Python: Step into the World of Machine Learning
2.7 (8 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
190 students enrolled
Wishlisted Wishlist

Please confirm that you want to add Python: Step into the World of Machine Learning to your Wishlist.

Add to Wishlist

Python: Step into the World of Machine Learning

Apply your existing Python skills to the highly lucrative fields of machine learning and deep learning.
2.7 (8 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
190 students enrolled
Created by Packt Publishing
Last updated 2/2017
English
Current price: $10 Original price: $200 Discount: 95% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 6 hours on-demand video
  • 19 Articles
  • 1 Supplemental Resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • Explore and use Python’s impressive machine learning ecosystem
  • Understand the different types of machine learning
  • Learn predictive modeling and apply it to real-world problems
  • Work with image data and build systems for image recognition and biometric face recognition
  • Build your own applications using machine learning
  • Build simple TensorFlow graphs for everyday computations
View Curriculum
Requirements
  • Basic knowledge of Python syntax
  • Python 3.x installed on your machine
Description

Are you looking at improving and extending the capabilities of your machine learning systems? Or looking for a career in the field of machine learning? If yes, then this course is for you.

ML is becoming increasingly pervasive in the modern data-driven world. It is used extensively across many fields, such as search engines, robotics, self-driving cars, and more. It is transforming the way businesses operate. Being able to understand the trends and patterns in complex data is critical to success. In a challenging marketplace, it is one of the key strategies for unlocking growth. 

The aim of the course is to teach you how to process various types of data, including how and when to apply different machine learning techniques

We cover a wide range of powerful machine learning algorithms, alongside expert guidance and tips on everything from sentiment analysis to neural networks. You’ll soon be able to answer some of the most important questions that you and your organization face.

Why should I choose this course?

This course is a blend of text, videos, code examples, quizzes, and coding challenges which together makes your learning journey all the more exciting and truly rewarding. It includes sections that form a sequential flow of concepts covering a focused learning path presented in a modular manner. This helps you learn a range of topics at your own speed and also move towards your goal of learning machine learning.

Testimonials:

The source content have been received well by the audience. Here are a couple of reviews:

"The author has communicated with clarity for the individual who would like to learn the practical aspects of implementing learning algorithms of today and for the future. Excellent work, up-to-date and very relevant for the applications of the day!"

- Anonymous Customer.

"Very helpful and objective."

- Fabiano Souza

"I would definitely recommend this to people who want to get started with machine learning in Python."

- Spoorthi V.


What is included?

Let’s dig into what this course covers. Since you already know the basics of Python, you are no stranger to the fact that it is an immensely powerful language. With the basics in place, this course takes a hands-on approach and demonstrates how you can perform various machine learning tasks on real-world data

The course starts by talking about various realms in machine learning followed by practical examples. It then moves on to discuss the more complex algorithms, such as Support Vector Machines, Extremely Random Forests, Hidden Markov Models, Sentiment Analysis, and Conditional Random Fields. You will learn how to make informed decisions about the types of algorithm that you need to use and how to implement these algorithms to get the best possible results.

After you are comfortable with machine learning, this course teaches you how to build real-world machine learning applications step by step. Further, we’ll explore deep learning with TensorFlow, which is currently the hottest topic in data science. With the efficiency and simplicity of TensorFlow, you will be able to process your data and gain insights that will change the way you look at data. You will also learn how to train your machine to build new models that help make sense of deeper layers within your data.

By the end of this course, you should be able to solve real-world data analysis challenges using innovative and cutting-edge machine learning techniques. 

We have combined the best of the following Packt products:

  • Python Machine Learning Cookbook and Python Machine Learning Solutions by Prateek Joshi
  • Python Machine Learning Blueprints and Python Machine Learning Projects by Alexander T. Combs
  • Deep Learning with TensorFlow by Dan Van Boxel
  • Getting Started with TensorFlow by Giancarlo Zaccone
  • Python Machine Learning by Sebastian Raschka
  • Building Machine Learning Systems with Python - Second Edition by Luis Pedro Coelho and Willi Richert


Meet your expert instructors:

Prateek Joshi is an artificial intelligence researcher, published author of five books, and TEDx speaker. He is the founder of Pluto AI, a venture-funded Silicon Valley startup building an analytics platform for smart water management powered by deep learning. He has been an invited speaker at technology and entrepreneurship conferences including TEDx, AT&T Foundry, Silicon Valley Deep Learning, and Open Silicon Valley. His tech blog has received more than 1.2 million page views from 200 over countries and has over 6,600+ followers. 

Alexander T. Combs is an experienced data scientist, strategist, and developer with a background in financial data extraction, natural language processing and generation, and quantitative and statistical modeling.

Dan Van Boxel is a data scientist and machine learning engineer with over 10 years of experience. He is most well-known for "Dan Does Data", a YouTube livestream demonstrating the power and pitfalls of neural networks. He has developed and applied novel statistical models of machine learning to topics such as accounting for truck traffic on highways, travel time outlier detection, and other areas. 

Giancarlo Zaccone, a physicist, has been involved in scientific computing projects among firms and research institutions. He currently works in an IT company that designs software systems with high technological content. He currently works in an IT company that designs software systems with high technological content.

Sebastian Raschka has been ranked as the number one most influential data scientist on GitHub by Analytics Vidhya. He has many years of experience with coding in Python and conducted several seminars on the practical applications of data science and machine learning. He has also actively contributed to open source projects and methods that he implemented, which are now successfully used in machine learning competitions, such as Kaggle.

Luis Pedro Coelho is a computational biologist. He analyzes DNA from microbial communities to characterize their behavior. He has also worked extensively in bioimage informatics—the application of machine learning techniques for the analysis of images of biological specimens. He has a PhD from Carnegie Mellon University, one of the leading universities in the world in the area of machine learning. He is the author of several scientific publications.

Willi Richert has a PhD in machine learning/robotics, where he used reinforcement learning, hidden Markov models, and Bayesian networks to let heterogeneous robots learn by imitation. Currently, he works for Microsoft in the Core Relevance Team of Bing, where he is involved in a variety of ML areas such as active learning, statistical machine translation, and growing decision trees.

Who is the target audience?
  • This course is for Python programmers, developers, and data scientists looking to use machine learning algorithms and techniques to create real-world applications
  • Some familiarity with Python programming will certainly be helpful to play around with the code
  • If you want to become a machine learning practitioner, a better problem solver, or maybe even consider a career in machine learning research, then this course is for you.
Students Who Viewed This Course Also Viewed
Curriculum For This Course
121 Lectures
07:02:14
+
Getting Started with Python Machine Learning
2 Lectures 17:45

An Introduction to Machine Learning
13:48

Test Your Knowledge
2 questions
+
The Realm of Supervised Learning
9 Lectures 29:05

Label encoding
02:07

Building a linear regressor
03:23

Computing regression accuracy and achieving model persistence
03:30

Building a ridge regressor
02:32

Building a polynomial regressor
02:21

Estimating housing prices
03:29

Computing the relative importance of features
01:47


Test Your Knowledge
5 questions
+
Constructing a Classifier
10 Lectures 27:15
Building a logistic regression classifier
04:44

Building a Naive Bayes classifier
02:05

Splitting the dataset for training and testing
01:17

Evaluating the accuracy using cross-validation
03:55

Visualizing the confusion matrix
02:01

Extracting the performance report
00:26

Evaluating cars based on their characteristics
05:04

Extracting validation curves
02:41

Extracting learning curves
01:34

Estimating the income bracket
03:28

Test Your Knowledge
6 questions
+
Predictive Modeling
7 Lectures 18:01
Building a linear classifier using Support Vector Machine (SVMs)
04:13

Building a nonlinear classifier using SVMs
01:41

Tackling class imbalance
02:47

Extracting confidence measurements
02:30

Finding optimal hyperparameters
02:04

Building an event predictor
02:15

Estimating traffic
02:31

Test Your Knowledge
3 questions
+
Clustering with Unsupervised Learning
8 Lectures 23:13
Clustering data using the k-means algorithm
02:38

Compressing an image using vector quantization
03:35

Building a Mean Shift clustering model
02:33

Grouping data using agglomerative clustering
03:04

Evaluating the performance of clustering algorithms
02:55

Automatically estimating the number of clusters using DBSCAN algorithm
03:33

Finding patterns in stock market data
02:34

Building a customer segmentation model
02:21

Test Your Knowledge
5 questions
+
Building Recommendation Engines
9 Lectures 25:56
Building function compositions for data processing
03:24

Building machine learning pipelines
03:54

Finding the nearest neighbors
01:49

Constructing a k-nearest neighbors classifier and regressor
05:31

Computing the Euclidean distance score
02:04

Computing the Pearson correlation score
01:54

Finding similar users in the dataset
01:34

Generating movie recommendations
02:27


Test Your Knowledge
2 questions
+
Analyzing Text Data
9 Lectures 25:45
Preprocessing data using tokenization
02:59

Stemming text data
02:22

Converting text to its base form using lemmatization
02:10

Dividing text using chunking
02:02

Building a bag-of-words model
02:53

Building a text classifier
03:08

Identifying the gender
02:11

Analyzing the sentiment of a sentence
03:09

Identifying patterns in text using topic modeling
04:51

Test Your Knowledge
4 questions
+
Speech Recognition
7 Lectures 15:18
Reading and plotting audio data
02:27

Generating audio signals with custom parameters
01:29

Synthesizing music
02:06

Extracting frequency domain features
02:05

Building Hidden Markov Models
02:18

Building a speech recognizer
03:11

Transforming audio signals into the frequency domain
01:42

Test Your Knowledge
2 questions
+
Dissecting Time Series and Sequential Data
7 Lectures 18:04
Transforming data into the time series format
03:00

Slicing time series data
01:07

Operating on time series data
01:19

Extracting statistics from time series data
01:40

Building Hidden Markov Models for sequential data
04:07

Building Conditional Random Fields for sequential text data
04:26

Analyzing stock market data using Hidden Markov Models
02:25

Test Your Knowledge
2 questions
+
Image Content Analysis
8 Lectures 20:17

Detecting edges
02:45

Histogram equalization
02:28

Detecting corners and SIFT feature points
03:39

Building a Star feature detector
01:22

Creating features using visual codebook and vector quantization
02:51

Training an image classifier using Extremely Random Forests
02:23

Building an object recognizer
01:47

Test Your Knowledge
2 questions
10 More Sections
About the Instructor
Packt Publishing
3.9 Average rating
8,175 Reviews
58,686 Students
686 Courses
Tech Knowledge in Motion

Packt has been committed to developer learning since 2004. A lot has changed in software since then - but Packt has remained responsive to these changes, continuing to look forward at the trends and tools defining the way we work and live. And how to put them to work.

With an extensive library of content - more than 4000 books and video courses -Packt's mission is to help developers stay relevant in a rapidly changing world. From new web frameworks and programming languages, to cutting edge data analytics, and DevOps, Packt takes software professionals in every field to what's important to them now.

From skills that will help you to develop and future proof your career to immediate solutions to every day tech challenges, Packt is a go-to resource to make you a better, smarter developer.

Packt Udemy courses continue this tradition, bringing you comprehensive yet concise video courses straight from the experts.