Introduction to AI & Machine Learning | Amr Shawqy | Skillshare

Playback Speed


  • 0.5x
  • 1x (Normal)
  • 1.25x
  • 1.5x
  • 2x

Introduction to AI & Machine Learning

teacher avatar Amr Shawqy, CTO/Cofounder @ExpandCart

Watch this class and thousands more

Get unlimited access to every class
Taught by industry leaders & working professionals
Topics include illustration, design, photography, and more

Watch this class and thousands more

Get unlimited access to every class
Taught by industry leaders & working professionals
Topics include illustration, design, photography, and more

Lessons in This Class

3 Lessons (10m)
    • 1. Lecture 1

      3:35
    • 2. Lecture 2

      3:20
    • 3. Lecture 3

      2:56
  • --
  • Beginner level
  • Intermediate level
  • Advanced level
  • All levels
  • Beg/Int level
  • Int/Adv level

Community Generated

The level is determined by a majority opinion of students who have reviewed this class. The teacher's recommendation is shown until at least 5 student responses are collected.

659

Students

--

Projects

About This Class

This class introduces AI & Machine Learning to anyone who have no idea what those technologies are. After completing this class you will understand clearly what is AI, what is Machine Learning, and what is logic or rule-based AI. Simple introduction explained easily and effectively.

Meet Your Teacher

Teacher Profile Image

Amr Shawqy

CTO/Cofounder @ExpandCart

Teacher

Hi. My name is Amr Shawqy. Entrepreneur at heart, always passionate to learn and teach new technologies covering a wide range of different scientific topics, especially software engineering and data science.

I worked as a software development manager and as a software engineer. I managed teams of 20+ resources working on different technology stacks for different clients located in multiple countries. I coded and engineered software solutions for different organizations using a wide range of technologies.

I always encouraged my teams to innovate and adopt & learn new technologies. That is the key to success in the software business, always stay ahead, always try and invent new stuff.

Currently, I am working as a CTO/Cofounder for ExpandCart, and as a s... See full profile

Class Ratings

Expectations Met?
  • Exceeded!
    0%
  • Yes
    0%
  • Somewhat
    0%
  • Not really
    0%
Reviews Archive

In October 2018, we updated our review system to improve the way we collect feedback. Below are the reviews written before that update.

Why Join Skillshare?

Take award-winning Skillshare Original Classes

Each class has short lessons, hands-on projects

Your membership supports Skillshare teachers

Learn From Anywhere

Take classes on the go with the Skillshare app. Stream or download to watch on the plane, the subway, or wherever you learn best.

Transcripts

1. Lecture 1: welcome toe the AI and machine learning complete course. In this course, you will learn practical examples toe get you up and running in machine learning in a few hours. It will allow you to build your own solutions and applications using machine learning technology. The possibilities are limitless. I want to thank you all for joining the course and hope you enjoy your experience. If you have any questions at any time, just send me in the Q and A section or through the slack community we have discussed before or send me an email. So the email address you have received when you subscribe at this course, I would be more than happy to help you understand any single aspect in this course or in machine learning and other science in general. So just don't hesitate and contact me any time, so make your life easier. In this course, I have included all the coding examples completed on ready Attach it to the lectures. Also, there is a section called important links. It has the important links we discuss here in the lectures on any links that I think useful for your journey to take a look on any or also extra reading materials that you can use also through the course. Any theoretical boards, you will find a Pdf file. Attach it to the section or the lecture related, so that you can read through instead of listening to the theoretical board in the video. If you don't like toe. But it's also explained very well in the video. Serious. So I hope you have fun and let's start our course right now. Understanding AI and machine learning Artificial intelligence is the top trending technology. Today. Almost all business platforms are using this in some form, like website development, mobile application development shed. But search engines and much more toe embodied their solutions with a human like intelligence. After fail, intelligence started to be studied by researchers as off 1943 and it was founded as a day academic discipline in 1956. And since then it has experienced several waves off optimism, followed by disappointment and loss of funding, followed by new approaches, success and renewed funding. So what is AI or artificial intelligence? AI is any technology that makes machines process respond toe data in human like ways so the machine can simulate human behavior such as learning and problems over. Scientists and researchers have experimented various approaches toe accomplish human like intelligence over the bus 60 years. But the most important and most famously I approaches are the following to logic. Andi Rule based AI, also known as symbolic reasoning, also known as good old fashioned A. And the second time is machine learning, which is, of course, the most famous I approach today. 2. Lecture 2: So let's start with logic and role based AI in logic and rule based AI, the computer program or a machine is given a set of rules or logic similar to nested. If else statements and the computer program would follow them to produce some sort of intelligence, the role could be also an AL grant. This type of AI was also called good old fashioned AI, and it was the dominant paradigm in the AI community from post for era until late 19 eighties, such computer programs were called rule engines or expert systems because it has a human experience translated into rules or algorithms. A simple example for that is the following algorithm for optimal Blais for the tick tack toe game. If someone has a threat that is, for example, two in a row. Take the remaining square. Otherwise, if a move forks to create to threats at once, may that otherwise, I think the center square if it is free. Otherwise, if your opponent has blamed in a corner, think the opposite corner otherwise taken empty quarter. If no one exists. Otherwise, take any empty square you can nearly could. The above example, with some listed if else statements and it will produce a tick tack toe game engine with a simulated intelligence. That was the good old fashioned EI. Researchers thought that this approach was the only way to produce. Generally, I generally I such as the intelligence of pro boats we saw in their iRobot movie and similar stories. They thought that if they could translate all human experiences into rules and logic statements that would make such human like intelligence, however, this approach was limited and they never reaching a riel intelligent system that way. It was not a failure off the approach. It was an incorrect utilization for the approach. The role based AI was very successful for certain applications, and it is being used until today. But it has a limited usage and we should not think off it as generally I or as a solution for complex problems or pattern recognition problems off this approach is that it is as smart as the rules are. Also, it cannot predict or solve anything being the hard coded rules, and it cannot learn from historical data. So this approach was good to solve certain set of problems, but it was not suitable for solving complex problems that has no clear or two massive set of rules. That is why scientists and researchers have continued the research to find better solutions , the most popular and the most important form off that was machine learned. 3. Lecture 3: machine learning is the next advance in AI over its history. Scientists have concluded that a machine could mimic human learning Behaviour in this approach machine can learn from historical data and use that learning toe make informant decisions on better in combination machine learning is the dominant approach for AI today it will. It is where a computer program finds batters in data and create rules off its own. So it's basically learning from data on improving its rules over time. Unlike the role based AI, where rules were hard coded by humans an easy example. Often a machine learning algorithm is on on demand. Music Streaming service for the service to make a decision about which new songs or artists to recommend to our listeners. Machine learning algorithm associate. The listeners reference with other listeners who have similar musical taste. Machine learning fuels all sorts off automated tasks and spans across multiple industries from data security firms hunting down male where toe finance professional looking out for favorable traits. They are designed to work like virtual personal assistants, and they were quite well at its most basic machine learning uses programmed algorithms toe receive on analyze import data to predict output values within an acceptable range. As new data is filled, toe these algorithms the learn and optimize their operations to improve performance, developing what so called intelligence over time there are four types of machine learning algorithms supervised, semi supervised, unsupervised and reinforcement learning machine. Learning, as we can see, can be done using many others in the following birth. We explain different algorithms and algorithm types that are commonly used in machine learning. This part is for your reference so that you can get an idea about what machine learning algorithms are used. But it's not important that you understand that right now. Just go over it on By the end of this course, it will make perfect sense as we will be. Could be really life examples with some off the algorithms explained here. So don't panic if you don't fully understand the following Bart. This is perfectly normal. At the beginning,