Keras is an open source Python neural-network library for the creation of deep learning neural-networks. Keras offers an intuitive set of abstractions, simplifying the development of deep learning neural-networks and models.

This instructor-led, live training (online or onsite) is aimed at software engineers who wish to develop advanced deep learning neural-networks and model using Keras and Python.

By the end of this training, participants will be able to:

Apply deep learning with supervised or unsupervised learning methods.

Develop, train, and implement concurrent neural networks and recurrent neural networks.

Use Keras and Python to build deep learning models to solve problems involving images, text, sound, and more.

Format of the Course

Interactive lecture and discussion.

Lots of exercises and practice.

Hands-on implementation in a live-lab environment.

Course Customization Options

To request a customized training for this course, please contact us to arrange.

Course Outline

Introduction

Keras and Deep Learning Frameworks

TensorFlow and Theano back-ends

Keras vs Tensorflow

Data and Machine Learning

Tabular data, visual data, unstructured data, etc.

Unsupervised learning, supervised learning, reinforcement learning, etc.

Preparing the Development Environment

Installing and configuring Anaconda

Installing Keras with a TensorFlow back-end

Neural Networks in Keras

Using Keras functional API to build a network

Pre-processing and fitting data

Defining a Keras model

Mutiple Input and Output Networks

Building two input-networks

Representing high-cardinality data

Merging layers

Extending the two input-network

Building neural networks with multiple outputs

Solving multiple problems simultaneously

Training and Pre-Training

Training models

Saving and loading models

Using ResNet50 on models

TensorBoard

Exporting Keras logs

Visualizing a computational graph and training progress

Gain a foundational understanding of machine learning

Implement both supervised and unsupervised machine learning models

Measure the performances of different machine learning models using the suitable metrics

Understand which machine learning model to use in which situation

Reduce data of higher dimensions to data of lower dimensions using principal component analysis

Requirements

A windows machine, and a willingness to learn

Description

In this course, we will cover the foundations of machine learning. The course is designed to not beat around the bush, and cover exactly what is needed concisely and engagingly. Based on a university level machine learning syllabus, this course aims to effectively teach, what can sometimes be dry content, through the use of entertaining stories, professionally edited videos, and clever scriptwriting. This allows one effectively absorb the complex material, without experiencing the usual boredom that can be experienced when trying to study machine learning content.

The course first goes into a very general explanation of machine learning. It does this by telling a story that involves an angry farmer and his missing donuts. This video sets the foundation for what is to come.

After a general understanding is obtained, the course moves into supervised classification. It is here that we are introduced to neural networks through the use of a plumbing system on a flower farm.

Thereafter, we delve into supervised regression, by exploring how we can figure out whether certain properties are value for money or not.

We then cover unsupervised classification and regression by using other farm-based examples.

This course is probably the best foundational machine learning course out there, and you will definitely benefit greatly from it.

Who this course is for:

Beginners to machine learning. College students looking to improve their capability. Professionals looking to implement machine learning in their day to day business.

Simple implementation of convolutional neural networks, deep neural networks, recurrent neural networks, and linear regression

Understanding of keras syntax

Understanding of different deep learning algorithms

Requirements

Basic python knowledge

Familiarity with data science and numpy

Description

When I started learning deep learning, I had a hard time figuring out how everything worked. What library was the best for me? Which algorithms worked best for which data set? How could I know my model was accurate? I spent a lot of time on tutorials, courses and reading to try and answer these questions. In the end, I felt like the process I took to learn deep learning was too inefficient. That is why I created this course.

Learn Keras: Build 4 Deep Learning Applications is a course that I designed to solve the problems my past self had. This course is designed to get you up and running with deep learning as quickly as possible. We use keras in this course because it is one of the easiest libraries to learn for deep learning. Each video, we go over a different machine learning algorithm and its use cases. The four algorithms we focus on the most are:

1. Linear Regression

2. Dense Neural Networks

3. Convolutional Neural Networks

4. Recurrent Neural Networks

In conclusion, if you are looking at a quick intro into deep learning, this course is for you.

So what are you waiting for? Let’s get started!

Who this course is for:

Someone who wants to get into machine learning but feels overwhelmed by other tutorials

Someone who is interested in machine learning but doesn’t know where to start

How to Implement Complex Neural Network which has both CNN and RNN layers

Requirements

Student should know theoretical concepts of Deep Learning

Some experience with Python will be a plus

Description

In this comprehensive course, you will learn how to implement various types of neural networks using Keras, with step-by-step guidance and hands-on projects. You don’t need to set up anything on your system as everything will be done online. You will be provided with example code and practice problems to reinforce your understanding of the concepts.

Throughout the course, you will work on four exciting projects that cover different neural network architectures and datasets. You will start by implementing and training a fully connected neural network for character classification using the popular MNIST dataset. You will then move on to creating and training a convolutional neural network (CNN) for the same dataset.

Next, you will learn how to implement and train a multi-layer LSTM neural network for Human Activity Recognition using the WISDM dataset. Finally, you will explore how to build and train a multi-layer CNN-RNN neural network for the same dataset.

For each project, you will be provided with code and Colab notebooks to experiment with, allowing you to practice and apply what you have learned in a real-world setting. This course is designed to take you from the basics to advanced models, so you can develop your skills and confidently implement complex neural networks.

While a theoretical background in deep learning is expected, a basic understanding is sufficient to get started with this course. Join us now and learn how to build and train neural networks using Keras!

Who this course is for:

Beginners course for people interested in learning the implementation of Neural Networks and doing real world projects