Unsupervised Learning by GAN:
Machine learning is a branch of artificial intelligence (AI) focused on building applications that learn from
data and improve their accuracy over time without being programmed to do so. In data science, an
algorithm is a sequence of statistical processing steps. In machine learning, algorithms are 'trained' to
find patterns and features in massive amounts of data in order to make decisions and predictions based
on new data. The better the algorithm, the more accurate the decisions and predictions will become as
it processes more data. CNN (convolution Neural Network) is one of the deep learning programs and is
one of the highest performing algorithms which have led to serious development and enhancement in
computer vision. But it has a certain drawback too. However, almost all the CNNs require heavily labeled
data and months of training. The annotation of a large data set is very expensive which required human
power, time, expensive annotation interfaces and usually subject to human biases. Other than that, the
paucity of data in real-world problem such as rare diseases in the medical application made the process
harder to complete. In such, unsupervised feature learning of image representation shows a promising
direction as the resources are quasi-unlimited due to the high digital image data flows nowadays.
Unsupervised Learning Model:
Unsupervised machine learning algorithms infer patterns from a dataset without reference to known, or
labeled, outcomes. Unlike supervised machine learning, unsupervised machine learning methods cannot
be directly applied to a regression or a classification problem because you have no idea what the values
for the output data might be, making it impossible for you to train the algorithm the way you normally
would. Unsupervised learning can instead be used to discover the underlying structure of the data.
In this paradigm of learning where the model is only given the input variables (X) and the problem does
not have any output variables (y). A model is constructed by extracting or summarizing the patterns in
the input data. There is no correction of the model, as the model is not predicting anything.
“The second main type of machine learning is the descriptive or unsupervised learning approach. Here
we are only given inputs, and the goal is to find “interesting patterns” in the data. […] This is a much less
well-defined problem, since we are not told what kinds of patterns to look for, and there is no obvious
error metric to use (unlike supervised learning, where we can compare our prediction of y for a given x
to the observed value)”.
— Page 2, Machine Learning: A Probabilistic Perspective, 2012.
Example of Unsupervised Learning is GAN.
Input Data X
Model
GAN:
Generative Adversarial Networks, or GANs for short, are an approach to generative modeling using deep
learning methods, such as convolutional neural networks. Generative modeling is an unsupervised
learning task in machine learning that involves automatically discovering and learning the regularities or
patterns in input data in such a way that the model can be used to generate or output new examples
that plausibly could have been drawn from the original dataset.
GANs are a clever way of training a generative model by framing the problem as a supervised learning
problem with two sub-models: the generator model that we train to generate new examples, and the
discriminator model that tries to classify examples as either real (from the domain) or fake (generated).
The two models are trained together in a zero-sum game, adversarial, until the discriminator model is
fooled about half the time, meaning the generator model is generating plausible examples.
GANs are an exciting and rapidly changing field, delivering on the promise of generative models in their
ability to generate realistic examples across a range of problem domains, most notably in image-to-
image translation tasks such as translating photos of summer to winter or day to night, and in
generating photorealistic photos of objects, scenes, and people that even humans cannot tell are fake.
Generative adversarial networks (GAN) consist of two models which are called the generative model G
and the discriminative model D. The whole idea of GAN can be thought of as the generative model, G
trying to produce fake currency and use it without detection, while the discriminative model D trying to
detect the fake currency. In such, GAN is one of the generative models that take advantage from
unsupervised learning as it can learn features from the discriminator that could improve the
performance of classifiers when limited labeled data is available.
References:
https://www.researchgate.net/publication/337701176_Unsupervised_Learning_of_Image_Data_Using_
Generative_Adversarial_Network
https://machinelearningmastery.com/what-are-generative-adversarial-networks-gans/
https://www.tibco.com/reference-center/what-is-unsupervised-learning
https://towardsdatascience.com/unsupervised-learning-part-5-f8809d7f1f90
