Artificial Intelligence Masterclass
4.5 (287 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
3,445 students enrolled

Artificial Intelligence Masterclass

Enter the new era of Hybrid AI Models optimized by Deep NeuroEvolution, with a complete toolkit of ML, DL & AI models
4.5 (287 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
3,445 students enrolled
Last updated 4/2019
English
English [Auto-generated], Italian [Auto-generated]
Current price: $11.99 Original price: $199.99 Discount: 94% off
2 days left at this price!
30-Day Money-Back Guarantee
This course includes
  • 12 hours on-demand video
  • 18 articles
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to Udemy's top 3,000+ courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • How to Build an AI
  • How to Build a Hybrid Intelligent System

  • Fully-Connected Neural Networks

  • Convolutional Neural Networks
  • Recurrent Neural Networks
  • AutoEncoders
  • Variational AutoEncoders
  • Mixture Density Network
  • Deep Reinforcement Learning
  • Policy Gradient
  • Genetic Algorithms
  • Evolution Strategies
  • Covariance-Matrix Adaptation Evolution Strategies (CMA-ES)
  • Controllers
  • Meta Learning
  • Deep NeuroEvolution
Requirements
  • High school mathematics
  • A bit of coding experience
Description

Today, we are bringing you the king of our AI courses...:


The Artificial Intelligence MASTERCLASS


Are you keen on Artificial Intelligence? Do want to learn to build the most powerful AI model developed so far and even play against it? Sounds tempting right...


Then Artificial Intelligence Masterclass course is the right choice for you. This ultimate AI toolbox is all you need to nail it down with ease. You will get 10 hours step by step guide and the full roadmap which will help you build your own Hybrid AI Model from scratch.  


In this course, we will teach you how to develop the most powerful Artificial intelligence model based on the most robust Hybrid Intelligent System. So far this model proves to be the best state of the art AI ever created beating its predecessors at all the AI competitions with incredibly high scores.


This Hybrid Model is aptly named the Full World Model, and it combines all the state of the art models of the different AI branches, including Deep Learning, Deep Reinforcement Learning, Policy Gradient, and even, Deep NeuroEvolution.


By enrolling in this course you will have the opportunity to learn how to combine the below models in order to achieve best performing artificial intelligence system:

  • Fully-Connected Neural Networks

  • Convolutional Neural Networks

  • Recurrent Neural Networks

  • Variational AutoEncoders

  • Mixed Density Networks

  • Genetic Algorithms

  • Evolution Strategies

  • Covariance Matrix Adaptation Evolution Strategy (CMA-ES)

  • Parameter-Exploring Policy Gradients

  • Plus many others



Therefore, you are not getting just another simple artificial intelligence course but all in one package combining a course and a master toolkit, of the most powerful AI models. You will be able to download this toolkit and use it to build hybrid intelligent systems. Hybrid Models are becoming the winners in the AI race, so you must learn how to handle them already.


In addition to all this, we will also give you the full implementations in the two AI frameworks: TensorFlow and Keras. So anytime you want to build an AI for a specific application, you can just grab those model you need in the toolkit, and reuse them for different projects!

Don’t wait to join us on this EPIC journey in mastering the future of the AI - the hybrid AI Models.


Who this course is for:
  • Anyone interested in Artificial Intelligence, Deep Learning, or Machine Learning
Course content
Expand all 87 lectures 12:01:47
+ Introduction
5 lectures 31:23
Your Three Best Resources
10:42
Download the Resources here
01:28
Meet your instructors!
00:14
+ Step 1 - Artificial Neural Network
9 lectures 01:18:00
Welcome to Step 1 - Artificial Neural Network
00:23
The Neuron
16:15
The Activation Function
08:29
How do Neural Networks work?
12:47
How do Neural Networks learn?
12:58
Gradient Descent
10:12
Stochastic Gradient Descent
08:44
Backpropagation
05:21
+ Step 2 - Convolutional Neural Network
10 lectures 01:41:04
Welcome to Step 2 - Convolutional Neural Network
00:17
Plan of Attack
03:31
What are Convolutional Neural Networks?
15:49
Step 1 - The Convolution Operation
16:38
Step 1 Bis - The ReLU Layer
06:41
Step 2 - Pooling
14:13
Step 3 - Flattening
01:52
Step 4 - Full Connection
19:24
Summary
04:19
Softmax & Cross-Entropy
18:20
+ Step 3 - AutoEncoder
11 lectures 39:29
Welcome to Step 3 - AutoEncoder
00:16
Plan of Attack
02:12
What are AutoEncoders?
10:50
A Note on Biases
01:15
Training an AutoEncoder
06:10
Overcomplete Hidden Layers
03:52
Sparse AutoEncoders
06:15
Denoising AutoEncoders
02:32
Contractive AutoEncoders
02:23
Stacked AutoEncoders
01:54
Deep AutoEncoders
01:50
+ Step 4 - Variational AutoEncoder
4 lectures 17:54
Welcome to Step 4 - Variational AutoEncoder
00:15
Introduction to the VAE
08:15
Variational AutoEncoders
04:29
Reparameterization Trick
04:55
+ Step 5 - Implementing the CNN-VAE
9 lectures 01:26:56
Welcome to Step 5 - Implementing the CNN-VAE
00:37
Introduction to Step 5
08:11
Initializing all the parameters and variables of the CNN-VAE class
13:54
Building the Encoder part of the VAE
19:34
Building the "V" part of the VAE
10:40
Building the Decoder part of the VAE
10:40
Implementing the Training operations
18:34
Full Code Section
01:25
The Keras Implementation
03:21
+ Step 6 - Recurrent Neural Network
7 lectures 01:11:54
Welcome to Step 6 - Recurrent Neural Network
00:20
Plan of Attack
02:32
What are Recurrent Neural Networks?
16:01
The Vanishing Gradient Problem
14:27
LSTMs
19:47
LSTM Practical Intuition
15:11
LSTM Variations
03:36
+ Step 7 - Mixture Density Network
4 lectures 25:07
Welcome to Step 7 - Mixture Density Network
00:21
Mixture Density Networks
09:33
VAE + MDN-RNN Visualization
05:45
+ Step 8 - Implementing the MDN-RNN
12 lectures 02:06:57
Welcome to Step 8 - Implementing the MDN-RNN
00:52
Initializing all the parameters and variables of the MDN-RNN class
13:42
Building the RNN - Gathering the parameters
09:54
Building the RNN - Creating an LSTM cell with Dropout
16:15
Building the RNN - Setting up the Input, Target, and Output of the RNN
14:54
Building the RNN - Getting the Deterministic Output of the RNN
11:56
Building the MDN - Getting the Input, Hidden Layer and Output of the MDN
13:22
Building the MDN - Getting the MDN parameters
10:57
Implementing the Training operations (Part 1)
15:31
Implementing the Training operations (Part 2)
13:34
Full Code Section
03:26
The Keras Implementation
02:33
+ Step 9 - Reinforcement Learning
4 lectures 31:54
Welcome to Step 9 - Reinforcement Learning
00:15
What is Reinforcement Learning?
11:26
A Pseudo Implementation of Reinforcement Learning for the Full World Model
20:00
Full Code Section
00:12