Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Artificial Intelligence Projects with Python-HandsOn: 2-in-1
Rating: 3.6 out of 5(11 ratings)
185 students

Artificial Intelligence Projects with Python-HandsOn: 2-in-1

Hands-on projects that simplify your first steps into the world of artificial intelligence with Python
Created byPackt Publishing
Last updated 5/2018
English

What you'll learn

  • Classify text and images according to predefined categories and make use of neural networks, decision trees, random forests for classification
  • Use deep reinforcement learning to build an AI that plays arcade games
  • Employ the SpaCy and textacy libraries for natural language processing
  • Use popular libraries such as Keras and TensorFlow for reinforcement learning
  • Extend pre-trained deep learning models
  • Build a recommendation engine for finding new music

Course content

2 sections • 30 lectures • 3h 55m total length

  • The Course Overview2:25

    This video gives an overview of the entire course.

  • Classification Overview and Evaluation Techniques4:58
    In this video, we will see what classification is and also, we will see how well a system is performing in this task.
  • Decision Trees3:45

    In this video, we will see what a decision tree is, how it works, and what is it good for.

  • Prediction with Decision Trees and Student Performance Data6:32
    In this video, we will see how we can predict a student’s performance in a course. We can do so by looking at the student’s prior performance and some facts about their home life. A decision tree classifier can be used to learn how to predict performance based on these historical attributes.
  • Random Forests1:54

    In this video, we will see what a random forest is, how it works, and what is it good for.

  • Predicting Bird Species with Random Forests9:17

    In this video, we will see how we can predict the species of a bird based on various attributes.

  • The Problem of Text Classification5:32

    In this video, we will see how we can manipulate text in order to use a classification technique, such as random forests. One popular approach is the bag-of-words model.

  • Detecting YouTube Comment Spam with Bag of Words and Random Forests8:37
    In this video, we will see how we can identify spam comments on a website. We look at a YouTube spam dataset to practice with bag-of-words and random forests to solve this problem.
  • Word2Vec Models4:45

    Is there any other way to represent text, perhaps more accurately? Indeed, Word2Vec is a more sophisticated approach that can yield more accurate results and this video explains that.

  • Detecting Positive/Negative Sentiment in User Reviews8:11
    In this video, we will see how we can identify positive and negative product reviews and how to use word2vec and doc2vec models to find which documents are similar to each other.
  • Neural Networks4:10

    In this video, we will see what neural networks are, why are they named this way, and how do they work.

  • Identifying the Genre of a Song Using Audio Analysis and Neural Networks11:17

    In this video, how we can identify the genre of a song.

  • Revising the Spam Detector to Use Neural Networks8:35

    In this video, we will see how to use neural networks for text data.

  • Overview of Deep Learning and Convolutional Neural Networks5:58
    In this video, we will see what deep learning is, why is it a popular term today, how does it work, and what are popular techniques in deep learning.
  • Identifying Handwritten Mathematical Symbols with Convolutional Neural Networks14:35
    In this video, we will see how to use CNNs to classify images.
  • Revising the Bird Species Identifier to Use Images11:55
    In this video, we will see how to use more sophisticated CNNs to classify images.

Requirements

  • Basic working knowledge of Python programming is expected.

Description

Artificial Intelligence is one of the hottest fields in computer science right now and has taken the world by storm as a major field of research and development. Python has surfaced as a dominant language in AI/ML programming because of its simplicity and flexibility, as well as its great support for open source libraries such as Scikit-learn, Keras, spaCy, and TensorFlow. If you're a Python developer who wants to take first steps in the world of artificial intelligent solutions using easy-to-follow projects, then go for this learning path.

This comprehensive 2-in-1 course is designed to teach you the fundamentals of deep learning and use them to build intelligent systems. You will solve real-world problems such as face detection, handwriting recognition, and more. You will also get an exposure to hands-on projects that will help you explore the world of artificial intelligence with Python. You will get well-versed with AI concepts that gets you up and running with AI in no time.

This training program includes 2 complete courses, carefully chosen to give you the most comprehensive training possible.

The first course, Python Artificial Intelligence Projects for Beginners, covers Hands-on Python recipes that implement practical examples to help you build artificial intelligence applications with eight realistic projects. You will start with the first project which covers decision trees for classifying data using Scikit-learn libraries. You will then build a classifier using random forests. You will also learn about text processing techniques and practice with bag-of-words and word2vec models.

The second course, Advanced Artificial Intelligence Projects with Python, covers intelligent application projects with artificial intelligence using the Python programming language. The very first project introduces you to natural language processing including part-of-speech tagging and named entity extraction. The next project introduces genetic algorithms wherein DEAP library is used. In this project, a music data set is used in a genetic algorithm that generates a music playlist satisfying multiple criteria such as song similarity and playlist length. The last project introduces reinforcement learning and deep reinforcement learning wherein you will use OpenAI Gym platform and Q-learning algorithm to build a game-playing AI.

By the end of this Learning Path, you will be confident to build your own AI projects with Python, with a useful blend of ideas to sharpen your skills in artificial intelligence.

Meet Your Expert(s):

We have the best work of the following esteemed author(s) to ensure that your learning journey is smooth: 

● Joshua Eckroth is an Assistant Professor of Computer Science at Stetson University, where he teaches Big Data Mining and Analytics, artificial intelligence (AI), and Software Engineering. Dr. Eckroth joined the Math and Computer Science Department at Stetson University in Fall 2014. He earned his PhD from Ohio State University in the areas of AI and cognitive science, focusing on abductive reasoning and metareasoning. He is an active researcher with numerous refereed publications in the fields of artificial intelligence and computer science education. Dr. Eckroth also serves as Chief Architect at i2k Connect, LLC., whose mission is to revolutionize the ability of companies to find, filter, and analyze data in documents by extracting essential information from data clutter. In addition, Dr. Eckroth is co-editor of AITopics, the Internet's largest collection of information about the research, the people, and the applications of artificial intelligence.

Who this course is for:

  • This Learning Path is for Python developers who want to take their first step in the world of artificial intelligent solutions using easy-to-follow projects.

Report abuse