Introduction to Artificial Intelligence

Lesson 2: Fundamentals of Machine Learning and Deep Learning

© Simplilearn. All rights reserved.

Learning Objectives

Discuss the meaning of machine learning and its relationship with AI

Describe the relationship between machine learning and statistical analysis

Explain the process of machine learning

List and compare the types of machine learning

Analyze different algorithms of machine learning

Explore the meaning of deep learning and artificial neural networks

Fundamentals of Machine Learning and Deep Learning
Topic 1: Meaning of Machine Learning
Meaning of Machine Learning

AI
Machine learning (ML) is an
It involves teaching a computer to recognize
application of artificial intelligence. ML
patterns in the data and creating rules rather
than programming it in traditional methods.

It provides an ability to machines to

automatically learn and improve from
experience without being explicitly The process of learning begins with

programmed. observations or data, such as direct

experience, or instructions to look for
patterns in the data.
Definition of Machine Learning

Machine learning can be defined as an approach to achieve

artificial intelligence through systems or software models that
can learn from experience to find patterns in a set of data.
Google Utilizing AI

Google uses artificial intelligence and machine learning in almost all of its applications.
Google Utilizing AI

Google Photos uses machine learning in smart search to display photos related to the keywords you
searched for and animate similar photos from your albums into quick videos.

The Smart Compose and Smart Reply features of Gmail uses AI to suggest phrases and
complete sentences when you draft an email or a reply. The spam filter uses artificial neural
networks to analyze and flag spam messages.

Google Assistant has recently launched a new feature called Google Duplex that lets AI take
over some real-world task such as booking a haircut appointment over phone.

The feature Talk to Books lets you make a statement or ask a question and surfaces relevant
passages from the books using machine learning.
Relationship Between AI, ML, and DL

• AI gained popularity in 1950, ML in 1980, and DL in 2010.

• Deep learning is a subset of machine learning, which is a subset of artificial intelligence.
Fundamentals of Machine Learning and Deep Learning
Topic 2: Relationship Between Machine Learning and Statistical Analysis
Importance of Data and Statistical Analysis

• Machine learning depends largely on data to study patterns.

• A large amount of data and statistical analysis of this data is required
for ML.
• Statistical analysis involves collecting and scrutinizing the data
sample to identify trends.
• A statistical model is a formalization of relationships between
variables in the form of mathematical equations.
Machine Learning and Statistical Analysis

Machine learning Statistical Analysis

• Machine learning is a • Statistical analysis belongs

subset of artificial to the field of
intelligence in the field of mathematics and deals with
computer science. finding a relationship
• Machine learning is between variables to
associated with high- predict an outcome.
dimensional data. • Statistical analysis deals
with low-dimensional data.

The goals of machine learning and statistical analysis are same, but
the formulations are significantly different.
Formulations of ML and Statistical Analysis

Machine learning Statistical Analysis

It takes away the deterministic function f out It tries to estimate the function f:
of the equation: Dependent Variable (Y) = f (Independent Variable)
Output(Y) ----- > Input (X) + Error Function
Naming Conventions of ML and Statistical Analysis

Machine learning Statistics

Network, graphs Model
Weights Parameters
Learning Fitting
Generalization Test set performance
Supervised learning Regression/classification
Unsupervised learning Density estimation, clustering
Large grant = $1,000,000 Large grant = $50,000
Nice place to have a meeting: Nice place to have a meeting:
Snowbird, Utah, French, Alps Las Vegas in August
Fundamentals of Machine Learning and Deep Learning
Topic 3: Process of Machine Learning
Approach of Machine Learning

ML leverages on existing data, images, and videos to train algorithms and models.

Numerous set of examples are fed into the system and are called training sets.

The larger the training set, the more accurate the AI system would be.

0 1 Each item in a training set is labeled either 0 or 1.

Machine Learning Process
A machine learning process can be divided into two phases: training and testing.

Labeled training data

Machine learning

+ Expected Learned model

Input data algorithm
output

Test data
Predictions
Learned model
Input data Output
Machine Learning Process
Training Phase

Labeled training data

Machine learning

+ Expected Learned model

Input data algorithm
output

Labeled data is given as input The algorithm studies the A machine learning model is
into the algorithm along with the patterns in the data and works derived, which can then be
expected output or labels. This is out a logic based on the used with test dataset.
called the training data. training data input and output.
Machine Learning Process
Testing Phase

Test data
Predictions
Learned model
Input data Output

The test data contains only the The system classifies the test data The patterns from the test
inputs, and the output is based on the patterns learned data and the logic of the
generated by the system based from the training data. learned model are used to
on the logic derived from the make predictions and derive
training data. output.
Fundamentals of Machine Learning and Deep Learning
Topic 4: Types of Machine Learning
Types of Machine Learning

There are four main types of machine learning:

Supervised Learning Unsupervised Learning Semi-supervised Learning Reinforcement Learning

Meaning of Supervised Learning

• In case of supervised learning, the ML program is provided with training data along
with the expected output or rules to categorize this data also known as labels.
• The ML system uses this set of inputs and outputs to predict the output for future
unseen inputs. It works well in the classification.
Supervised Learning Process

Labeled training data

Machine learning

+
Input data Expected Learned model
algorithm
features output
Supervised Learning Example

Known Data Step one: Train the model

• Provide images of apples along with the
expected response to the model. This is called
Model
the labeled data.
Known Response

These are
Apples
Supervised Learning Example

Step two: Test the model

New Response
• The model learns from the labeled data.
? These are
apples
• Provide a set of images to the model again
New data Model
without the expected output.
• The output of the model is, “These are apples.”
Supervised Learning Example

Predicting house prices based on various features

Number of
Bathrooms Garage space Year it was built Location
rooms
Meaning of Unsupervised Learning

• In case of unsupervised learning, the machine learning algorithm learns from an

unlabeled dataset. Only the input data is used by the algorithm to train the model.
• The algorithm is expected to find patterns and anomalies from this input data.
• This method is mostly used in fraud detection, customer segmentation, and MRI analysis.
Unsupervised Learning Process

Training data
Machine learning
Input data Learned model
algorithm
features
Unsupervised Learning Example: Image Identification

Step one: Input unlabeled data

• We provide the system with a data that contains
photos of different kinds of fruits without the
expected output. This is called the unlabeled data.
Model
• The goal of unsupervised learning models is to
Known
data understand the output from given data and notice
patterns, trends, and similarities.
Unsupervised Learning Example: Image Identification

Visible
Pattern
Step two: Train the model
• The model identifies the patterns like shape, color,
and size in the data.
• It groups the fruits based on these features,
Model
attributes, or qualities.
Known
data
Unsupervised Learning Example: Litterati

• Litterati, the global database for litter, uses unsupervised

learning to organize geographical litter locations using
clustering.
Unsupervised Learning Example: Mouse Clicks

• Unsupervised learning is used to understand the users’ mouse clicks on a

web page or a website.
• It helps companies understand the user browsing patterns.
Meaning of Semi-supervised Learning

• Semi-supervised learning is a hybrid approach and is a

combination of supervised and unsupervised learning.
• It uses a combination of labeled and unlabeled data.
Semi-supervised Learning Example

Labeled data

Step one: Collect and group data

• Collect and group labeled and
unlabeled data for training.

Training data

Unlabeled data
Semi-supervised Learning Example

Step two: Input data

• Feed all the training data into the

Model model.
Training data
Meaning of Reinforcement Learning

• Reinforcement learning is a type of machine learning that

allows the learning system to observe the environment and
learn the ideal behaviour.
• The learning system (agent) observes the environment,
selects and takes certain actions, and gets rewards in return
(or penalties in certain cases).
• The feedback is given to the system or agent in a loop.
• The agent learns the strategy or policy (choice of actions)
that maximizes its rewards over time and tries to maximize
the cumulative reward.
Reinforcement Learning Example: Robot

• Robot is an agent trying to manipulate the

Robot environment, which is the surface.

• This happens as the robot walks and tries to go
Reward Walking from one state to another.
• It gets a reward for accomplishing a sub module

Surface of the task (taking couple of steps).

Reinforcement Learning Example: Robot

• In a manufacturing unit, a robot uses deep

reinforcement learning to identify a device from one
box and put it in a container.
• The robot learns this by means of a rewards-based
learning system, which incentivizes it for the right
action.
Selecting the ML Approach

The data modeling approach for machine learning is based on the

structure and volume of the data at hand, regardless of the use case. Any
of the following approaches can be chosen considering all the factors.

Supervised Learning Unsupervised Learning Semi-supervised Learning Reinforcement Learning

Quiz Time

Guess what ML approach is used

Supervised Learning
by spam detection?

Unsupervised Learning

Semi-supervised Learning

Reinforcement Learning
Quiz Time

Guess what ML approach is used

Supervised Learning
by spam detection?

Unsupervised Learning

Semi-supervised Learning

Reinforcement Learning
Fundamentals of Machine Learning and Deep Learning
Topic 5: Algorithms of Machine Learning
Machine Learning Algorithms

• There are four main types of machine learning algorithms.

• The choice of the algorithm depends on the type of data in the use case.
Types of Supervised Learning

The two main types of supervised learning that use labeled data are
regression and classification.
Classification

• Classification is applied when the output has finite and

discrete values.
• For example, social media sentiment analysis has three
potential outcomes: positive, negative, or neutral.
Regression

• Regression is applied when the output is a continuous

number.
• A simple regression algorithm: y = wx + b. For example,
relationship between environmental temperature (y) and
humidity levels (x).
Classification vs. Regression

By fitting to the labeled training set, you can find the most optimal model
parameters to predict unknown labels on other objects (test set).

If the label is a real number, we call the task regression. If the label is from the limited number of unordered
For example, finding actual value of house price based values, we call it classification. For example,
features like location, construction year, etc. classifying images of animals into separate groups
(labels) of dogs and cats.
Linear Regression

• Linear regression is an equation that describes a line

that represents the relationship between the input
variables (x) and the output variables (y).

• It does so by finding specific weightings for the input

variables called coefficients (B).
Quiz Time

Which of these is a use case for

Spam detection
linear regression?

Google Translate

Car mileage based on brand,

model, year, weight, etc.

Robot learning to walk

Quiz Time

Which of these is a use case for

Spam detection
linear regression?

Google Translate

Car mileage based on brand,

model, year, weight, etc.

Robot learning to walk

Meaning of Decision Tree

• A decision tree is a graphical representation of all the

possible solutions to a decision based on a few conditions.
• It uses predictive models to achieve results.
• A decision tree is drawn upside down with its root at the
top.
Classification and Regression Trees

• The tree splits into branches based on a condition or internal

Decision Root Node
node.
Node Commute more

Yes
than 1 hour
No
• The end of the branch that doesn’t split anymore is the
decision/leaf.
Commute more
than 1 hour
Decline offer • In this case, the condition whether the employee accepts or
Yes rejects the job offer is represented as green oval shaped
No
boxes.
Offers free
coffee
Decline offer
• This tree is called as classification tree as the target is to
classify whether the job is accepted by the employee or not.
Yes

No

• Regression trees are represented in the same manner, but

Decline offer
they predict continuous values like price of a house.
Decision Tree:

• Decision tree algorithms are referred to as CART or

Should I accept a new
Job offer? Decline offer

Classification and Regression Trees.

• Each node represents a single input variable (x) and a split
point on that variable, assuming the variable is numeric.
Quiz Time

Can you think of a use case for

decision tree?
Naive Bayes

• Naive Bayes is a simple but surprisingly powerful algorithm for predictive modeling.
• The model comprises of two types of probabilities: the probability of each class and
the conditional probability of each class based on the value of x.
• Once calculated, this probability model can be used to make predictions for new data
using Bayes theorem.
• The probabilities can be easily estimated as bell curve when your data is real valued.
Naive Bayes Example

How does an email client classify between valid and spam emails?

Spam/Junk Ham/Inbox
Naive Bayes Classification

• The objects can be classified as either green or red. The task is to classify new cases
as they arrive.
• For Example, using Naïve Bayes, you can classify the class labels based on the
current objects.
• Since there are twice as many green objects as red, it is reasonable to believe that a
new case (which has not been observed yet) has same ratio.
Naive Bayes Classification

• In Bayesian analysis, this belief is known as prior probability.

• Prior probabilities are based on previous experience.

• Prior probability of green: number of green objects/total number of objects

• Prior probability of red: number of red objects/total number of objects

Naive Bayes Classification

Since there is a total of 60 objects, 40 of which are green and 20 are red, prior probabilities
for class membership are:
• Prior probability for green: 40/60
• Prior probability for red: 20/60 (number of red objects/total number of objects)
Naive Bayes Classification

• The more green (or red) objects there are in the vicinity of X, the more likely that the new
cases will belong to that particular color.

• To measure the likelihood, draw a circle around X which encompasses a number of points
irrespective of their class labels.

• Then, calculate the number of points in the circle that belong to each class label.
Naive Bayes Classification
CALCULATION OF LIKELIHOOD

In this illustration, it is clear that likelihood of X given GREEN is smaller than Likelihood of
X given RED, since the circle encompasses 1 GREEN object and 3 RED ones.
Naive Bayes Classification
CALCULATION OF PRIOR PROBABILITY

• Although the prior probabilities indicate that X may belong to GREEN (given that there
are twice as many GREEN compared to RED) the likelihood indicates otherwise.
• The class membership of X is RED (given that there are more RED objects in the vicinity
of X than GREEN).
• In Bayesian analysis, the final classification is produced by combining both sources of
information, i.e., the prior and the likelihood, to form a posterior probability using
Bayes' rule (named after Rev. Thomas Bayes 1702-1761).
Naive Bayes Classification
CALCULATION OF PRIOR PROBABILITY
Naive Bayes Classification

Finally, we classify X as RED since its class membership achieves the largest posterior probability.
Machine Learning Algorithms

The next algorithm is K-Means clustering.

K-Means Clustering

• K-Means clustering is an algorithm that can be used for any type of grouping.
• Examples of K-Means clustering:
o Group images
o Detect activity types in motion sensors
o Separate bots from anomalies
o Segment by purchasing history
• Meaningful changes in data can be detected by monitoring to see if a tracked data point
switches groups over time.
K-Means Clustering: Use Cases

Behavioral Inventory Sorting sensor Detecting bots or

segmentation categorization measurements anomalies

Segment by purchase Group inventory by Detect activity types in Separate valid activity
history sales activity motion sensors groups from bots

Segment by activities Group valid activity to

Group inventory by
on application, Group images clean up outlier
manufacturing metrics
website, or platform detection

Define personas
Separate audio
based on interests

Create profiles based Identify groups in

on activity monitoring health monitoring
K-Means Clustering for Unsupervised Learning

• To run a K-Means algorithm, randomly initialize three points called the cluster centroids.

• There are three cluster centroids in the image given below since data is grouped into three
clusters.

K-Means is an iterative algorithm and it involves two steps:

Step 1: Cluster assignment Step 2: Move centroid step

K-Means Clustering for Unsupervised Learning

Step 1:

Algorithm travels through data points, depending on which cluster is closer.

It assigns it to red, blue, or green cluster.

Step 2:

Algorithm calculates average of all points in cluster and moves centroid to the average location.
K-Means Clustering for Unsupervised Learning

• Steps 1 and 2 are repeated until there are no changes in clusters or when the specified
condition is met.

• K is chosen randomly, or elbow plot/silhouette score helps decide it.

Fundamentals of Machine Learning and Deep Learning
Topic 6: Deep Learning
Introduction to Deep Learning

ML
Deep learning (DL) is a subset of
The term deep learning refers to deep
machine learning. DL
artificial neural networks, and less frequently
to deep reinforcement learning.

Deep Neural Networks or DNNs use

techniques that mimic the human brain.
DNNs have set new records in accuracy for
The DNN algorithms are arranged in layers
many problems such as image recognition
and they learn patterns of the patterns.
and recommender system.
Definition of Deep Learning

Deep learning is a specialized form of machine learning that uses supervised,

unsupervised, or semi-supervised learning to learn from data representations.
It is similar to the structure and function of the human nervous system, where
a complex network of interconnected computation units work in a coordinated
fashion to process complex information.
Neural Networks of Human Brain

Biological Neuron • Our brain consists of approximately 86 billion

interconnected neurons.
• Neurons are interconnected nerve cells in the
human brain that are involved in processing and
transmitting chemical and electrical signals.
• They take input and pass along outputs.
• Each neuron responds to certain stimuli and
passes output to another.
Neural Networks of Human Brain

• A human brain can learn how to identify objects from photos.

• For example, the brain could use several neurons to understand and
interpret that the animal seen is a dog (with details such as fur, eyes,
tail, etc).
• Each of these neurons may have a different weightage (governed by
how important the feature is) to the overall image.
• If all these neurons fire in the same direction, our brain tells us that
we saw a dog.
• Furthermore, neurons also fire up to tell us that what kind of dog it is
(Doberman, German shepherd etc).
Neural Networks of Human Brain

• Babies, from the time they are born until they grow up to be
toddlers, learn to recognize and distinguish multiple objects like
trees, dogs, cats, bottles etc.
• The more data you feed or teach them, the better their recognition
capabilities become.
• Imagine the number of “training” examples of each they must have
seen to be able to distinguish these things.
• The same goes for machine learning and deep learning applications
like facial recognition, image/object recognition, etc. The more data
we feed the model, the better it becomes.
Artificial Neural Networks

• Neural networks are a set of algorithms that are modeled loosely

after the human brain and are designed to recognize patterns.
• The multiple layers of training are called Artificial Neural Networks
(ANN).
• Each input is separately weighted, and the sum is passed through
a non-linear function known as an activation function or transfer
function.
Artificial Neural Network: Definition

“Artificial Neural Network (ANN) is a computing system made up of a

number of simple, highly interconnected processing elements which process
information by their dynamic state response to external inputs.”
- Robert Hecht-Nielsen
Features of Artificial Neuron

• Artificial neurons interpret sensory data through machine perception,

labeling, or clustering raw input.

• They recognize numerical patterns contained in vectors. These vectors

contain real world data such as images, sound, text, or time series.

• Neural networks help to cluster and classify the raw input.

• They can be considered a clustering and classification layer on top of

the data stored and managed.

• They classify labeled dataset based on expected results.

• They group unlabeled dataset based on the similarities in the inputs.

Definition of Perceptron

A perceptron is a neural network unit (an artificial neuron) that does certain
computations to detect features or business intelligence in the input data.
Meaning of Multilayer Perceptron

• The field of artificial neural networks is often called neural networks or multilayer perceptron.

• A perceptron is a single neuron model that is a precursor to larger neural networks.

• It investigates how simple models of biological brains can be used to solve difficult computational
tasks like the predictive modeling in machine learning.

• The goal is to develop robust algorithms and data structures that can be used to model difficult
problems.
Structure of Multilayer Perceptron
Outputs

Activation • A row of neurons is called a layer, and one network can have
weights multiple layers.
• The architecture of the neurons in the network is often called
Inputs the network topology.
Model of a simple neuron • Layers after the input layer are called hidden layers because
they are not directly exposed to the input.

Output layer • The simplest network structure is to have a single neuron in the
hidden layer that directly outputs the value.
Hidden • The final hidden layer is called the output layer.
layer

Input layer

Model of a simple network

Online and Batch Learning

• Once configured, the neural network needs to be trained on the dataset.

Online The weights in the network are updated from the errors calculated for each
learning training example. This is called online learning.

Batch The errors can be saved up across all of the training examples, and the
learning
network can be updated at the end. This is called batch learning.

• Once a neural network has been trained, it can be used to make predictions.
Deep Neural Networks

• Artificial Neural Networks (ANN) are multi- • Deep Neural Networks (DNN) are layers that
layer fully-connected neural nets. have more than one hidden layer between input
and output layers.
Convolutional Neural Networks (CNN)

Convolutional Neural Networks

• Convolutional Neural Networks

(CNN) are neural networks
mainly used for image
processing and classification.
Convolutional Neural Network (CNN)

Until quite recently, computers were not good at tasks like recognizing a
puppy in a picture or recognizing spoken words, which humans excel at.
Uses of CNN

CNN is trained and used in the following ways:

Automatic video
classification systems
Voice recognition
Self-
driving
cars

Natural
Image language
search processing
CNN Applications
Quiz Time

Do you think artificial intelligence would

surpass human intelligence?
Predicted Future: AI in News

Google develops artificial intelligence algorithm

that predicts your death with 95% accuracy. Singularity is predicted to be achieved by 2045
when computers will have the same level of
intelligence as that of humans.

Forbes estimates that 85% of customer

interactions will be managed by AI by 2020.

The world’s leading car manufacturers predict driverless

cars will be on the streets by 2020–2030.
Doomsday AI machines could lead to
nuclear war, think tank paper warns.
Predicted Future of AI

Source: https://www.Time.com/
Future Forecasted Revenue of AI

Source: https://www.statista.com/
Quiz
QUIZ
What are the different ways in which a machine can learn?
1

a. Supervised and unsupervised

b. Supervised, unsupervised, and semi-supervised

c. Unsupervised and semi-supervised

d. Supervised and semi-supervised

QUIZ
What are the different ways in which a machine can learn?
1

a. Supervised and unsupervised

b. Supervised, unsupervised, and semi-supervised

c. Unsupervised and semi-supervised

d. Supervised and semi-supervised

The correct answer is b

Supervised, unsupervised, and semi-supervised

QUIZ
Give applications of each type of machine learning.
2

a. Supervised: clustering, unsupervised: airplane booking, semi-supervised: Image recognition

b. Supervised: web page classification, unsupervised: spam detection, semi-supervised:

mapping or clustering

c. Supervised and unsupervised: bioinformatics, semi-supervised: mapping or clustering

d. Supervised: bioinformatics, unsupervised: supply chain carrier analysis, mapping/clustering,

semi-supervised: web page classification
QUIZ
Give applications of each type of machine learning.
2

a. Supervised: clustering, unsupervised: airplane booking, semi-supervised: Image recognition

b. Supervised: web page classification, unsupervised: spam detection, semi-supervised:

mapping or clustering

c. Supervised and unsupervised: bioinformatics, semi-supervised: mapping or clustering

d. Supervised: bioinformatics, unsupervised: supply chain carrier analysis, mapping/clustering,

semi-supervised: web page classification

The correct answer is d

Supervised: bioinformatics, unsupervised: supply chain carrier analysis, mapping/clustering, semi-

supervised: web page classification
QUIZ
What are some of the machine learning Algorithms?
3

a. Decision trees, XGboost, Google Vision API

b. Random forests, regression (linear and logistic) but not KNN

c. Regression, decision trees, Naive Bayes, K-Means clustering

d. XGboost, Adaboost, regression except Naive Bayes

QUIZ
What are some of the machine learning Algorithms?
3

a. Decision trees, XGboost, Google Vision API

b. Random forests, regression (linear and logistic) but not KNN

c. Regression, decision trees, Naive Bayes, K-Means clustering

d. XGboost, Adaboost, regression except Naive Bayes

The correct answer is C

Regression, decision trees, Naive Bayes, K-Means clustering

QUIZ
What is the basic concept of deep learning?
4

a. Deep learning is a subset of machine learning in Artificial Intelligence (AI) with networks
capable of learning unsupervised from data that is unstructured or unlabeled.

b. Machine learning is a subset of deep learning in Artificial Intelligence (AI) that has human
brain networks capable of learning unsupervised from data that is unstructured or unlabeled.

c. Deep learning is a set of algorithms that are arranged one after another in tandem (like
regression, KNN, Naive Bayes, decision trees), to enable maximum accuracy.

d. None of the above

QUIZ
What is the basic concept of deep learning?
4

a. Deep learning is a subset of machine learning in Artificial Intelligence (AI) with networks
capable of learning unsupervised from data that is unstructured or unlabeled.

b. Machine learning is a subset of deep learning in Artificial Intelligence (AI) that has human
brain networks capable of learning unsupervised from data that is unstructured or unlabeled.

c. Deep learning is a set of algorithms that are arranged one after another in tandem (like
Regression, KNN, Naive Bayes, decision trees), to enable maximum accuracy.

d. None of the above

The correct answer is a

Deep learning is a subset of machine learning in Artificial Intelligence (AI) that has networks capable
of learning unsupervised from data that is unstructured or unlabeled. Also known
as Deep Neural Learning or Deep Neural Network.
Key Takeaways

Machine learning algorithm learns from data, whereas statistical model is a

formalization of relationships between variables.

Supervised learning, unsupervised learning, and semi-supervised learning are

the three types of machine learning.

Reinforcement learning is an area of machine learning which is used when the

training data has a feedback loop.

A decision tree is a tree-like graph that uses the branching method to

demonstrate every possible outcome of a decision.

Naive Bayes' is a classification technique which assumes that the presence of a

particular feature in a class is unrelated to the presence of any other feature.

K-means clustering is a type of unsupervised learning, which is used to solve

clustering problem.

Neural networks are set of algorithms that are modeled loosely after the
human brain and are designed to recognize patterns.
This concludes “Fundamentals of Machine Learning
and Deep Learning.”
The next lesson is “Machine Learning Workflow.”

©Simplilearn. All rights reserved