Machine Learning Course: Data Science and Deep Learning

Udemy

Category: Data Science Tags: Beginner, Online Course

About this course

This is a complete machine learning course with data science and deep learning with Python. You will get to know the techniques used by real data scientists and machine learning professionals in the tech industry, which will prepare you for a move into this hot career path. This course is a comprehensive machine learning tutorial that includes over 100 lectures spanning 14 hours of video, and most topics include hands-on Python code examples that you can use for reference and practice. So, let’s get over the terminologies first…

What is Machine Learning & Deep Learning?

In machine learning, data mostly passes through algorithms that perform linear transformations to produce output. Deep learning is a subset of machine learning in which data goes through multiple numbers of non-linear transformations to obtain an output. It refers to many steps in this case. The output of one step is the input for another step, and this is done continuously to get a final output. All of these steps are not linear. An example of a non-linear transformation is a matrix transformation.

Deep learning is sometimes called deep neural networks(DNN) because it makes use of multi-layered artificial neural networks to implement deep learning. Deep learning algorithms require very powerful machines and are very useful in detecting patterns from input data.

What is Data Science?

Data science continues to evolve as one of the most challenging and in-demand career paths for skilled practitioners. Today, successful data practitioners understand that they must advance past the traditional skills of analyzing large amounts of data, data mining, data processing, and programming skills.

In order to uncover useful intelligence for their organizations, data scientists must master the full spectrum of the data science life cycle and possess a level of flexibility and understanding to maximize returns at each phase of the process.

About the course instructor

The Machine Learning course was created by Sundog Education by Frank Kane who spent his 9 years at Amazon and IMDb for developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time.

What you will learn from this Machine Learning course

• Build artificial neural networks with the Tensor flow and Keras.
• Classification of images, data, and sentiments using deep learning.
• Make predictions using linear regression, polynomial regression, and multivariate regression.
• Data Visualization with MatPlotLib and Seaborn.
• Implementation of machine learning at a massive scale with Apache Spark’s MLLib.
• Understanding reinforcement learning – and how to build a Pac-Man bot.
• Classify data using K-Means clustering, Support Vector Machines (SVM), KNN, Decision Trees, Naive Bayes, and PCA.
• Use train/test and K-Fold cross-validation to choose and tune your models.
• Build a movie recommender system using item-based and user-based collaborative filtering.
• Clean your input data to remove outliers.
• Design and evaluate A/B tests using T-Tests and P-Values.

How easy it is?

Every concept is introduced in plain English, avoiding confusing mathematical notation and jargon. It’s then demonstrated using Python code you can experiment with and build upon, along with notes you can keep for future reference. The total focus is on practical understanding and application of them. In the end, you’ll be given a final project to apply what you’ve learned!

Syllabus

This machine learning course will cover, AI, and data mining techniques which include the following:

1. Machine learning course introduction

• Introduction to the course.
• Learn how to install Python and Anaconda on your system.

2. Statistics and Probability refresher, and Python practice

• Types of Data
• Using mean, median, and mode in python also Probability Density Function; Probability Mass Function, Common Data Distributions, and exercises on Conditional Probability

3. Predictive models

• Linear, polynomial, and multiple regressions.

4. Machine Learning with Python

• It includes Ayesian Methods: Concept K-Means Clustering, Clustering people based on income and age, Measuring Entropy, Support Vector Machines (SVM).
• Using SVM to cluster people using scikit-learn.

5. Recommender Systems

• User-based and item based Collaborative Filtering
• Exercises on  Improvement of the recommender’s results

6. More Data Mining and Machine Learning Techniques

• Concepts of K-Nearest-Neighbors and Dimensionality Reduction; Principal Component Analysis, Example with the Iris data set, Data Warehousing Overview: ETL and ELT Data Warehousing Overview: ETL and ELT
• Reinforcement Learning & Q-Learning concepts and measuring classifiers (Precision, Recall, F1, ROC, AUC)

7. Dealing with Real-World Data

• Bias/Variance Tradeoff,  K-Fold Cross-Validation to avoid overfitting and Data cleaning and normalization, cleaning web log data, and normalizing numerical data and activities on detecting outliers.
• Imputation Techniques for Missing Data, Handling Unbalanced Data: Oversampling, Undersampling, and SMOTE.
• Hands-on with Binning, Transforming, Encoding, Scaling, and Shuffling.

8. Apache Spark: Machine Learning on Big Data

• Introduction of Spark, Spark, and the Resilient Distributed Dataset (RDD).
• Introducing MLLib and Decision Trees in Spark and activities of clustering in Spark and Searching Wikipedia with Spark.

9. Experimental Design / ML in the Real World

• Deploying Models to Real-Time Systems, A/B Testing Concepts, T-Tests, and P-Values.
• Activities for Hands-on With T-Tests, Determining How Long to Run an Experiment, and A/B Test Gotchas.
• Deep Learning and Neural Networks.

10. Deep Learning and Neural Network

• Introduction to Tensorflow, Keras, Convolutional Neural Networks (CNN’s).
• Recurrent Neural Networks (RNN’s) and activities Using an RNN for sentiment analysis and Transfer Learning.
• Tuning Neural Networks: Learning Rate and Batch Size Hyperparameters.
• Deep Learning Regularization with Dropout and Early Stopping.

Prerequisites for the Machine Learning course

• You should have a desktop computer (Windows, Mac, or Linux) capable of running Anaconda 3 or newer. The course will walk you through installing the necessary free software.
• Need some previous coding or scripting experience.
• At least high school level math skills will be required.

Note: Your review matters

If you have already done this course, kindly drop your review in our reviews section. It would help others to get useful information and better insight into the course offered.

FAQ

• About our policies and review criteria.
• How can you choose and compare online courses?
• How to add Courses to your Wishlist?
• You can suggest courses to add to our website.