlabeled) in the discrimination task
$D(x) = \frac{Z(x)}{Z(x) + 1}, \text{ where } Z(x) = \sum_{k=1}^{K} \exp[l_k(x)]$.
In this case use feature matching but not minibatch discrimination.
It also improves the quality of generated images.

#### Introduction

* The paper proposes a general and end-to-end approach for sequence learning that uses two deep LSTMs, one to map input sequence to vector space and another to map vector to the output sequence.
* For sequence learning, Deep Neural Networks (DNNs) requires the dimensionality of input and output sequences be known and fixed. This limitation is overcome by using the two LSTMs.
* [Link to the paper](https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf)

#### Model

* Recurrent Neural Networks (RNNs) generalizes feed forward neural networks to sequences.
* Given a sequence of inputs $(x_{1}, x_{2}...x_{t})$, RNN computes a sequence of outputs $(y_1, y_2...y_t')$ by iterating over the following equation:

$$h_t = sigm(W^{hx}x_t + W^{hh} h_{t-1})$$

$$y^{t} = W^{yh}h_{t}$$

* To map variable length sequences, the input is mapped to a fixed size vector using an RNN and this fixed size vector is mapped to output sequence using another RNN.
* Given the long-term dependencies between the two sequences, LSTMs are preferred over RNNs.
* LSTMs estimate the conditional probability *p(output sequence | input sequence)* by first mapping the input sequence to a fixed dimensional representation and then computing the probability of output with a standard LST-LM formulation.

##### Differences between the model and standard LSTMs

* The model uses two LSTMs (one for input sequence and another for output sequence), thereby increasing the number of model parameters at negligible computing cost.
* Model uses Deep LSTMs (4 layers).
* The words in the input sequences are reversed to introduce short-term dependencies and to reduce the "minimal time lag". By reversing the word order, the first few words in the source sentence (input sentence) are much closer to first few words in the target sentence (output sentence) thereby making it easier for LSTM to "establish" communication between input and output sentences.


#### Experiments

* WMT'14 English to French dataset containing 12 million sentences consisting of 348 million French words and 304 million English words.
* Model tested on translation task and on the task of re-scoring the n-best results of baseline approach.
* Deep LSTMs trained in sentence pairs by maximizing the log probability of a correct translation $T$, given the source sentence $S$
* The training objective is to maximize this log probability, averaged over all the pairs in the training set.
* Most likely translation is found by performing a simple, left-to-right beam search for translation.
* A hard constraint is enforced on the norm of the gradient to avoid the exploding gradient problem.
* Min batches are selected to have sentences of similar lengths to reduce training time.
* Model performs better when reversed sentences are used for training.
* While the model does not beat the state-of-the-art, it is the first pure neural translation system to outperform a phrase-based SMT baseline.
* The model performs well on long sentences as well with only a minor degradation for the largest sentences.
* The paper prepares ground for the application of sequence-to-sequence based learning models in other domains by demonstrating how a simple and relatively unoptimised neural model could outperform a mature SMT system on translation tasks.