Last updated 2/2017MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 800.09 MB | Duration: 7h 1m

Apply your existing Python skills to the highly lucrative fields of machine learning and deep learning.

What you'll 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

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 ees, robotics, self-driving cars, and more. It is transfog the way businesses operate. Being able to understand the trends and patterns in complex data is critical to success. In a challeg marketplace, it is one of the key strats 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 sennt 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, Sennt 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 JoshiPython Machine Learning Blueprints and Python Machine Learning Projects by Alexander T. CombsDeep Learning with TensorFlow by Dan Van BoxelGetting Started with TensorFlow by Giancarlo ZacconePython Machine Learning by Sebastian RaschkaBuilding 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 eeer 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 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 sars 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 spens. He has a PhD from Carn 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 learniobotics, 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.

Overview

Section 1: Getting Started with Python Machine Learning

Lecture 1 Course Introduction

Lecture 2 An Introduction to Machine Learning

Section 2: The Realm of Supervised Learning

Lecture 3 Preprocessing data using different techniques

Lecture 4 Label encoding

Lecture 5 Building a linear regressor

Lecture 6 Computing regression accuracy and achieving model persistence

Lecture 7 Building a ridge regressor

Lecture 8 Building a polynomial regressor

Lecture 9 Estimating housing prices

Lecture 10 Computing the relative importance of features

Lecture 11 Estimating bicycle demand distribution

Section 3: Constructing a Classifier

Lecture 12 Building a logistic regression classifier

Lecture 13 Building a Naive Bayes classifier

Lecture 14 Splitting the dataset for training and testing

Lecture 15 Evaluating the accuracy using cross-validation

Lecture 16 Visualizing the confusion matrix

Lecture 17 Extracting the performance report

Lecture 18 Evaluating cars based on their characteristics

Lecture 19 Extracting validation curves

Lecture 20 Extracting learning curves

Lecture 21 Estimating the income bracket

Section 4: Predictive Modeling

Lecture 22 Building a linear classifier using Support Vector Machine (SVMs)

Lecture 23 Building a nonlinear classifier using SVMs

Lecture 24 Tackling class imbalance

Lecture 25 Extracting confidence measurements

Lecture 26 Finding optimal hyperparameters

Lecture 27 Building an event predictor

Lecture 28 Estimating traffic

Section 5: Clustering with Unsupervised Learning

Lecture 29 Clustering data using the k-means algorithm

Lecture 30 Compressing an image using vector quantization

Lecture 31 Building a Mean Shift clustering model

Lecture 32 Grouping data using agglomerative clustering

Lecture 33 Evaluating the performance of clustering algorithms

Lecture 34 Automatically estimating the number of clusters using DBSCAN algorithm

Lecture 35 Finding patterns in stock market data

Lecture 36 Building a customer sntation model

Section 6: Building Recommendation Ees

Lecture 37 Building function compositions for data processing

Lecture 38 Building machine learning pipelines

Lecture 39 Finding the nearest neighbors

Lecture 40 Constructing a k-nearest neighbors classifier and regressor

Lecture 41 Computing the Euclidean distance score

Lecture 42 Computing the Pearson correlation score

Lecture 43 Finding similar users in the dataset

Lecture 44 Generating movie recommendations

Lecture 45 Building a simple classifier

Section 7: Analyzing Text Data

Lecture 46 Preprocessing data using tokenization

Lecture 47 Stemming text data

Lecture 48 Converting text to its base form using lemmatization

Lecture 49 Dividing text using chunking

Lecture 50 Building a bag-of-words model

Lecture 51 Building a text classifier

Lecture 52 Identifying the gender

Lecture 53 Analyzing the sennt of a sentence

Lecture 54 Identifying patterns in text using topic modeling

Section 8: Speech Recognition

Lecture 55 Reading and plotting audio data

Lecture 56 Generating audio signals with custom parameters

Lecture 57 Synthesizing music

Lecture 58 Extracting frequency domain features

Lecture 59 Building Hidden Markov Models

Lecture 60 Building a speech recognizer

Lecture 61 Transfog audio signals into the frequency domain

Section 9: Dissecting Series and Sequential Data

Lecture 62 Transfog data into the series format

Lecture 63 Slicing series data

Lecture 64 Operating on series data

Lecture 65 Extracting statistics from series data

Lecture 66 Building Hidden Markov Models for sequential data

Lecture 67 Building Conditional Random Fields for sequential text data

Lecture 68 Analyzing stock market data using Hidden Markov Models

Section 10: Image Content Analysis

Lecture 69 Operating on images using OpenCV-Python

Lecture 70 Detecting edges

Lecture 71 Histogram equalization

Lecture 72 Detecting corners and SIFT feature points

Lecture 73 Building a Star feature detector

Lecture 74 Creating features using visual codebook and vector quantization

Lecture 75 Training an image classifier using Extremely Random Forests

Lecture 76 Building an object recognizer

Section 11: Biometric Face Recognition

Lecture 77 Capturing and processing video from a webcam

Lecture 78 Building a face detector using Haar cascades

Lecture 79 Building eye and nose detectors

Lecture 80 Perfog Principal Components Analysis

Lecture 81 Perfog Kernel Principal Components Analysis

Lecture 82 Perfog blind source separation

Lecture 83 Building a face recognizer using Local Binary Patterns Histogram

Section 12: Visualizing Data

Lecture 84 Plotting 3D scatter plots

Lecture 85 Plotting and animating bubble plots

Lecture 86 Drawing pie charts

Lecture 87 Plotting date-formatted series data

Lecture 88 Plotting histograms

Lecture 89 Visualizing heat maps

Lecture 90 Animating dynamic signals

Section 13: Building Your First App using Machine Learning

Lecture 91 Build an app to find underpriced apartments

Lecture 92 Your Coding Challenge

Section 14: Forecasting the Stock Market with Machine Learning

Lecture 93 What does research tell us about the stock market?

Lecture 94 Developing a trading strategy

Lecture 95 Building a model and evaluating its performance

Lecture 96 Modeling with dynamic warping

Section 15: Building a Chatbot

Lecture 97 The design of chatbots

Lecture 98 Building a chatbot

Lecture 99 Your Coding Challenge

Section 16: Deep Learning with TensorFlow

Lecture 100 An introduction to deep learning and TensorFlow

Lecture 101 Installing TensorFlow

Lecture 102 Simple computations

Lecture 103 Logistic regression model building

Lecture 104 Logistic regression training

Section 17: Deep Neural Networks

Lecture 105 Basic neural nets

Lecture 106 Single hidden layer model

Lecture 107 Single hidden layer explained

Lecture 108 Multiple hidden layer model

Lecture 109 Multiple hidden layer results

Section 18: Convulation Neural Networks

Lecture 110 Convolutional layer motivation

Lecture 111 Convolutional layer application

Lecture 112 Pooling layer motivation

Lecture 113 Pooling layer application

Lecture 114 Deep CNN

Lecture 115 Deeper CNN

Lecture 116 Wrapping up deep CNN

Section 19: Recurrent Neural Network

Lecture 117 Introducing Recurrent Neural Networks

Lecture 118 skflow

Lecture 119 RNNs in skflow

Section 20: Wrapping Up

Lecture 120 Research evaluation

Lecture 121 The future of TensorFlow

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.

HomePage: