disclaimer: I'm the first author of the paper

## TL;DR 

We have made a lot of progress on catastrophic forgetting within the standard evaluation protocol,
i.e. sequentially learning a stream of tasks and testing our models' capacity to remember them all.

We think it's time a new approach to Continual Learning (CL), coined OSAKA, which is more aligned with real-life applications of CL. It brings CL closer to Online Learning and Open-World Learning.

main modifications we propose:
- bring CL closer to Online learning i.e. at test time, the model is continually learning and evaluated on its online predictions 
- it's fine to forget, as long as you can quickly remember (just like we humans do)
- we allow pretraining, (because you wouldn't deploy an untrained CL system, right?) but at test time, the model will have to quickly learn new out-of-distribution (OoD) tasks (because the world is full of surprises)
- the tasks distribution is actually a hidden Markov chain. This implies:
    - new and old tasks can re-occur (just like in real life). Better remember them quickly if you want to get a good total performance!
    - tasks have different lengths
    - and the tasks boundaries are unknown (task agnostic setting)

### Bonus:
We provide a unifying framework explaining the space of machine learning setting {supervised learning, meta learning, continual learning, meta-continual learning, continual-meta learning} in case it was starting to get confusing :p

## Motivation

We imagine an agent, embedded or not, first pre-trained in a controlled environment and later deployed in the real world, where it faces new or unexpected situations. This scenario is relevant for many applications. For instance, in robotics, the agent is pre-trained in a factory and deployed in homes or
in manufactures where it will need to adapt to new domains and maybe solve new tasks. Likewise, a virtual assistant can be pre-trained on static datasets and deployed in a user’s life to fit its personal needs. 

Further motivations can be found in time series forecasting, e.g., market prediction,
game playing, autonomous customer service, recommendation systems, autonomous driving, to name a few. In this scenario, we are interested in the cumulative performance of the agent throughout its lifetime. Differently, standard CL reports the agent’s final performance on all tasks at the end of its life. In order
to succeed in this scenario, agents need the ability to learn new tasks as well as quickly remembering old ones.

## Unifying Framework

We propose a unifying framework explaining the space of machine learning setting {supervised learning, meta learning, continual learning, meta-continual learning, continual-meta learning} with meta learning terminology. 

https://i.imgur.com/U16kHXk.png

(easier to digest with accompanying text)

## OSAKA

The main features of the evaluation framework are
- task agnosticism
- pre-training is allowed, but OoD tasks at test time
- task revisiting
- controllable non-stationarity
- online evaluation

(see paper for the motivations of the features)

## Continual-MAML: an initial baseline

A simple extension of MAML that is better suited than previous methods in the proposed setting.

https://i.imgur.com/C86WUc8.png

Features are:
- Fast Adapatation
- Dynamic Representation
- Task boundary detection
- Computational efficiency


## Experiments

We provide a suite of 3 benchmarks to test algorithms in the new setting.

The first includes the Omniglot, MNIST and FashionMNIST dataset. 

The second and third use the Synbols (Lacoste et al. 2018) and TieredImageNet datasets, respectively.

The first set of experiments shows that the baseline outperforms previous approaches, i.e., supervised learning, meta learning, continual learning, meta-continual learning, continual-meta learning, in the new setting.

https://i.imgur.com/IQ1WYTp.png

The second and third experiments lead us to similar conclusions

code: https://github.com/ElementAI/osaka

  * GANs are based on adversarial training.
  * Adversarial training is a basic technique to train generative models (so here primarily models that create new images).
  * In an adversarial training one model (G, Generator) generates things (e.g. images). Another model (D, discriminator) sees real things (e.g. real images) as well as fake things (e.g. images from G) and has to learn how to differentiate the two.
  * Neural Networks are models that can be trained in an adversarial way (and are the only models discussed here).

### How
  * G is a simple neural net (e.g. just one fully connected hidden layer). It takes a vector as input (e.g. 100 dimensions) and produces an image as output.
  * D is a simple neural net (e.g. just one fully connected hidden layer). It takes an image as input and produces a quality rating as output (0-1, so sigmoid).
  * You need a training set of things to be generated, e.g. images of human faces.
  * Let the batch size be B.
  * G is trained the following way:
    * Create B vectors of 100 random values each, e.g. sampled uniformly from [-1, +1]. (Number of values per components depends on the chosen input size of G.)
    * Feed forward the vectors through G to create new images.
    * Feed forward the images through D to create ratings.
    * Use a cross entropy loss on these ratings. All of these (fake) images should be viewed as label=0 by D. If D gives them label=1, the error will be low (G did a good job).
    * Perform a backward pass of the errors through D (without training D). That generates gradients/errors per image and pixel.
    * Perform a backward pass of these errors through G to train G.
  * D is trained the following way:
    * Create B/2 images using G (again, B/2 random vectors, feed forward through G).
    * Chose B/2 images from the training set. Real images get label=1.
    * Merge the fake and real images to one batch. Fake images get label=0.
    * Feed forward the batch through D.
    * Measure the error using cross entropy.
    * Perform a backward pass with the error through D.
  * Train G for one batch, then D for one (or more) batches. Sometimes D can be too slow to catch up with D, then you need more iterations of D per batch of G.

### Results
  * Good looking images MNIST-numbers and human faces. (Grayscale, rather homogeneous datasets.)
  * Not so good looking images of CIFAR-10. (Color, rather heterogeneous datasets.)


![Generated Faces](https://raw.githubusercontent.com/aleju/papers/master/neural-nets/images/Generative_Adversarial_Networks__faces.jpg?raw=true "Generated Faces")

*Faces generated by MLP GANs. (Rightmost column shows examples from the training set.)*

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

### Rough chapter-wise notes

* Introduction
  * Discriminative models performed well so far, generative models not so much.
  * Their suggested new architecture involves a generator and a discriminator.
  * The generator learns to create content (e.g. images), the discriminator learns to differentiate between real content and generated content.
  * Analogy: Generator produces counterfeit art, discriminator's job is to judge whether a piece of art is a counterfeit.
  * This principle could be used with many techniques, but they use neural nets (MLPs) for both the generator as well as the discriminator.
 
* Adversarial Nets
  * They have a Generator G (simple neural net)
    * G takes a random vector as input (e.g. vector of 100 random values between -1 and +1).
    * G creates an image as output.
  * They have a Discriminator D (simple neural net)
    * D takes an image as input (can be real or generated by G).
    * D creates a rating as output (quality, i.e. a value between 0 and 1, where 0 means "probably fake").
  * Outputs from G are fed into D. The result can then be backpropagated through D and then G. G is trained to maximize log(D(image)), so to create a high value of D(image).
  * D is trained to produce only 1s for images from G.
  * Both are trained simultaneously, i.e. one batch for G, then one batch for D, then one batch for G...
  * D can also be trained multiple times in a row. That allows it to catch up with G.

* Theoretical Results
  * Let
    * pd(x): Probability that image `x` appears in the training set.
    * pg(x): Probability that image `x` appears in the images generated by G.
  * If G is now fixed then the best possible D classifies according to: `D(x) = pd(x) / (pd(x) + pg(x))`
  * It is proofable that there is only one global optimum for GANs, which is reached when G perfectly replicates the training set probability distribution. (Assuming unlimited capacity of the models and unlimited training time.)
  * It is proofable that G and D will converge to the global optimum, so long as D gets enough steps per training iteration to model the distribution generated by G. (Again, assuming unlimited capacity/time.)
  * Note that these things are proofed for the general principle for GANs. Implementing GANs with neural nets can then introduce problems typical for neural nets (e.g. getting stuck in saddle points).

* Experiments
  * They tested on MNIST, Toronto Face Database (TFD) and CIFAR-10.
  * They used MLPs for G and D.
  * G contained ReLUs and Sigmoids.
  * D contained Maxouts.
  * D had Dropout, G didn't.
  * They use a Parzen Window Estimate aka KDE (sigma obtained via cross validation) to estimate the quality of their images.
  * They note that KDE is not really a great technique for such high dimensional spaces, but its the only one known.
  * Results on MNIST and TDF are great. (Note: both grayscale)
  * CIFAR-10 seems to match more the texture but not really the structure.
  * Noise is noticeable in CIFAR-10 (a bit in TFD too). Comes from MLPs (no convolutions).
  * Their KDE score for MNIST and TFD is competitive or better than other approaches.

* Advantages and Disadvantages
  * Advantages
    * No Markov Chains, only backprob
    * Inference-free training
    * Wide variety of functions can be incorporated into the model (?)
    * Generator never sees any real example. It only gets gradients. (Prevents overfitting?)
    * Can represent a wide variety of distributions, including sharp ones (Markov chains only work with blurry images).
   * Disadvantages
    * No explicit representation of the distribution modeled by G (?)
    * D and G must be well synchronized during training
      * If G is trained to much (i.e. D can't catch up), it can collapse many components of the random input vectors to the same output ("Helvetica")

This paper introduces a neural network architecture
that is deeper and wider, yet optimizing for computational
efficiency by approximating the expected sparse structure
(following from Arora et al's work) using readily available
dense blocks. An ensemble of 7 models (all with the same
architecture but different image sampling) achieved top spot
in the classification task at ILSVRC2014.

"Their main result states that if the probability distribution of the data-set is representable by a large, very sparse deep neural network, then the optimal network topology can be constructed layer by layer by analyzing the correlation statistics of the activations of the last layer and clustering neurons with highly correlated outputs."

Main contributions:

- A more generalized exploration of the NIN architecture,
called the Inception module.
    - 1x1 convolutions to capture dense information clusters
    - 3x3 and 5x5 to capture more spatially spread out
    clusters
    - Ratio of 3x3 and 5x5 to 1x1 convolutions increases as we go deeper
    as features of higher abstraction are less spatially
    concentrated.
- To avoid the blow-up of output channels cause by merging outputs
of convolutional layers and pooling layer, they use 1x1 convolutions
for dimensionality reduction. This has the added benefit of another
layer of non-linearity (and thus increasing discriminative capability).
- Multiple intermediate layers are tied to the objective function. Since
features produced by intermediate layers of a deep network are
supposed to be very discriminative, and to strengthen the gradient signal
passing through them during back-propagation, they attach auxiliary classifiers
to intermediate layers.
    - During training, they do a weighted sum of this loss with the total loss
    of the network.
    - At test time, these auxiliary networks are discarded.
    - Architecture: average pooling, 1x1 convolution (for dimensionality reduction),
    dropout, linear layer with softmax.

## Strengths

- Excellent results on ILSVRC2014.

## Weaknesses / Notes

- Even though the authors try to explain some of the intuition, most of
the design decisions seem arbitrary.

We want to find two matrices $W$ and $H$ such that $V = WH$. Often a goal is to determine underlying patterns in the relationships between the concepts represented by each row and column. $W$ is some $m$ by $n$ matrix and we want the inner dimension of the factorization to be $r$. So 

$$\underbrace{V}_{m \times n} = \underbrace{W}_{m \times r} \underbrace{H}_{r \times n}$$

Let's consider an example matrix where of three customers (as rows) are associated with three movies (the columns) by a rating value.

$$
V = \left[\begin{array}{c c c}
5 & 4 & 1  \\\\
4 & 5 & 1 \\\\
2 & 1 & 5
\end{array}\right]
$$


We can decompose this into two matrices with $r = 1$. First lets do this without any non-negative constraint using an SVD reshaping matrices based on removing eigenvalues:


$$
W = \left[\begin{array}{c c c}
-0.656 \\\
 -0.652 \\\
 -0.379
\end{array}\right],
H = \left[\begin{array}{c c c}
-6.48 & -6.26 & -3.20\\\\
\end{array}\right]
$$

We can also decompose this into two matrices with $r = 1$ subject to the constraint that $w_{ij} \ge 0$ and  $h_{ij} \ge 0$. (Note: this is only possible when $v_{ij} \ge 0$):

$$
W = \left[\begin{array}{c c c}
0.388 \\\\
0.386 \\\\
0.224
\end{array}\right],
H = \left[\begin{array}{c c c}
11.22 & 10.57 & 5.41  \\\\
\end{array}\right]
$$

Both of these $r=1$ factorizations reconstruct matrix $V$ with the same error. 

$$
V \approx WH = \left[\begin{array}{c c c}
4.36 & 4.11 & 2.10 \\\
4.33 & 4.08 & 2.09 \\\
2.52 & 2.37 & 1.21 \\\
\end{array}\right]
$$


If they both yield the same reconstruction error then why is a non-negativity constraint useful? We can see above that it is easy to observe patterns in both factorizations such as similar customers and similar movies. `TODO: motivate why NMF is better`



#### Paper Contribution 

This paper discusses two approaches for iteratively creating a non-negative $W$ and $H$ based on random initial matrices. The paper discusses a multiplicative update rule where the elements of $W$ and $H$ are iteratively transformed by scaling each value such that error is not increased. 

The multiplicative approach is discussed in contrast to an additive gradient decent based approach where small corrections are iteratively applied. The multiplicative approach can be reduced to this by setting the learning rate ($\eta$) to a ratio that represents the magnitude of the element in $H$ to the scaling factor of $W$ on $H$.



### Still a draft

This is follow-up work to the ResNets paper. It studies the propagation formulations behind the connections of deep residual networks and performs ablation experiments. A residual block can be represented with the equations $y_l = h(x_l) + F(x_l, W_l); x_{l+1} = f(y_l)$. $x_l$ is the input to the l-th unit and $x_{l+1}$ is the output of the l-th unit. In the original ResNets paper, $h(x_l) = x_l$, $f$ is ReLu, and F consists of 2-3 convolutional layers (bottleneck architecture) with BN and ReLU in between. In this paper, they propose a residual block with both $h(x)$ and $f(x)$ as identity mappings, which trains faster and performs better than their earlier baseline. Main contributions:

- Identity skip connections work much better than other multiplicative interactions that they experiment with:
    - Scaling $(h(x) = \lambda x)$: Gradients can explode or vanish depending on whether modulating scalar \lambda > 1 or < 1.
    - Gating ($1-g(x)$ for skip connection and $g(x)$ for function F):
    For gradients to propagate freely, $g(x)$ should approach 1, but
    F gets suppressed, hence suboptimal. This is similar to highway
    networks. $g(x)$ is a 1x1 convolutional layer.
    - Gating (shortcut-only): Setting high biases pushes initial $g(x)$
    towards identity mapping, and test error is much closer to baseline.
    - 1x1 convolutional shortcut: These work well for shallower networks
    (~34 layers), but training error becomes high for deeper networks,
    probably because they impede gradient propagation.

- Experiments on activations.
    - BN after addition messes up information flow, and performs considerably
    worse.
    - ReLU before addition forces the signal to be non-negative, so the signal is monotonically increasing, while ideally a residual function should be free to take values in (-inf, inf).
    - BN + ReLU pre-activation works best. This also prevents overfitting, due
    to BN's regularizing effect. Input signals to all weight layers are normalized.

## Strengths

- Thorough set of experiments to show that identity shortcut connections
are easiest for the network to learn. Activation of any deeper unit can
be written as the sum of the activation of a shallower unit and a residual
function. This also implies that gradients can be directly propagated to
shallower units. This is in contrast to usual feedforward networks, where
gradients are essentially a series of matrix-vector products, that may vanish, as networks grow deeper.

- Improved accuracies than their previous ResNets paper.

## Weaknesses / Notes

- Residual units are useful and share the same core idea that worked in
LSTM units. Even though stacked non-linear layers are capable of asymptotically
approximating any arbitrary function, it is clear from recent work that
residual functions are much easier to approximate than the complete function.
The [latest Inception paper](http://arxiv.org/abs/1602.07261) also reports
that training is accelerated and performance is improved by using identity
skip connections across Inception modules.

- It seems like the degradation problem, which serves as motivation for
residual units, exists in the first place for non-idempotent activation
functions such as sigmoid, hyperbolic tan. This merits further
investigation, especially with recent work on function-preserving transformations such as [Network Morphism](http://arxiv.org/abs/1603.01670), which expands the Net2Net idea to sigmoid, tanh, by using parameterized activations, initialized to identity mappings.