Scribd
Upload
35 views34 pages

EE5075 Lecture 3A Correct

Uploaded by

Kalindu Liyanage
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
35 views34 pages

EE5075 Lecture 3A Correct

Uploaded by

Kalindu Liyanage
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 34

EE5075

Artificial Intelligence Applications

LECTURE 3A

Machine Learning -
By Python - Introduction
By Buddhika Jayasekara ([email protected])
Artificial Intelligence (AI)
Artificial Intelligence: the study of how to produce machines that have some of
the qualities that the human mind has, such as the ability to understand language,
recognize pictures, solve problems, and learn Ref: Cambridge Dictionary

Perceive Environment
(Vision)

Communication Knowledge
(Natural Language Representation
Processing)
Robots

AI Intelligence

Automated
Reasoning Machine Learning

Manipulate
(Robotics)
Automated systems

2
AI
technique

Natural
Intelligence
Intelligent Solution

Physical
presence
(Hardware/
Software)

8/24/2024 9:13 AM 3
Machine Learning - Artificial Neural Network (ANN)
Machine Learning
Human Learning
Inputs Weights
p1 w1

w2
a
p2
w3 f Output
p3

1
Bias
a = f (p1 w1 + p2 w2 + p3 w3 + b ) = f ( pi wi + b )

Artificial Neuron

Human brain Neuron

Artificial Neural Network (ANN)

Body → Machine / System


Biological Neuron Network
4
Python

❑ Interpreted high-level general-purpose programming


language
❑ Supported by series of libraries
❑ Available in different distributions
❑ Ref: https://www.python.org/

https://wiki.python.org/moin/
PythonDistributions

5
6
Python - Numpy

❑ Most popular machine learning library in Python


❑ Use by TensorFlow and other libraries for performing multiple
operations on Tensors
❑ Makes complex mathematical implementations very simple

7
8
Scikit-Learn

❑ For working with complex data


❑ For standard machine learning and data mining tasks like
reducing dimensionality, classification, regression, clustering,
and model selection

9
10
Pandas

❑ A machine learning library in Python


▪ provides data structures of high-level
▪ a wide variety of tools for analysis
❑ Inbuilt methods for grouping, combining data, and filtering, as
well as time-series functionality

11
12
Matplotlib

❑ A comprehensive library for creating static, animated, and


interactive visualizations in Python

13
14
Keras

❑ A machine learning library in Python


❑ Supports almost all the models of a neural network – fully
connected, convolutional, pooling, recurrent

15
16
TensorFlow

❑ Tensors are N-dimensional matrices


❑ Works like a computational library for writing new algorithms
that involve a large number of tensor operations
❑ Neural networks can be easily expressed as computational
graphs
▪ implemented using TensorFlow as a series of operations on Tensors

17
18
Notebook

❑ Google Colab
▪ Colaboratory, or “Colab” for short, is a
product from Google Research
▪ Hosted by Google
▪ Access to GPU and TPU
▪ Many libraries for deep learning, machine
https://colab.research.google.com/
learning, data science
▪ Stored in google Drive

❑ Other options
▪ Jupyter Notebook

https://jupyter.org/

19
Getting Started with Colab

❑ Goto https://colab.research.google.com/ or
❑ Create Collab notebook in Google Drive

20
Getting Familiar with Libraries

21
22
23
24
25
26
Slicing

27
Boolean
Masking

28
Documentation

❑ At https://numpy.org/

29
30
Built on
Numpy

31
32
Documentation

❑ At https://pandas.pydata.org/

33
Any Questions

34

You might also like