1. An Introduction to
Machine Learning and Deep Learning
Workshop-01

2. What is Machine Learning?

3. Supervised Learning
•
•

4. Linear
Regression
Linear Regression is the
supervised Machine Learning
model in which the model finds
the best fit linear line between the
independent and dependent
variable i.e. it finds the linear
relationship between the
dependent and independent
variable.

5. Parameters
:
Hypothesis:
Cost Function:
Goal:
• Our Goal now is to minimise the error. i.e. to
minimise the Cost function.
• We need to find the perfect parameters
such that the mean error is minimum.
Understanding the Mathematical and Intuitive Aspects

6. Logistic
Regression
• Type of statistical model (also
known as logit model), often
used for classification and
predictive analytics.
• Logistic regression estimates
the probability of an event
occurring, such as voting or
not voting, based on a given
dataset of independent
variables.

7. we have,
We use the "Sigmoid Function," also called the "Logistic
Function":
g(z) outputs a value between 0 and
1
Cost Function:
Prediction
:

8. Remember that the general form of gradient descent
is:
We can fully write out our entire cost function as
follows:
Gradient
Descent:

9. k-nearest
neighbours algorithm
This algorithm is based on the assumption
that data points that are close to each other
in space are more likely to belong to the
same class.
Choosing the value of K:

10. What is Unsupervised learning?
•
•

11. k-means
algorithm
Step 0: Randomly initialise k cluster
centroids.
Repeat {
Step 1: Assign points to cluster
centroids
Step 2: Move cluster centroids.
}

13. DEEP LEARNING
•
•

14. Why Deep Learning?

15. The people in these photos are
infact not real. Yes!! These
people do not exist.
reference: thispersondoesnotexist.com
An architecture called StyleGAN
is used to generate these
almost real faces.
StyleGAN is a modified architecture
of Generative Adversarial
Networks(GANs) which is capable of
generating real-life images

16. Artificial Neural Networks
The term "Artificial Neural Network" is derived from Biological
neural networks that develop the structure of a human brain.
Similar to the human brain that has neurons interconnected to
one another, artificial neural networks also have neurons that are
interconnected to one another in various layers of the networks.
These neurons are known as nodes.
A Biological Neuron
A typical ANN

17. Mathematics behind Neural Networks

18. Convolutional Neural Networks
• A Convolutional Neural Network, also known as CNN or ConvNet, is a class of neural networks that specializes
in processing data that has a grid-like topology, such as an image.
• A digital image is a binary representation of visual data. It contains a series of pixels arranged in a grid-like
fashion that contains pixel values to denote how bright and what color each pixel should be.
A CNN typically has three layers: convolutional,pooling and a fully connected layer.

19. Principle of convolution
• The principle of the convolution is to slide across the input image from the left to the
right and from the top to the bottom using a specific size window.
• The sliding window in the CNN is called the filter (or kernel), and the area slipped by the
filter is called the receptive field.
• The matrix and the pixel values of the images multiply when the convolutional layer
passes the filter after that the values are added and then deviation value is added.
𝑦=∑(𝑥𝑖𝑗×𝑓𝑖𝑗)+𝑏
Calculation process for the features of the convolution layer

20. Recurrent Neural Networks
• A recurrent neural network (RNN) is a type of artificial neural network which uses sequential data or time series data.
• These deep learning algorithms are commonly used for ordinal or temporal problems, such as language translation,
natural language processing (nlp), speech recognition, and image captioning.
• Like feedforward and convolutional neural networks (CNNs), recurrent neural networks utilize training data to learn.
They are distinguished by their “memory” as they take information from prior inputs to influence the current input and
output.
• While traditional deep neural networks assume that inputs and outputs are independent of each other, the output of
recurrent neural networks depend on the prior elements within the sequence.

21. Transformers

22. Generative Adversarial Networks(GANs)
• 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 made up of two neural networks
named Generator and Discriminator.
• The generator part of a GAN learns to create
fake data by incorporating feedback from the
discriminator. It learns to make the
discriminator classify its output as real.
• The discriminator in a GAN is simply a
classifier. It tries to distinguish real data from
the data created by the generator. It could
use any network architecture appropriate to
the type of data it's classifying.

23. Resource
s
• Andrew NG machine learning specialisatiation
• Pytorch Turtorials by Daniel Bourke
• TensorFlow tutorials by Alladin perssson
• Andrew NG Deep Learning Specialisation
• Summer Analytics 2023, IIT Guwahati