Chapter VI:

Introduction to Deep Learning

Machine Learning
Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Learning

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 2

Deep Learning?

◼ Deep Learning is a subset of Machine

Learning which in turn is a subset of Artificial
Intelligence.
◼ Artificial Intelligence is the technique that
enables the Machine to mimic Human
Behavior.
Chapter 6: Introduction to Deep Learning 3
 Cont..
◼ Machine Learning is a technique to
achieve AI through Algorithms trained
with data.
◼ Deep Learning is a type of Machine
Learning inspired by the structure of
the human brain in terms of Deep
Learning this structure is called an
Artificial Neural Network.

Chapter 6: Introduction to Deep Learning 4

 Cont..

Chapter 6: Introduction to Deep Learning 5

How DL is different from ML?
◼ Let’s create a machine that could
differentiate between tomatoes and cherries.
◼ If done using Machine Learning we'd have to
tell the machine the features based on which
the two can be differentiated. These features
could be the size and the type of them.
◼ With Deep Learning on the other hand the
features are picked out by the Neural
Network without Human Intervention.

Chapter 6: Introduction to Deep Learning 6

How DL is different from ML?
◼ Let’s create a Machine that could
differentiate between tomatoes and
cherries.

Chapter 6: Introduction to Deep Learning 7

 Cont..
◼ If done using Machine Learning we'd have to tell
the machine the features based on which the
two can be differentiated.
◼ These features could be the size and the type
of them.

Chapter 6: Introduction to Deep Learning 8

 Cont..
◼ With Deep Learning on the other hand the
features are picked out by the Neural Network
without Human Intervention.

Chapter 6: Introduction to Deep Learning 9

 Cont..
“Traditional” machine learning:

handcrafted learned
cat
features classifier

Deep, “end-to-end” learning:

learned learned learned

learned
low-level mid-level high-level cat
classifier
features features features

Chapter 6: Introduction to Deep Learning 10

Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Learning

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 11

Limitations of Machine Learning
◼ One of the big challenges with traditional Machine
Learning models is a process called feature
extraction.
◼ For complex problems such as object recognition or
handwriting recognition, this is a huge challenge.

Chapter 6: Introduction to Deep Learning 12

 Cont..
◼ Let's dive into the working of neural networks here
we’ve three students each of them write down the
digit nine on a piece of paper notably. They don't all
write it identically, the human brain can easily
recognize the digits!

Chapter 6: Introduction to Deep Learning 13

 Cont..
◼ What if a computer had to recognize them?

◼ That's where Deep Learning comes,

◼ In here's a neural network trained to identify
handwritten digits each number is present as an
image of twenty eight pixels now that amounts to a
total of seven hundred and eighty four pixels.
Chapter 6: Introduction to Deep Learning 14
 Cont..

Chapter 6: Introduction to Deep Learning 15

Why is DL is Useful?
◼ DL provides a flexible, learnable
framework for representing visual, text,
linguistic information
◼ DL represents an effective end-to-end
learning system.
◼ Requires large amounts of training data
◼ Since about 2010, DL has outperformed
other ML techniques. (First in vision and
speech, then NLP, and other applications).

Chapter 6: Introduction to Deep Learning 16

Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Learning

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 17

Anatomy of a Deep Neural Network
◼ Deep Learning is implemented through
Neural Networks.
◼ Motivation behind Neural Networks is the
biological Neuron.

Chapter 6: Introduction to Deep Learning 18

 Cont..
◼ Layers, which are combined into a network (or model).
◼ The Input data and corresponding targets
◼ The Loss function, which defines the feedback signal
used for learning
◼ The Optimizer, which determines how learning
proceeds

Chapter 6: Introduction to Deep Learning 19

Layers

Chapter 6: Introduction to Deep Learning 20

Input Data and Targets
◼ The network maps the input data X to
predictions Y′
◼ During training, the predictions Y′ are
compared to true targets Y using the loss
function.

Chapter 6: Introduction to Deep Learning 21

Loss Function
▪ The quantity to be minimized (optimized)
during training
 the only thing the network cares about

▪ Common tasks have “standard” loss

functions:
 mean squared error for regression
 binary cross-entropy for two-class
classification
 categorical cross-entropy for multi-
class classification
Chapter 6: Introduction to Deep Learning 22
Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Learning

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 23

How Deep Learning Algorithms Work?
◼ While deep learning algorithms feature self-learning
representations, they depend upon ANNs that mirror the
way the brain computes information. During the training
process, algorithms use unknown elements in the input
distribution to extract features, group objects, and
discover useful data patterns. Much like training
machines for self-learning, this occurs at multiple levels,
using the algorithms to build the models.
◼ Deep learning models make use of several algorithms.
While no one network is considered perfect, some
algorithms are better suited to perform specific tasks. To
choose the right ones, it’s good to gain a solid
understanding of all primary algorithms.

Chapter 6: Introduction to Deep Learning 24

Types of Algorithms used in Deep Learning
Here is the list of top 5 most popular deep learning
algorithms:
I. Convolutional Neural Networks (CNNs)
II. Long Short Term Memory Networks (LSTMs)

III. Recurrent Neural Networks (RNNs)

IV. Multilayer Perceptrons (MLPs)

V. Self Organizing Maps (SOMs)

Deep learning algorithms work with almost any kind

of data and require large amounts of computing
power and information to solve complicated issues.

Chapter 6: Introduction to Deep Learning 25

Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Neural Network

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 26

Deep Learning Frameworks
◼ Deep learning (DL) frameworks offer building
blocks for designing, training, and validating
deep neural networks through a high-level
programming interface.
◼ Widely-used DL frameworks, such as PyTorch,
TensorFlow, PyTorch Geometric, DGL, and
others, rely on GPU-accelerated libraries.

Chapter 6: Introduction to Deep Learning 27

TensorFlow
◼ Tensorflow, probably one of the most used frameworks
for deep learning worldwide, is an open-source and
python friendly library. Google developed it, and it is very
useful in developing and studying neural networks.
◼ Tensorflow has a very modern approach to tackling real-
world problems. It provides certain levels of abstraction.
This helps you to have a look at the segments that you
really need to see and that you don’t have to keep on
searching for it.
◼ Tensorflow lets you train your model easily irrespective of
the platform (Web, servers, devices, etc.) and the
language. You can work efficiently without worrying about
speed and computational power.

Chapter 6: Introduction to Deep Learning 28

Pytorch
◼ Pytorch is a modern-day framework and globally
used in research and various deep learning
projects. This was made by both Facebook’s AI
team and Uber’s Pyro software.
◼ It is an open-source framework and strongly uses
GPUs and CPUs. It is also an optimized version of
Tensor, which is another framework and a user-
friendly interface.
◼ The computational power consumption is shown in
the form of computational graphs, which gives a
proper insight to developers of how much
processing power will the algorithm consumes.
Chapter 6: Introduction to Deep Learning 29
Keras
◼ Keras is a very popular framework used in machine
learning. Being open-source, its also based on python. It
runs on top of powerful deep learning libraries like
TensorFlow, Theano, CNTK, etc.
◼ Despite the presence of such powerful libraries, Keras is
the optimal choice when it comes to developing deep
learning models. That has some reasons for it.
◼ Since Keras runs on a minimal structure, it tries to
provide simpler ways to develop models based on top of
TensorFlow. It provides lesser computational strain. Keras
can run for both CPUs and GPUs. It supports being
operative on multiple platforms. It is useful for both CNN
and RNN.

Chapter 6: Introduction to Deep Learning 30

Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Neural Network

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 31

Deep Learning Applications
◼ Now, it is time we answered the million-
dollar question, “which are common
applications of Deep Learning in Artificial
Intelligence (AI)?”

Chapter 6: Introduction to Deep Learning 32

Healthcare
The healthcare sector has long been one of the
prominent adopters of modern technology to overhaul
itself.
As such, it is not surprising to see Deep Learning
finding uses in interpreting medical data for:
◼ The diagnosis, prognosis & treatment of diseases

◼ Drug Prescription

◼ Analyzing and Classifying MRIs, CT scans, X-Rays,

etc., to detect and notify about medical anomalies
◼ Personalizing Treatment

◼ Monitoring the Health of Patients and more

Chapter 6: Introduction to Deep Learning 33

Fake News Detection
◼ The concept of spreading fake news to tip the scales in one’s
favor is not old. However, due to the explosive popularity of
the internet, and social media platforms, in particular, fake
news has become ubiquitous.
◼ Fake news, apart from misinforming the citizens, can be used
to alter political campaigns, vilify certain situations and
individuals, and commit other similar morally illegible acts. As
such, curbing any and all fake news becomes a priority.
◼ Deep Learning proposes a way to deal with the menace of
fake news by using complex language detection techniques
to classify fraudulent news sources.
◼ This method essentially works by gathering information from
trusty sources and juxtaposing them against a piece of news
to verify its validity.

Chapter 6: Introduction to Deep Learning 34

Facial Recognition
◼ Facial Recognition is the technological method of
identifying individuals from images and videos by
documenting their faces. It uses advanced biometric
technology to record a person’s face and match it
against a database to extract their identity.
◼ Facial Recognition is an old technology, first
conceptualized in the 1960s. However, it is the
integration of neural networks in facial recognition that
exponentially increased its detection accuracy.
◼ Deep Learning enforced Facial Recognition works by
recording face embeddings and using a trained model to
map them against a huge database of millions of
images.

Chapter 6: Introduction to Deep Learning 35

Road map
◼ What is Deep Learning
◼ Limitations of Machine Learning

◼ Anatomy of a Deep Neural Network

◼ Deep Learning Algorithms

◼ Deep Learning Frameworks

◼ Deep Learning Applications

◼ Further Resources

Chapter 6: Introduction to Deep Learning 36

Further Resources!
❑ This course is largely “inspired by”: “Deep
Learning with Python” by François Chollet
❑ Recommended textbook: “Deep learning”
by Goodfellow, Bengio, Courville
❑ Lots of further material available online, e.g.:
I. http://cs231n.stanford.edu/
II. http://course.fast.ai/
III. https://developers.google.com/machine-learning/crash-
course/
IV. www.nvidia.com/dlilabs
V. http://introtodeeplearning.com/
VI. https://github.com/oxford-cs-deepnlp-2017/lectures,
VII. https://jalammar.github.io/
Chapter 6: Introduction to Deep Learning 37
 Thank You!

Chapter 6: Introduction to Deep Learning 38