The best strategy to improve optimization is by designing models that are easier to optimize. For example, linear paths or skip connections between layers reduce the length of the shortest path from the lower layer’s parameters to the output, and thus mitigate the vanishing gradient problem. Model innovations like the LSTM, rectiﬁed linear units and maxout units have all moved toward using linear functions to improve optimization. 

Designing Models to Aid Optimization

Machine learning acts indirectly, specifically, with loss fucntion having relationship with but not the same with the measurement P, which pure optimization always wants to optimize.

How does learning differ from pure optimization?

The training process based on minimizing this average training error is known
as empirical risk minimization.

Empirical Risk Minimization

This method of optimization involves applying algorithm concepts to training other algorithms, hence the "meta-" prefix. 

Meta-Algorithm Approaches

Empirical risk is defined as the empirical average of the loss function. In this case, empirical means the performance was evaluated with real-life testing.

Empirical Risk

Surrogate loss function is a proxy having consistency or calibration with the original loss function, which is not comfortable for people to use derivatives or other direct method to optimize.

Surrogate Loss Function

Early Stopping means stopping earlier when the loss function doesn't have relatively obvious progress or with worse validation in one or several recent epochs.

Early Stopping

The underlying premise:
- In high dimensional feature spaces, there is a very large likelihood of encountering multiple local minima. 
- This is compounded with the fact that the feature space isn’t well behaved i.e. an inevitable presence of plateaus, saddle points affecting the magnitude of the gradient along with the direction of the gradient not pointing towards the approximate region of lower cost.

Thus, being able to initialize parameters in a region smaller than the feature space itself and one that behaves well enough for the descent to lead to a reasonable solution is powerful. This is exactly what continuation methods try to achieve.

Continuation Methods

Indexed notation is commonly used to represent a subsequence of elements, such as vectors. A sequence starting from index $m$ and ending at index $len$ is written as $x_m, x_{m+1}, \dots, x_{len-1}, x_{len}$. In the context of sequence models, this notation is frequently used for different components. For instance, a sequence of hidden states is often denoted as $h_m, h_{m+1}, \dots, h_{len}$, while a sequence of embeddings might be represented as $\mathbf{e}_m, \mathbf{e}_{m+1}, \dots, \mathbf{e}_{len}$.

Indexed Sequence Notation

Deep Learning models require incredible computational resources to successfully train a model. As a result, optimizing the training process is a key step in developing an algorithm. One approach involves finding the parameters of a neural network that minimize its loss function. This is accomplished via gradient descent, a popular technique for minimizing loss function error. 

University of Virginia, Charlottesville

Deep learning algorithms can be implemented to solve real-world problems today.

Deep feedforward networks, also called multilayer perceptrons (MLPs), is the quintessential deep learning model that is behind nearly all modern practical applications of deep learning.

Scaling these models to large inputs such as high-resolution images or long temporal sequences requires specialization. 
 - Convolutional neural networks (CNN) can be used for processing large images.
 - Recurrent neural networks (RNN) can be used for processing temporal sequences. 


Deep Learning Algorithms

Goodfellow, I., Bengio, Y., & Courville, A. (2016). $\mathit{Deep \ Learning.}$ MIT Press. Retrieved from [www.deeplearningbook.org](https://www.deeplearningbook.org) 

Deep Learning

A helpful website that introduces neural networks:
https://missinglink.ai/guides/neural-network-concepts/

Neural Network Reference

Convolutional networks, also known as convolutional neural networks, or CNNs, are a specialized kind of neural network for processing data that has a known grid-like topology. Examples include time-series data, which can be thought of as a 1-D grid taking samples at regular time intervals, and image data, which can be thought of as a 2-D grid of pixels. 

The network employs a mathematical operation called convolution. Convolution is a specialized kind of linear operation. Convolutional networks are simply neural networks that use convolution in place of general matrix multiplication in at least one of their layers.

The CNN gets its power from the following concepts:
- Sparse connectivity
- Parameter sharing

Convolutional Neural Network (CNN)

Recurrent neural networks, or RNNs, are a family of neural networks for processing sequential data. A recurrent neural network is specialized for processing a sequence of inputs $x^{(1)}, . . . , x^{(τ)}$ and each time add additional layers of comprehension on top of the previous inputs. 


Recurrent Neural Network (RNN)

**Generative Models**  As might be clear from their name , generative models are able to generate new contents by learning features of certain datasets. As for more formal definition, generative models specify in terms of a probabilistic model describing how it thinks the dataset was produced.  Using sampling from this probability distribution, we can create new data in the style of the old.
 
The joint probability distribution P(X,Y) is learned from the data, and then divided by P(X) to obtain the conditional probability distribution P(Y|X), which is used as a predictive model. It is called a generative model because the model represents the relationship between a given input X and an output Y. Common generative models are: Naive Bayes, Hidden Markov Model, Gaussian Mixture Model, Document Topic Generation Model (LDA), and restricted Boltzmann machine.

Generative Models

There are functions you can compute with a small layer that shallower networks would need a lot more hidden units in order to compute. 

Circuit Theory

https://www.simplilearn.com/deep-learning-algorithms-article

More about deep learning algorithms 

Data inputted into deep learning algorithms should be split into a distribution in which the majority of data (well over 70%+) is fed into the training set. This differs from traditional machine learning algorithms which had ~70% of the data given to the training set. This difference comes from the fact that there is now much more data available and deep learning algorithms improve with more data, whereas traditional machine learning algorithms improvement levels out after a certain amount of data is fed in.

For example, in a dataset of 1 million examples, you mighht decide that 10k examples are enough to evaluate which algorithm is better - 98% train, 1% dev, 1% test.

Deep learning train/dev/test split 

Deep feedforward networks, also called feedforward neural networks, or multilayer perceptrons (MLPs), are the quintessential deep learning models.

It was the first and simplest type of artificial neural network devised. In this network, the information moves in only one direction, forward, from the input nodes, through the hidden nodes (if any) and to the output nodes. There are no cycles or loops in the network.

Deep Feedforward Networks (MLP = Multi-Layer Perceptrons)

Instead of manually building up deep network architectures, many python libraries are available online to help users to easily implement deep learning models.

- Trax (built on TensorFlow)
- Tensor2Tensor (built on TensorFlow)
- Pytorch
- Fast.ai ( built on top of PyTorch)
- Keras (built to be a higher level framework to interface with other frameworks like TensorFlow)
- Vowpal Wabbit 
- Theano
- Caffee 

Deep Learning Python libraries (frameworks)

What can convolutional neural networks be used for?

A generative adversarial network (GAN) is a class of machine learning framework where two neural networks, a generative model and a discriminant model, contest against each other in a "game" (in the form of a zero-sum game, where one agent's gain is another agent's loss). Given a training set, this technique learns to generate new data with the same statistics as the training set. 

The core idea of a GAN is based on the "indirect" training through the discriminator, which itself is also being updated dynamically. This basically means that the generator is not trained to minimize the distance to a specific image, but rather to fool the discriminator and the discriminator is rewarded every time it correctly deduces if a sample is from the model distribution or the data distribution. This enables the model to learn in an unsupervised manner.

Generative adversarial network(GAN)

Optimization for Training Deep Models

Whereas deep learning algorithms were once always implemented on a single computer's central processing unit (CPU), research has shown that families of CPUs or even a single graphics processing unit (GPU) is much more effective. Some systems employ even greater parallelization to achieve the fastest training times with distributed architectures.

Implementations of Deep Learning

Monte Carlo algorithms return results with variability. The variability can typically be reduced by allocating more resources. The benefit of Monte Carlo algorithms is that they can provide an approximated estimation with limited source while maintaining a certain degree of accuracy. In Machine Learning, many problems are too complicated to have precise answers. Monte Carlo approximations are therefore a good approach to these problems.

Monte Carlo Methods

Deep learning frameworks provide specialized software tools that streamline the construction, training, and deployment of neural networks. The availability of these efficient frameworks has made the design and implementation of whole system optimization significantly easier, which is a critical component in achieving high performance for complex deep learning pipelines.

Deep Learning Frameworks

An adversarial example is an input to a machine learning model that has been intentionally modified with small, often imperceptible perturbations designed to cause the model to output an incorrect classification. For instance, adding specific, calculated noise to an image of a panda can cause a deep neural network to misclassify it as a gibbon, even though the image remains visually identical to the original for a human observer.

Learn Before

Related

Learn After