• Machine Learning

  • A Beginners Guide to History, Development and Future Possibilities of Machine Learning
  • By: William Bahl
  • Narrated by: William Bahl
  • Length: 2 hrs and 5 mins
  • 4.9 out of 5 stars (52 ratings)

1 title per month from Audible’s entire catalog of best sellers, and new releases.
Access a growing selection of included Audible Originals, audiobooks and podcasts.
You will get an email reminder before your trial ends.
Your Premium Plus plan is $14.95 a month after 30 day trial. Cancel anytime.
Buy for $6.95

Buy for $6.95

Pay using card ending in
By confirming your purchase, you agree to Audible's Conditions of Use and Amazon's Privacy Notice. Taxes where applicable.

Publisher's Summary

This book is designed to be an introduction to machine learning algorithms for a complete beginner. It starts with an explanation of exactly what machine learning algorithms are and then walks you through the languages and frameworks used to create them. 

Studying machine learning is considered to be quite challenging due to the impression that special talent is required or some unachievable level of mathematics is needed in order to understand the various algorithms and techniques. The purpose of this book is to show you that anyone can learn to become a machine learner and put the theory into practice. 

This book provides you with all the information you need to understand machine learning at a beginner level. You will get an idea on the different subjects that are linked to machine learning and some facts about machine learning that make it an interesting subject to learn. Without further ado let’s get started.

PLEASE NOTE: When you purchase this title, the accompanying PDF will be available in your Audible Library along with the audio.

©2019 William Bahl (P)2019 William Bahl

What listeners say about Machine Learning

Average Customer Ratings
Overall
  • 5 out of 5 stars
  • 5 Stars
    49
  • 4 Stars
    3
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0
Performance
  • 5 out of 5 stars
  • 5 Stars
    49
  • 4 Stars
    3
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0
Story
  • 5 out of 5 stars
  • 5 Stars
    49
  • 4 Stars
    3
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0

Reviews - Please select the tabs below to change the source of reviews.

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Great but get the PDF

Neural networks are programming paradigms that are biologically inspired to enable a computer to learn from data that is observed.

Deep Learning is a set of techniques that you are going to use for Neural Networks.

Both Neural Networks and Deep Learning are going to give you the best solution to any problem that you may come up against when you are working with image, speech and natural language recognition and processing.

However, with deep learning, the computer is capable of making continuous adjustments in order to improve its performance every time it is used. But to really grasp the concept of deep learning, we need to take some time and look closely under the hood. Its use today can help us to see how deep learning is already changing our lives for the better.

24 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

This book is really a great audio book

This book is really a great audio book. This audio book discuss about Machine Learning. The content of this audio book is very vast. Tips use in this audio book is the best. If a man want to know about Machine Learning then he must be listen this audio book. Highly recommended for all.

24 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

This book has a very clear instructions.

Through this audio book, I learned what machine learning is, its principles of operation, features and advantages. It has a very clear instructions. There is also a description of Big Data explanation, familiarity with artificial intelligence. Really good for all beginners.

23 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

This is a very informative audio book

This is a very informative audio book. I am completely listening this audio book it's helpful for developing my skill. This audio book Machine Learning that guide all beginners to history, development and future possibilities of machine learning is very helpful for understanding. I am happy to get this audiobook. Thanks to the great author!

22 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

This book is for the worthy reveal.

This book is for the worthy reveal. The book will not bore you with the mathematical foundations of Machine Learning, and it will leave you with the desire to get you to explore more about this interesting field. Also it tackles about different algorithms that beginners must learn.

21 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Very Useful!

Very nice and gentle introduction into the field of Machine Learning. It will open up your mind and it will give you a desire to learn more about machines and the future developments of machine learning. A very useful book for all beginners.

20 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

I appreciate this book.

This is a very resource able book for Machine Learning. This book author very clear and well writes it's easy to understand. Simple examples will help me understand the complex math and probability statistics underlining Machine Learning. This book helps for developing my skill. I appreciate this book.

19 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Up there with Bahl's Courses

In machine learning, when you are considering what the idea of generalization is about, you are basically seeing that there are two components present and you will need to use both of them before you can get through all the data. The components that need to be present include the reliability assumption and revisiting the true error rate.

Any time that you can work with this, and you can meet the reliability assumption, you will be able to expect that the algorithm that you use in machine learning to get the results is pretty reliable for helping you know the distribution. But, there are also times when the assumption that you make here is not going to be very practical. This means that the standards that you picked out may have been unrealistic and that you went with the wrong algorithm to get all the work done.

In addition, the type of algorithm that you try to pick out for machine learning doesn’t guarantee that you come up with a hypothesis that is something you like. Unlike using the Bayes predictor, which is an algorithm we will talk about more, later on, these algorithms are not set up to find which type of error rate is the best for you either.

18 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Great book!

It conveys great beginning stages for inference combination.Unmistakably, the creator appreciates machine learning and instructing it to other people. I trust he has achieved this objective extremely delightful. It aggravated my longing to work with machine learning strategies.

18 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

It delivers good starting points

Clearly, the author enjoys machine learning and teaching it to others. I believe he has accomplished this goal very scrumptious. It inflamed my desire to work with machine learning techniques. A reinforcement learning notebook. It delivers good starting points for derivation convergence. I also found the technique executed in the notebook.

17 people found this helpful

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Leslie Hummer
  • Leslie Hummer
  • 06-21-20

Great book for data scientists

Machine learning can work really well when it comes to the field of data science as well as artificial intelligence. To start, data science is a pretty broad term that will include different concepts. One of these concepts is machine learning, but it can also include artificial intelligence, big data, and data mining to name a few. Data science is actually a newer field that is growing as people find more uses for computers and use them more often.

Statistics is really important when it comes to data science, and it can also be used often when it comes to machine learning. You would be able to work with classical statistics, even at the higher levels, so that the data set will stay consistent throughout. But the way that you use it will depend on what kinds of data you are using and how complex the information gets.

It is important to understand the difference between the categories of artificial intelligence and machine learning. There are some instances where they can be very similar, but there are some major differences, which is why they are considered two different things.

24 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Shane D.
  • Shane D.
  • 10-28-19

This is really an excellent audiobook

This is really an excellent audio-book about machine learning. If the terms are used, they should be defined upfront. If various specific methods are mentioned, it would be good to provide a comparison and overview of those. I really like this audio-book and would recommend any one who need such type of information.

24 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Suzainne Chua
  • Suzainne Chua
  • 10-28-19

Great book for beginners.

This is an extremely long audiobook, but I found it easy to listen and good content in each chapter. After listening the audiobook i feel like i have a strong understanding of everything and it's made it much easier to listen and Machine Learning. I personally recommend this book to all.

23 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Joanna Dy
  • Joanna Dy
  • 10-28-19

So much information in this audio-book!

So much information in this audio-book! The author details out the steps to set you on the path to success along with providing pearls of wisdom along the way! I've learn many ideas that I can use for the future. This book also educate me about the history of machine learning.

22 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Nicole  Dunigan
  • Nicole Dunigan
  • 06-22-20

Probably the best publicly available self ........

Probably the best publicly available self contained resource on the subject.

Analyzing the data will tell you what kind of algorithm to use to interpret it, but before you can actually use the algorithm, you’ll likely need to do some prep work on your data. Properly preparing your data helps to ensure that you get the results you’re looking for and that the algorithm functions the way you intend.

The number and types of features and attributes you want to consider will also have an impact on how much preparation work you need to do on your data. If there are a lot of missing features or outliers, cleaning up the data can help your models run more efficiently. You may also need to transform the data by compiling it or scaling so it’s easier for the program to process.

You may also find that you don’t want to use every piece of data that you have available to train your algorithm. Curating the dataset that the algorithm learns from can help to direct the types of situations it predicts well. You may choose to leave out entire portions of the data, or simply to have the program ignore certain features.

21 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Jamaica
  • Jamaica
  • 10-28-19

I am completely satisfied with this audio-book

This audio-book has Highly Effective with Machine Learning, I exceedingly suggest this audio-book, If you take this so you will be get all things. In general this audio-book are great. I like this Guide for Beginners To Expert audio-book. I am completely satisfied with this audio-book. Thanks to the one who wrote this book.

21 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Thea G.
  • Thea G.
  • 10-28-19

I am very satisfied with this audio book

I am very satisfied with this audio book. This is really an excellent audio book about machine learning. If the terms are used, they should be defined upfront. I really like this book and would recommend any one who need such type of information. I will be checking more great and so informative books from this author.

20 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Mary  Stirling
  • Mary Stirling
  • 06-23-20

Rich...

The idea of machine learning was pioneered far earlier than you might think, as early as the 1960s, in fact. Those early experiments with machine learning couldn’t accomplish very much and were largely focused on pattern recognition.

Machine learning algorithms have been used since the 90s, and they have improved the way we interact with the Internet and other technology significantly. What exactly is machine learning, though? What are we referring to when we talk about a machine capable of learning?

The reality, however, is that the concept of machine learning is even older than computers; it is, in fact, centuries older. That’s because the idea of building a machine capable of making computations on its own comes from mathematicians who lived long ago

19 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Maria Samson
  • Maria Samson
  • 10-28-19

The author has done an excellent job in this book

I am so much satisfied after listening to this book. In this book, I will get so many valuable information about artificial intelligence. I only wish it had more about unsupervised learning. The author has done an excellent job in this book. I highly recommend this book to anyone wishing to deepen their understanding of predictive analytics and machine learning.

19 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for  Andrew Miura
  • Andrew Miura
  • 06-25-20

It is what it markets

Being able to understand and trust your models is the core requirement of good data science. It can be easy to fall into the trap of believing machine learning algorithms are the answers to all of your data interpretation woes. While they can be immensely helpful, your ability to use the algorithms effectively is equally important to your success. The data you get from machine learning algorithms are useless if you don’t know how to frame it in a way you and others can use and understand. Always show the context of the problem and the steps you took to find the solution with your results. Even the most valuable data analysis can seem useless if it’s viewed out of context or in a vacuum. Putting your results in context lets you see the big picture, which can help to make further connections, and at the least makes sure you’re getting the most value out of your data. Being able to express your results in terms that even laypeople can understand is one good indication that you understand the problem, the model, and the data completely. Even if you won’t be presenting the data to anyone outside your industry, compiling it in a way that would be comprehensible to outsiders can be a good test of how well you know your own data. Your data is only as valuable as the results you’re able to draw from it. If you’re not getting results that you can use, you should ask yourself if you truly understand your data and your model. Double-check your model for accuracy to make sure the answers that it’s given you are ones that you can trust.

18 people found this helpful