What is artificial Intelligence ?
Artificial Intelligence (AI) is the simulation of human intelligence by machines.
Examples:
1) Learning
2)Understanding
3)Decision making
4) knowledge
5) pattern recognition
Things that are easy for computers to do but tough for humans?
1) Solving Mathematics Problems like addition, subtraction, multiplication and division.
2) Data Entry is easier for computer than human.
3) Sorting item based on a particular attribute.
Things that are easy for humans to do but are tough for computers ?
1) Voice recognition: Sarcasm
Example:
Sir asked a student :
Did you enjoy your group project ?
Student replied: yes sir!
Sir : Sir felt that he was being sarcastic with his answer.
In the case of the computer, would be unable to recognize whether the student is being sarcastic with his answer.
2) Image recognition: Sometimes computers find difficult to recognize a object in the image.
Example : In one of the movies , A guy created a software the can recognize different types of food dishes. but the software was able to recognize only a hotdog.
3) Facial recognition: recognizing someone's face .sometimes computers are unable to recognize face due to some changes.
Example : In apple Iphone 10 , 12, 13 models have special feature were you can unlock the phone by just showing your face. But suppose a face has a beard ,glasses or any changes on it the software is unable to scan the face and the phone does not unlock.
HISTORY OF ARTIFICIAL INTELLIGENCE
TURING TEST
Turing test was established by Alan Turing during 1950s.
This a test of machine's ability to exhibit intelligent behavior with competition to a human. Per question there will be 2 responses (1 computer, 1 human).
If the evaluator guesses the answer correct human wins. If the evaluator guesses the wrong machines wins.
ACTIVITY #1
Q1) Search for examples where we can apply machine learning, and some examples for deep learning.
Machine Learning
1) Speech Recognition: Machine Learning has the ability to transform speech into text. Software applications can convert live voice and recorded speech into text.
Examples:
1) Voice search
2) Voice dialing
3) Voice texting
Real World examples :
Alexa and Siri are some of the popular speech recognition examples. They assist in finding information, asked over voice (Hey Siri! Whether forecast update pls!). For answering such questions the virtual assistant looks out information and sends commands to the apps or sites to collect the following information.
2) Recommendation Engines: A recommendation engine is a data filtering tool using machine learning to recommend the most relevant items to a particular user as per the interest.
Real world example:
Netflix viewing suggestions. If you check homepage of your Netflix you can find series or movies recommend that similar to your interest. Netflix uses machine learning to curate its enormous collection of TV shows and movies. Netflix taps the streaming history and habits of its millions of users to predict what individual viewers will likely enjoy
Deep Learning
1) Language Recognition: Deep learning machines are beginning to differentiate dialects of a language. A machine decides that someone is speaking English and then engages an AI that is learning to tell the differences between dialects. Once the dialect is determined, another AI will step in that specializes in that particular dialect. All of this happens without involvement from a human.
2) Image colorization : In past, Humans used to add color to black and white images and videos manually. Which was a time -consuming process . Today, Deep Learning algorithms are being used to identify the context and objects to convert black and white images and videos into color.
ACTIVITY # 2
Q1) What is depth-First search?
Depth-first search is an algorithm for searching and traversing for tree or graph data structures .
Q2) Find one advantage and one disadvantage of depth-first search algorithms.
Advantage:
DFS(Depth first search ) requires less time and memory space to find the solution. DFS assures that the solution will be found if it exists infinite time.
Disadvantage:
Not Guaranteed that it will give you a solution. May not find optimal solution to the problem.
ACTIVITY # 3
Machine learning means to make a machine learn to solve problems by providing them with examples.
Like in the above example we added some image samples in class 1, class 2, and class 3 in teachable machines. With the Help of the Image samples, the teachable machine can identify the object accordingly.
The object added to the image was a book by Roald Dahl. The second object added to class 2 was the Eiffel tower and the third object added was a Nasa rocket.
After adding the image samples and the model is trained to scan and to identify the object.
when we 1st placed the book in front of camera the teachable machine perfectly identified the book. Even after placing the Eiffel tower and Nasa rocket the teachable machine perfectly identified the object.
when placing the two objects (Eiffel tower and Nasa rocket) together the machine was getting confused .
Few applications :
1) Handwriting Recognition: Handwriting Recognition is the ability of the computer to understand and to interpret intelligible handwritten input from sources like paper, images, photograph.
2) Speech Recognition: Speech Recognition is the ability of the machine to identify the words spoken aloud and convert them into text file.
3) Image segmentation: image segmentation is process of portioning or partitioning a digital image into multiple segments . The objective image segmentation is to simply the representation of image into something meaningful.
4) Recommender Systems : Recommender System is a information filtering system that seeks to predict the rating or preference a user would give to an item or object .
ACTIVITY # 4
Commentaires