Machine learning

diploma
Lecture 1
 Agenda
Introduction

Python 2 vs python 3

Python installation

Anaconda and Jupiter notebooks environment

Machine learning introduction

 WHAT THIS DIPLOMA COVERS
1 2 3
Python Linear algebra Calculus and
Basics to advanced statistics
Most needed chapters to
syntax dive in machine learning Most needed chapters to
data science stack dive in machine learning

4 5
Machine learning Capstone project
Putting all together in one
Supervised, unsupervised
big project
and reinforcement
learning algorithms
Projects we
will do Capstone project
Kaggle projects

Machine learning projects

Tasks related to all algorithms of machine learning
we will take

Data analysis projects

Tasks related to scientific stack: pandas , Numpy
and Matplotlib

Python projects
Many tasks that covers every single lesson we take
 Python curriculum
Part 1: Object and Part 2: statements, Part 3: oop,errors and
data structure basics methods and exception handling
functions
• Numbers • Objects
• Strings • If statements • Classes
• Lists • For loop • Methods
• Dictionaries • While loop • Inheritance
• Tuples • Range() • Special methods
• Files • List comprehension • Errors
• Sets • Methods • Exceptions
• Booleans • Function
• Try. Except
• Basic operators • Lambda expression
• Chained
• finally
• Nested statements
comparison • scopes
operators
 Python curriculum
Part 4: Part 5: introduction to Part 6: data analysis
modules,packges and gui and visualization
built in functions packages
• Tkinter library
• Creating modules • Concepts • Numpy
• Installing modules • widgets • Pandas
• Map • Geometry • Matplotlib
• Reduce management • Seaborn
• Filter • Event handling • Plotly
• Zip • Build an application
• Enumerate
• Decorators
• Generators
 Mathematics curriculum
Part 1: linear algebra Part 2: statistics Part 3: calculus

• vectors • Statistical • Derivatives

• Linear visualization • Chain rule
combinations • probability • Product rule
• Linear • Bayes rule • limits
transformation and • Estimators
matrices • Outliers
• Dot product and
cross product
 Machine learning curriculum
Part 1: regression Part 2: classification Part 3: clustering

• Linear regression • Logistic regression • K-means clustering

• Multi linear • KNN • Hierarchical
regression • Decision tree Clustering
• SVR • Random forest • DBSCAN
• Decision tree • SVM
• Random forest • Naive Bayes
 Python curriculum
Part 4: model Part 5: reinforcement Part 6: NLP,deep
validation learning and learning and big data
recommendation
• Confusion matrix systems • Intro to natural
• R squared language
• Cross validation • Upper Confidence processing
• Bias trade off Bound (UCB) • Neural network
• Thompson • Convolution neural
Sampling network
• Building simple • Big data with spark
recommendation
system
Section
Break
Software needed

Anaconda is a free and open-source distribution of

the Python and R programming languages for scientific
computing (data science, machine learning applications,
large-scale data processing, predictive analytics, etc.),
that aims to simplify package management and
deployment.
 Why python
Python combines remarkable power with very clear syntax. Python is
also usable as an extension language for applications written in other
languages that need easy-to-use scripting or automation
interfaces. Python is widely considered as the preferred language for
teaching and learning Ml (Machine Learning)

Python properties

Easy You are not alone

Open source Fast

 ARTIFICIAL
INTELLIGENCE

What is AI

The theory and development of

computer systems able to perform
tasks normally requiring human
intelligence, such as visual
perception, speech recognition,
decision-making, and translation
between languages.
 FIELDS OF AI
Machine learning
I hope and I believe that this Template will your Time,
Money and Reputation. Get a modern PowerPoint
Presentation that is beautifully designed.

01
Computer vision
02 I hope and I believe that this
Template will your Time, Money and
Reputation. Get a modern
PowerPoint Presentation that is
beautifully designed.
Natural language processing
I hope and I believe that this 03
Template will your Time, Money and
Reputation. Get a modern
PowerPoint Presentation that is
04
beautifully designed. Robotics
I hope and I believe that this Template will your Time,
Money and Reputation. Get a modern PowerPoint
Presentation that is beautifully designed.
So what is
machine learning
Machine learning is an application
of artificial intelligence (AI) that
provides systems the ability to
automatically learn and improve
from experience without being
explicitly programmed. Machine
learning focuses on the
development of computer programs
that can access data and use it
learn for themselves.
 Types of machine learning
Reinforcement learning
Reinforcement Learning is a type
of Machine Learning, and thereby also a Unsupervised learning
branch of Artificial Intelligence. It allows Unsupervised learning is a type of machine
machines and software agents to learning algorithm used to draw inferences
automatically determine the ideal behavior from datasets consisting of input data
within a specific context, in order to without labeled responses. The most
maximize its performance. common unsupervised learning method is
cluster analysis, which is used for
exploratory data analysis to find hidden
patterns or grouping in data.

Supervised learning
Supervised learning is the Data mining task
of inferring a function from
labeled training data. The training data
consist of a set of training examples.
Machine learning applications

Object detection Self driving cars

Flying cars Recommendation systems

Ml apps

Spam filter Cancer classifiers

 Why machine learning

less time more accuracy Many algorithms by

researchers

High computations ability Many data available