Hands-On Artificial Intelligence with Keras and Python
4.4 (2 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.
23 students enrolled

Hands-On Artificial Intelligence with Keras and Python

Use Keras to solve advanced industry relevant projects
4.4 (2 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.
23 students enrolled
Created by Packt Publishing
Last updated 4/2019
English
English [Auto]
Current price: $86.99 Original price: $124.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 2.5 hours on-demand video
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Develop a deep learning network from scratch with Keras using Python to solve a practical problem of classifying the traffic signs on the road.
  • Introduction to Computer Vision & Deep Learning.
  • Setup and develop an environment with VM or Docker. Ipython and Jupyter notebook.
  • Activation functions, Forward propagation, backward propagation.
  • How to use Tensorflow backend. Hands-on coding with me.
  • Tensorboard and intuitions of filters and hyper-parameters.
  • Deploy and evaluate for other real-world applications. Future work and readings!
  • Neural network style transfer - Image style translation and generation
  • Game AI - Running game agents using Deep Q network
Course content
Expand all 20 lectures 02:31:28
+ Introduction
4 lectures 15:13

This video will give you an overview about the course.

Preview 02:57

In this video, you’ll be introduced to Deep Learning terminology and explain where Keras fits into the picture of Deep learning models.

   •  Introduce AI, Machine learning, Deep learning terminologies

   •  Understand Tensor in TensorFlow and its general naming implications

   •  Understand where Keras fits in the picture

AI, Machine Learning, Deep Learning Overview
03:55

This video will give a brief introduction to Keras and explain why it is important.

   •  Comparative analysis of different Deep Learning frameworks

   •  Understand the different layers and core models in Keras briefly

   •  Code simplicity analysis of Keras vs Tensorflow to understand the usability of Keras

Keras Overview
03:42

In this video, we will set up the development environment for the course.

   •  Use Anaconda on Ubuntu 14 or higher

   •  Clone the Git repo and follow the environment setup commands

   •  conda env create <> conda activate <> conda env list

Development Environment Setup
04:39
+ CNN, Deep Driving Simulator
5 lectures 57:10

This video will give you a brief understanding of Deep Learning. Develop an intuition of higher dimensional space modeling using neural networks

   •  Intuition of Deep Learning and how it relates to modeling

   •  Understand Machine learning ideas and concepts

   •  Develop a good intuition of the field

Preview 08:46

This video will introduce you to the deep neural network.

   •  Understand Forward propagation

   •  Understand Backward propagation

Deep Neural Nets : Forward and Backward Propagation
13:56

This video introduces CNN and intuition of convolutions and Covnets.

   •  Introduce convolutions, Convolution Maths and operations

   •  Find out features from a dataset and strive towards minimizing error using pre-built Keras libraries

   •  Explain where Keras fits in the picture

CNN Intuition
12:00

This video gives a brief introduction to autonomous driving simulators and figuring out how to drive autonomously. Which features to look at? Develop the model and compile it.

   •  Download the simulator and drive autonomously

   •  Understand the Keras code for model development

   •  Build the model and visualize the loss function

Autonomous Driving Simulator
05:29

This video will give a brief on running the frozen model in autonomous mode and verify how it performs.

   •  Run the frozen model using the command to help to drive autonomously

   •  Retrain if necessary to go round the lap

   •  Try other tracks

Running in Autonomous Mode
16:59
+ Deep Reinforcement Learning with Keras for Game AI
4 lectures 28:48

This video will give you a brief understanding of Reinforcement Learning. Develop an intuition.

   •  Gives an intuition of Reinforcement Learning and how it relates to modeling

   •  Define Agent, Policy, Reward

   •  Develop a good intuition of the field

Reinforcement Learning and Q-Learning for Game AI
07:16

This video will give you a brief introduction and intuition of OpenAI Gym.

   •  Set up environment

   •  Understand RL benchmarking

   •  Learn RL training with Keras

Setting up Game Environment – OpenAI Gym with Keras
06:55

In this video, you will get a brief introduction to a game environment and how to extract State, Action, and Reward out of it. Finally, train to run the agent in autonomous mode.

   •  Download and setup everything

   •  Understand the different parts of the code

   •  Build the model and give intuition of changing the model to Keras

Developing DQN-Based Dino Run Game
09:20

In this video, you will run the frozen model in autonomous mode and verify how it performs.

   •  Run the frozen model using the command to help navigate autonomously

   •  Retrain if necessary to score even higher

   •  Try other tracks

Developing Model for Dino Run Game to Run in AI Mode
05:17
+ Image Style Transfer Using Neural Network Style Transfer
4 lectures 34:39

This video will give a brief understanding of the Style transfer algorithm using standard CNN.

   •  Intuition of Style transfer

   •  Understand the Loss function in 2 different styled images

   •  Develop and understand the use of standard state-of-the-art DNN models

Neural Network Style Transfer
06:04

In this video, you will understand the code.

   •  Understand TensorFlow eager execution

   •  Display of results where the style transfer is happening

   •  Understand the code execution in Jupyter notebook environment

Neural Network Style Transfer – CNN Code Using Keras
10:20

In this video, we will look at different paradigm of NN – GAN.

   •  Understand the loss function in GAN

   •  Go from GAN to CGAN paradigm

   •  Style transfer and generating different images using CGAN

Generative Adversarial Network
09:17

In this video, you will look at Style transfer and generating different images using CGAN

   •  Example of a Style transfer code in CGAN

   •  Develop the generator and discriminator

   •  Derive and code the loss function

Style Transfer – CGAN Code
08:58
+ Conclusion, What’s Next?
3 lectures 15:38

In this video, we will look at what are the problems in CNN

   •  Understand the current research trends in CNN

   •  Materials to look at for CNN

CNN Problem and Trends
06:24

In this video, we will see what are the problems in RL

   •  Understand the current research trends in RL

   •  Materials to look at for RL

RL Problems and Trends
04:40

In this video, we will see what are the problems in GAN

   •  Understand the current research trends in GAN

   •  Materials to look at for GAN

GAN Problems and Trends
04:34
Requirements
  • This course will take a Hands-on approach to teach you the skills required to develop Keras models using Python, relevant interesting industry problems with illustrative examples. This will overcome your challenge in AI from scratch.
Description

AI will help you solve key challenges in the future in several domains. It is an exciting time to be doing AI with world making its shift towards Industry 2.0 with automation in focus.

This course will help you learn by doing an industry relevant problem in image processing domain, develop and understand automation and AI techniques. You will learn how to harness the power of algorithms by creating apps which intelligently interact with the world around you, addressing common challenges faced in AI ecosystem.

By the end of the course, you will be able to build real-world artificial intelligence applications using Keras and Python.

About the Author

Sandipan Das is working as a senior software engineer in the field of perception within Autonomous vehicles industry in Sweden. He has more than 8 years of experience in developing and architecting various software components. He understands the industry needs and the gaps in between a traditional university degree and the job requirements in the industry. He has worked extensively on various neural network architectures and deployed them in real vehicles for various perception tasks in real-time.

Who this course is for:
  • If you are a data science enthusiast looking to achieve the power of Artificial Intelligence. Developers who want to build some broad range of skills such as image translation, autonomous driving simulation, deep reinforcement learning with AI will find this course most useful. Even experienced users of AI will discover new ideas and techniques in the projects, which will help them in becoming an AI expert.