Listen free for 30 days

Listen with a free trial

One credit a month, good for any title to download and keep.
Unlimited listening to the Plus Catalogue - thousands of select Audible Originals, podcasts and audiobooks.
Exclusive member-only deals.
No commitment - cancel anytime.
Buy Now for £6.59

Buy Now for £6.59

Pay using card ending in
By completing your purchase, you agree to Audible's Conditions of Use and authorise Audible to charge your designated card or any other card on file. Please see our Privacy Notice, Cookies Notice and Interest-based Ads Notice.

Summary

Deep learning has been a great part of various scientific fields and since this is my third book regarding this topic, you already know the great significance of deep learning in comparison to traditional methods. At this point, you are also familiar with types of neural networks and their wide range of applications including image and speech recognition, natural language processing, video game development, and others. This book is all about convolutional neural networks and how to use these neural networks in various tasks of automatic image and speech recognition in Python.

You will also get a better insight into the architecture of convolutional layers as we are going deeper into this subject. Deep learning is pretty complex subject, but since you already have a fundamental knowledge of this topic, getting to know convolutional neural networks better is the next logical step.

What you will learn in Convolutional Neural Networks in Python:

  • Architecture of convolutional neural networks
  • Solving computer vision tasks using convolutional neural networks
  • Python and computer vision
  • Automatic image and speech recognition
  • Theano and TensorFlow image recognition
  • How to use MNIST vision dataset
  • What are commonly used convolutional filters

Get this book today and learn more about convolutional neural networks in Python!

©2017 Anthony Williams (P)2017 Anthony Williams

What listeners say about Convolutional Neural Networks in Python

Average customer ratings
Overall
  • 5 out of 5 stars
  • 5 Stars
    51
  • 4 Stars
    3
  • 3 Stars
    1
  • 2 Stars
    0
  • 1 Stars
    0
Performance
  • 5 out of 5 stars
  • 5 Stars
    51
  • 4 Stars
    3
  • 3 Stars
    1
  • 2 Stars
    0
  • 1 Stars
    0
Story
  • 5 out of 5 stars
  • 5 Stars
    51
  • 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

A pedagogical masterpiece

Amazing course , but keep in mind the prerequisites are necessary. Learned a lot from this course , just like all other Anthony's courses. Specially the way how we can write a CNN is a class based format. The most important part about CNN is understanding the convolution operation and fitting in the shapes together , for feed forward and for that proper understanding of feature maps is important and the instructor nails just that. Great course , I wish there was a CNN - part 2 with it .

22 people found this helpful

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

For AI/ML professionals

This has been the most exiting course within the Deep Learning specialization by deep learning.ai.

It provides all the basic theoretical and practical knowledge to get you started right away with CNNs and its applications in computer vision, including state-of-the-arts algorithms for image recognition, face detection and neural style transfer. With the help of the well-designed and challenging programming assignments you can practice and reinforce what you have just learned by doing it yourself, while becoming familiar with popular NN frameworks such as TensorFlow and Keras.

Excellent course in term of both theoretical and practical knowledge. I strongly recommend it for learners in the field.

21 people found this helpful

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

Python neural network guide

This is a very important course of deep learning and it has been nicely taught with all in depth details and how each part of the code is performing what. Looking forward to learn more of other courses.

21 people found this helpful

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

Nice short intro to neural networks

The course is great for those who are practically-minded and want to understand convolution and convolutional neural networks by way of example. However, this course will be quite difficult to follow if you have no deep learning experience.

20 people found this helpful

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

For All Tech Professional

Fantastic course! All the Anthony's courses are done very well, they give complete preparation but they are very challenging; their sequence forms a pleasant and complete course path; congratulations to the author.

19 people found this helpful

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

Machine Learning with Neural Network.

The patterns that are recognized by various deep neural networks are in the numerical form contained in bias vectors. Into these bias vectors, all data from the real world like sound, text, time series and images at some point during deep learning will be translated. Neural networks are designed in order to help us classify and cluster a large collection of data. In other words, think of neural networks as classification and clustering layer that is placed on top of data that will be managed and stored. Neural networks are also designed in order to help us to group various data that is unlabeled according to certain similarities that exist within different data collections. Data example inputs are also similar on some occasions, and neural networks classify that data when there is a labeled data collection available for data training process. It also can be said that neural networks extract various data features which are fed to different algorithms for further classification and clustering. Think of neural networks as various components of the larger family of machine learning models and applications. Neural networks involve different algorithms designed for data regression, data classification and reinforcement deep learning.

18 people found this helpful

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

AI and Machine Learning concepts

Very thorough coverage of the meaning and definitions of convolution. He looks at the subject from a variety of angles and compares them all.

18 people found this helpful

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

Rare and Great Work!

Constructive Feedback: I wish Anthony could write more about Convolution, what exact filters are applied etc in a convolutional network. And more about the dimension changes between the convolution layers. I'm also confused about Fan in vs Fan out

17 people found this helpful

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

Neural networks, Python and Raspberry Pi

Overall this was a really good lecture series even though I would have liked a little more detail in some of the lectures. The author is responsive and helpful. I would recommend this course.

16 people found this helpful

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

Nice book for Tensorflow

It is a carefully designed course, while the instructor is very organized in starting with basic convolutions and extending to neural nets.

15 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 Matthew Nelson
  • Matthew Nelson
  • 20-02-20

Intellectual and Resourceful

I like this course a lot. It is not slow, and get to the meat of what you need to know. The projects has very clear codes. And as all his courses there is a certain amount of mathematical treatment to the topic which promotes a proper understanding of the algorithm. I'm still struggling with learning the immense Deepnet libraries, but this has been a huge help. Thanks for making this knowledge far more accessible than it was.
Do note that to truly get the idea of convolution, you should read up a little bit about signal processing treatment of the topic.

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 Clara Pappas
  • Clara Pappas
  • 20-02-20

Good Pain

Overall satisfied with the course. It talks a lot more about convolution than I expected since I took deep learning courses in the past and they always explain it briefly. Now we get the full picture thanks to this course. It has a good pace and it goes in depth.

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 anna
  • anna
  • 20-02-20

To join AI crew.

Very good audible for those that really want to get the right focus on fundamentals. It is a great course for clearly highlighting the importance of understanding the mathematics and the structure of the image processing.
I’ve found this audiobook to be extremely helpful, and i feel it exceeds most courses because it has the focus on the frameworks required to make the information useful over and over again in areas related to my own interests.

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 Marshall  Shepard
  • Marshall Shepard
  • 26-03-21

Mix of mathematical concepts and practical example

This book is focused on convolutional layers that are used in different fields including computer vision, audio recognition, various image effects and other. As soon as we get familiar with deep learning and neural networks in general, we are going to see most typical applications of a convolutional neural network, and there will be more word of it in Chapter 1 Introduction to Convolutional Neural.

Deep learning methods lie under an assumption that hidden level representations in gathered data are in fact generated by the relationship and interaction of various features of these layers. Also further there is an assumption that these certain layers and their features, in fact, correspond to multiple levels of composition and certain levels of abstraction. It should be noted that a different number of layers as well layer sizes may provide a wide range of different structures and abstractions.
Deep learning techniques actually exploit a particular idea of the hierarchical concept of various factors and features in circumstances where layers form higher levels are generated from those from lower levels. In other words, higher level features are learned from lower layer features.
Deep learning models are commonly generated with a layerby-layer algorithm where deep learning methods help in order to disentangle various abstractions and compositions in order to pick out those useful and relevant features that will eventually improve overall performance.

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 Jacqueline
  • Jacqueline
  • 20-02-20

Neural Nets for Everyone

I'm taking all Anthony's courses. All of them so far are clear, detailed and focused. In particular this is the first course talking about convolutional neural networks that I see the real theory behind, instead of just setting up and running an algorithm. I highly recommend all of these courses!

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 Ronald
  • Ronald
  • 21-02-20

The best 2 hours about this topic

I know I did not meet all the prerequisites outlined by the instructor, but I was still able to follow along quite well - and especially liked the additional material in the appendix. While I've sat through all the lectures once, I'm actually looking forward to running through them a 2nd time for more in depth practice.

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 Carole  Barco
  • Carole Barco
  • 21-02-20

Come for the theory, stay for the practical advice

Great course, and great teacher. My favorite thing about this course is its gradual explanation of each concept that flows into the next. Lectures are well introduced and quite interesting, complemented with well-written code.

18 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 Anna  Sheckler
  • Anna Sheckler
  • 21-02-20

Accessible yet thorough

This is a thanks note for you. Around 13 months ago, I was new in deep learning area totally. Know nothing about ANN,CNN,logistic regression or even python. Then I went your course and take nearly all of them. Because of your excellent courses for both theory and coding, I get chances to join a lot of projects in our school lab. Just several days ago, I got an offer as a deep learning engineer in Palo Alto and my annual salary is around $180k. At same time, I also published 3 papers in deep learning area. All of these happened because of you. This is the greatest course forever!

17 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  Regina Guy
  • Regina Guy
  • 21-02-20

One of the great side benefit of this book

This course really helped me take my understanding of deep learning to the next level. I feel like I understand what’s happening inside the neural network.

16 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  Mimi Robinson
  • Mimi Robinson
  • 22-02-20

Would Recommend! 5/5

Nicely prepared and well presented course. Long discussion on convolution within 2 hours which is glossed over in other sources. Code assignments gives good insights into concepts learned about convolution, CNNs, Theano, & Tensorflow. Looking forward to more courses!

15 people found this helpful