The Ultimate Deep Learning & NLP Certification Bundle

443 Enrolled
6 Courses & 36 Hours
$29.99$1,200.00
You save 97% -

What's Included

Computer Vision Applications with Deep Learning
  • Certification included
  • Experience level required: Intermediate
  • Access 75 lectures & 7 hours of content 24/7
  • Length of time users can access this course: Lifetime

Course Curriculum

75 Lessons (7h)

  • Welcome
    Introduction2:35
    Outline and Perspective6:49
    Where to get help2:06
  • Review
    Review of CNNs10:34
    Where to get the code and data2:26
    Fashion MNIST3:29
    Review of CNNs in Code6:09
  • VGG and Transfer Learning
    VGG Section Intro3:04
    What's so special about VGG?7:00
    Transfer Learning8:22
    Relationship to Greedy Layer-Wise Pretraining2:19
    Getting the data2:17
    Code pt 19:23
    Code pt 23:41
    Code pt 33:27
    VGG Section Summary1:47
  • ResNet (and Inception)
    ResNet Section Intro2:49
    ResNet Architecture12:45
    Building ResNet - Strategy2:25
    Building ResNet - Conv Block Details3:34
    Building ResNet - Conv Block Code6:08
    Building ResNet - Identity Block Details1:23
    Building ResNet - First Few Layers2:27
    Building ResNet - First Few Layers (Code)4:15
    Building ResNet - Putting it all together4:19
    Exercise: Apply ResNet1:16
    Applying ResNet2:39
    1x1 Convolutions4:03
    Optional: Inception6:47
    Different sized images using the same network4:12
    ResNet Section Summary2:27
  • Object Detection (SSD)
    SSD Section Intro5:04
    Object Localization6:36
    What is Object Detection?2:53
    How would you find an object in an image?8:40
    The Problem of Scale3:47
    The Problem of Shape3:52
    SSD in Tensorflow9:57
    Modifying SSD to work on Video5:04
    Optional: Intersection over Union & Non-max Suppression5:06
    SSD Section Summary2:52
  • Neural Style Transfer
    Style Transfer Section Intro2:52
    Style Transfer Theory11:23
    Optimizing the Loss8:02
    Code pt 17:46
    Code pt 27:13
    Code pt 33:50
    Style Transfer Section Summary2:21
  • Facial Recognition
    Facial Recognition Section Introduction3:38
    Siamese Networks10:17
    Code Outline5:01
    Loading in the data4:40
    Splitting the data into train and test4:24
    Converting the data into pairs5:02
    Generating Generators4:20
    Creating the model and loss3:12
    Accuracy and imbalanced classes7:07
    Facial Recognition Section Summary3:28
  • Basics Review
    (Review) Tensorflow Basics7:27
    (Review) Tensorflow Neural Network in Code9:43
    (Review) Keras Discussion6:48
    (Review) Keras Neural Network in Code6:37
    (Review) Keras Functional API4:26
  • Appendix
    What is the Appendix?2:48
    Windows-Focused Environment Setup 201820:20
    How to How to install Numpy, Theano, Tensorflow, etc...17:30
    Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?22:04
    How to Succeed in this Course (Long Version)10:24
    How to Code by Yourself (part 1)15:54
    How to Code by Yourself (part 2)9:23
    Proof that using Jupyter Notebook is the same as not using it12:29
    Python 2 vs Python 34:38
    What order should I take your courses in? (part 1)11:18
    What order should I take your courses in? (part 2)16:07
    Where to get discount coupons and FREE deep learning material2:20

Computer Vision Applications with Deep Learning

LP
Lazy Programmer

Instructor

The Lazy Programmer is a data scientist, big data engineer, and full-stack software engineer. He has taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Humber College, and The New School. Multiple businesses have benefitted from their web programming expertise. He does all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies he has used are Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases, he has used MySQL, Postgres, Redis, MongoDB, and more.

Description

In this course, you’ll see how you can turn a CNN into an object detection system, that not only classifies images but can locate each object in an image and predict its label. You could imagine that such a task is a basic prerequisite for self-driving vehicles. With 75 lectures, you'll be looking at SSD, neural style transfer, and facial recognition. Sign up and learn these advanced applications of CNNs.

  • Access 75 lectures & 7 hours of content 24/7
  • See how a CNN can be turned into an object detection system
  • Learn about a state-of-the-art algorithm called SSD
  • Understand the process of neural style transfer
  • Become informed & aware about facial recognition

Specs

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Know how to build, train & use a CNN using some library (preferably in Python)
  • Understand basic theoretical concepts behind convolution & neural networks
  • Decent Python coding skills, preferably in data science & the Numpy Stack

Terms

  • Unredeemed licenses can be returned for store credit within 30 days of purchase. Once your license is redeemed, all sales are final.
Your cart is empty. Continue Shopping!
Processing order...