Deep Learning: Convolutional Neural Networks in Python

Computer Vision and Data Science and Machine Learning combined! In Theano and TensorFlow

Generative AI
4.7/5
$29.99
$199.99
85% OFF!
  • All levels
  • 121 Lectures
  • 20h 11m
  • English
  • Lifetime access, certificate of completion (shareable on LinkedIn, Facebook, and Twitter), Q&A forum, LaTeX notes, subtitles in English
Login or signup to
register for this course

Course Description

This is the 3rd part in my Data Science and Machine Learning series on Deep Learning in Python. At this point, you already know a lot about neural networks and deep learning, including not just the basics like backpropagation, but how to improve it using modern techniques like momentum and adaptive learning rates. You've already written deep neural networks in Theano and TensorFlow, and you know how to run code using the GPU.

This course is all about how to use deep learning for computer vision using convolutional neural networks. These are the state of the art when it comes to image classification and they beat vanilla deep networks at tasks like MNIST.

In this course we are going to up the ante and look at the StreetView House Number (SVHN) dataset - which uses larger color images at various angles - so things are going to get tougher both computationally and in terms of the difficulty of the classification task. But we will show that convolutional neural networks, or CNNs, are capable of handling the challenge!

Because convolution is such a central part of this type of neural network, we are going to go in-depth on this topic. It has more applications than you might imagine, such as modeling artificial organs like the pancreas and the heart. I'm going to show you how to build convolutional filters that can be applied to audio, like the echo effect, and I'm going to show you how to build filters for image effects, like the Gaussian blur and edge detection.

We will also do some biology and talk about how convolutional neural networks have been inspired by the animal visual cortex.

After describing the architecture of a convolutional neural network, we will jump straight into code, and I will show you how to extend the deep neural networks we built last time (in part 2) with just a few new functions to turn them into CNNs. We will then test their performance and show how convolutional neural networks written in both Theano and TensorFlow can outperform the accuracy of a plain neural network on the StreetView House Number dataset.

All the materials for this course are FREE. You can download and install Python, Numpy, Scipy, Theano, and TensorFlow with simple commands shown in previous courses.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.



Suggested Prerequisites:

  • calculus
  • linear algebra
  • probability
  • Python coding: if/else, loops, lists, dicts, sets
  • Numpy coding: matrix and vector operations, loading a CSV file
  • linear regression, logistic regression
  • neural networks and backpropagation
  • Can write a feedforward neural network in Theano and TensorFlow


Tips for success:

  • Use the video speed changer! Personally, I like to watch at 2x.
  • Take handwritten notes. This will drastically increase your ability to retain the information.
  • Write down the equations. If you don't, I guarantee it will just look like gibberish.
  • Ask lots of questions on the discussion board. The more the better!
  • Don't get discouraged if you can't solve every exercise right away. Sometimes it'll take hours, days, or maybe weeks!
  • Write code yourself, this is an applied course! Don't be a "couch potato".

Lectures

  • 23 sections
  • 121 lectures
  • 20h 11m total length
Introduction and Outline
Preview
02:42
Where to get the code
02:06
How to Succeed in this Course
03:04
Intro to Google Colab, how to use a GPU or TPU for free
12:32
Uploading your own data to Google Colab
11:41
Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn?
08:54
Temporary 403 Errors
02:58
Review Section Introduction
02:37
What is Machine Learning?
14:26
Code Preparation (Classification Theory)
15:59
Classification Notebook
08:40
Code Preparation (Regression Theory)
07:18
Exercise: Predicting Diabetes Onset
02:34
Regression Notebook
10:34
Exercise: Real Estate Predictions
02:33
The Neuron
09:58
How does a model 'learn'?
10:53
Making Predictions
06:45
Saving and Loading a Model
04:27
Suggestion Box
03:10
Artificial Neural Networks Section Introduction
06:00
Forward Propagation
09:40
The Geometrical Picture
09:43
Activation Functions
17:18
Multiclass Classification
08:41
How to Represent Images
12:36
Color Mixing Clarification
55:00
Code Preparation (ANN)
12:42
ANN for Image Classification
08:36
ANN for Regression
11:05
Exercise: E. Coli Protein Localization Sites
02:21
Why use tf.data?
03:59
Sample Code for tf.data
21:00
What is Convolution? (part 1)
16:38
What is Convolution? (part 2)
05:56
What is Convolution? (part 3)
06:41
Convolution on Color Images
15:58
Why use 0-indexing?
23:16
CNN Architecture
20:58
CNN Code Preparation
15:13
CNN for Fashion MNIST
06:46
CNN for CIFAR-10
04:28
Data Augmentation
08:51
Batch Normalization
05:14
Improving CIFAR-10 Results (Legacy)
10:22
Improving CIFAR-10 Results
19:11
Exercise: Facial Expression Recognition
01:35
FAQ: How to Choose Filters?
09:47
Embeddings
13:37
Code Preparation (NLP)
13:52
Text Preprocessing (Legacy)
05:30
Text Preprocessing
19:03
CNNs for Text
08:07
Text Classification with CNNs (Legacy)
06:10
Text Classification with CNNs
24:11
Exercise: Sentiment Analysis
02:01
Genomics Concepts, Data Description, Task Description
12:53
Genomics with CNNs in Python
23:13
Large Datasets and Data Generators
07:03
Data Generators in Tensorflow and Keras
36:45
Making Predictions for a Single Image File (JPEG, PNG, etc.)
10:33
Tensorflow Datasets and image_dataset_from_directory
05:06
Tensorflow Datasets and image_dataset_from_directory in Python
19:20
Mean Squared Error
09:11
Binary Cross Entropy
05:58
Categorical Cross Entropy
08:06
Gradient Descent
07:52
Stochastic Gradient Descent
04:36
Momentum
06:11
Variable and Adaptive Learning Rates
11:46
Adam Optimization (pt 1)
13:15
Adam Optimization (pt 2)
11:14
Introduction and Outline
01:51
Review of Important Concepts
03:43
Where to get the code and data for this course
02:08
How to Succeed in this Course
03:13
Tensorflow or Theano - Your Choice!
04:10
How to load the SVHN data and benchmark a vanilla deep network
05:04
Real-Life Examples of Convolution
08:53
Beginner's Guide to Convolution
06:28
What is convolution?
05:19
Convolution example with audio: Echo
06:40
Convolution example with images: Gaussian Blur
05:42
Convolution example with images: Edge Detection
03:22
Write Convolution Yourself
09:15
Alternative Views on Convolution
06:43
Translational Invariance
02:23
Architecture of a CNN
05:09
Convolution on 3-D Images
10:50
Tracking Shapes in a CNN
16:38
Relationship to Biology
02:19
Convolution and Pooling Gradients
02:40
LeNet - How the Shapes Go Together
12:52
Theano - Building the CNN components
04:20
Theano - Full CNN and Test on SVHN
17:27
Visualizing the Learned Filters
03:36
TensorFlow - Building the CNN components
03:40
TensorFlow - Full CNN and Test on SVHN
10:39
Practical Image Processing Tips
03:08
Advanced CNNs and how to Design your Own
11:10
Facial Expression Recognition Problem Description
12:22
The class imbalance problem
06:02
Utilities walkthrough
05:46
Convolutional Net in Theano
21:04
Convolutional Net in TensorFlow
19:04
What is the Appendix?
03:47
Pre-Installation Check
04:13
Anaconda Environment Setup
20:21
How to install Numpy, Scipy, Matplotlib, Pandas, PyTorch, and TensorFlow
17:33
Beginner's Coding Tips
13:22
How to Code Yourself (part 1)
15:55
How to Code Yourself (part 2)
09:24
Proof that using Jupyter Notebook is the same as not using it
12:29
Python 2 vs Python 3
04:38
Is Theano Dead?
10:04
How to use Github & Extra Coding Tips (Optional)
11:12
How to Succeed in this Course (Long Version)
10:25
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:05
What order should I take your courses in? (part 1)
11:19
What order should I take your courses in? (part 2)
16:07
Where to get discount coupons and FREE AI tutorials
05:49
Data Links

Reviews

4.7

38 reviews for this course

5 Stars
(57%)
4 Stars
(35%)
3 Stars
(6%)
2 Stars
(1%)
1 Stars
(1%)

Testimonials and Success Stories

student-avatar

H. Z.

Machine Learning Research Scientist
flag-usa
United States

“I am one of your students. Yesterday, I presented my paper at ICCV 2019. You have a significant part in this, so I want to sincerely thank you for your in-depth guidance to the puzzle of deep learning. Please keep making awesome courses that teach us!”

5.0
student-avatar

Wade J.

Data Scientist
flag-usa
United States

“I just watched your short video on “Predicting Stock Prices with LSTMs: One Mistake Everyone Makes.” Giggled with delight.

You probably already know this, but some of us really and truly appreciate you. BTW, I spent a reasonable amount of time making a learning roadmap based on your courses and have started the journey.

Looking forward to your new stuff.”

5.0
student-avatar

Kris M.

Data Scientist
flag-usa
United States

“Thank you for doing this! I wish everyone who call’s themselves a Data Scientist would take the time to do this either as a refresher or learn the material. I have had to work with so many people in prior roles that wanted to jump right into machine learning on my teams and didn’t even understand the first thing about the basics you have in here!!

I am signing up so that I have the easy refresh when needed and the see what you consider important, as well as to support your great work, thank you.”

5.0
student-avatar

Steve M.

Machine Learning Research Scientist
flag-usa
United States

“I have been intending to send you an email expressing my gratitude for the work that you have done to create all of these data science courses in Machine Learning and Artificial Intelligence. I have been looking long and hard for courses that have mathematical rigor relative to the application of the ML & AI algorithms as opposed to just exhibit some 'canned routine' and then viola here is your neural network or logistical regression.

Your courses are just what I have been seeking. I am a retired mathematician, statistician and Supply Chain executive from a large Fortune 500 company in Ohio. I also taught mathematics, statistics and operations research courses at a couple of universities in Northern Ohio.

I have taken many courses and have enjoyed the journey, I am not going to be critical of any of the organizations from whom I have taken courses. However, when I read a review about one of your courses in which the student was complaining that one would need a PhD in Mathematics to understand it, I knew this was the course (or series of courses) that I wanted. (Having advanced degrees in mathematics, I knew that it was highly unlikely that a PhD would actually be required.)”

5.0
student-avatar

Saurabh W.

Data Scientist
flag-india
India

“Hi Sir I am a student from India. I've been wanting to write a note to thank you for the courses that you've made because they have changed my career. I wanted to work in the field of data science but I was not having proper guidance but then I stumbled upon your "Logistic Regression" course in March and since then, there's been no looking back. I learned ANNs, CNNs, RNNs, Tensorflow, NLP and whatnot by going through your lectures. The knowledge that I gained enabled me to get a job as a Business Technology Analyst at one of my dream firms even in the midst of this pandemic. For that, I shall always be grateful to you. Please keep making more courses with the level of detail that you do in low-level libraries like Theano.”

5.0
student-avatar

David P.

Financial Analyst
flag-usa
United States

“I just wanted to reach out and thank you for your most excellent course that I am nearing finishing.

And, I couldn't agree more with some of your "rants", and found myself nodding vigorously!

You are an excellent teacher, and a rare breed.

And, your courses are frankly, more digestible and teach a student far more than some of the top-tier courses from ivy leagues I have taken in the past.

(I plan to go through many more courses, one by one!)

I know you must be deluged with complaints in spite of the best content around That's just human nature.

Also, satisfied people rarely take the time to write, so I thought I will write in for a change. :)”

5.0
student-avatar

P. C.

Deep Learning Research Scientist
flag-china
China

“Hello, Lazy Programmer!

In the process of completing my Master’s at Hunan University, China, I am writing this feedback to you in order to express my deep gratitude for all the knowledge and skills I have obtained studying your courses and following your recommendations.

The first course of yours I took was on Convolutional Neural Networks (“Deep Learning p.5”, as far as I remember). Answering one of my questions on the Q&A board, you suggested I should start from the beginning – the Linear and Logistic Regression courses. Despite that I assumed I had already known many basic things at that time, I overcame my “pride” and decided to start my journey in Deep Learning from scratch.

Course by course, I was renewing the basics and the prerequisites. Thus, in several months, after every day studying under your guidance, I was able to gain enough intuitions and practical skills in order to begin progressing in my research. Having a solid background, it was just a pleasure to read all the relevant papers in the field as well as to make all the experiments needed for achieving my goal – creating a high-performance CNN for offline HCCR.

I believe, the professionalism of any teacher can be estimated by the feedback received from their students, and it’s of the utmost importance for me to thank you, Lazy Programmer!

I want you to know, in spite, that we have never actually met and you haven’t taught me privately, I consider you one of my greatest Teachers.

The most important things I have learned from you (some in the hard way, though) beside many exciting modern Deep Learning/AI techniques and algorithms are:

1) If one doesn’t know how to program something, one doesn’t understand it completely.

2) If one is not honest with oneself about one’s prior knowledge, one will never succeed in studying more advanced things.

3) Developing skills in BOTH Math and Programming is what makes one a good student of this major.

I am still studying your courses, and am certain I will ask you more than just a few technical questions regarding their content, but I already would like to say, that I will remember your contribution to my adventure in the Deep Learning field, and consider it as big as one of such great scientists’ as Andrew Ng, Geoffrey Hinton, and my supervisor.

Thank you, Lazy Programmer! 非常感谢您,Lazy 老师!

If you are interested, you can find my first paper’s preprint here:

https://arxiv.org/abs/xxx”

5.0
student-avatar

Dima K.

Data Scientist
flag-ukraine
Ukraine

“By the way, if you are interested to hear. I used the HMM classification, as it was in your course (95% of the script, I had little adjustments there), for the Customer-Care department in a big known fintech company. to predict who will call them, so they can call him before the rush hours, and improve the service. Instead of a poem, I Had a sequence of the last 24 hours' events that the customer had, like: "Loaded money", "Usage in the food service", "Entering the app", "Trying to change the password", etc... the label was called or didn't call. The outcome was great. They use it for their VIP customers. Our data science department and I got a lot of praise.”

5.0
student-avatar

Andres Lopez C.

Data Engineer
flag-usa
United States

“This course is exactly what I was looking for. The instructor does an impressive job making students understand they need to work hard in order to learned. The examples are clear, and the explanations of the theory is very interesting.”

5.0
student-avatar

Mohammed K.

Machine Learning Engineer
flag-germany
Germany

“Thank you, I think you have opened my eyes. I was using API to implement Deep learning algorithms and each time I felt I was messing out on some things. So thank you very much.”

5.0
student-avatar

Tom P.

Machine Learning Engineer
flag-usa
United States

“I have now taken a few classes from some well-known AI profs at Stanford (Andrew Ng, Christopher Manning, …) with an overall average mark in the mid-90s. Just so you know, you are as good as any of them. But I hope that you already know that.

I wish you a happy and safe holiday season. I am glad you chose to share your knowledge with the rest of us.”

5.0
Start learning today

Join 30 day bootcamp for free

4.7/5 from — 600k+ learners