Building and Deploying Keras Models in a Multi-cloud Environment
Deep learning is merged into the normal operations of many companies due to the availability of huge repositories of data and easy to develop learning frameworks. Here, you'll use Keras to develop one such network or implement into your own model.
What you'll learn
As machine learning and deep learning techniques become popular, the importance of intuitive and simple abstractions that enable fast development and quick prototyping of these models become critical. In this course, Building and Deploying Keras Models in a Multi-cloud Environment, you'll learn the simple and intuitive functions and classes that Keras offers to build neural network models. First, you'll gain an understanding of the basic working of a neuron and how neural networks are structured and trained. You'll study the simplest form of a model, a network for linear regression which can be built using the simple Sequential model class in Keras, along with other forms of Sequential models such as convolutional neural networks for image classification. Next, you'll move on to recurrent neural networks and understand their ability to store state using outputs from previous time instances, and build a sequence-to-sequence RNN for language translation from English to French using Keras' functional API. Lastly, you'll learn to build and train these models on the most popular cloud platforms, Azure, AWS and the GCP. You'll study their IaaS and PaaS offerings for machine learning and use deep learning VMs or the distributed training framework to train our models. By the end of this course, you will be very comfortable using the Keras high-level API to build your machine learning models and know how you can take these models to the cloud for training at scale.
Table of contents
- Version Check 0m
- Module Overview 1m
- Prerequisites and Course Outline 2m
- Neurons and Neural Networks 5m
- Introducing Keras 2m
- Demo: Installing TensorFlow and Keras 2m
- Working with Sequential Models 4m
- Training a Neural Network: Gradient Descent Optimization and Back Propagation 4m
- Saving Models 1m
- Demo: Sequential Model for Linear Regression 6m
- Demo: Classification Using the Iris Dataset - Data Preparation and One Hot Encoding 5m
- Demo: Sequential Model for Classification and Saving to Disk 6m
- Demo: Loading a Saved Model 2m
- CNNs and the Local Receptive Field 2m
- Convolution 2m
- Feature Maps and the Convolutional Layer 4m
- Pooling 3m
- CNN Architectures 2m
- Demo: CNN for Image Classification - Cat and Dog 5m
- Demo: Training A CNN 3m
- Demo: Classification Using a CNN 2m
- Demo: Visualizing NNs Using GraphViz and Quiver 4m
- Module Overview 1m
- The Functional API 2m
- The Recurrent Neuron 4m
- Training RNNs - Vanishing and Exploding Gradients 5m
- The LSTM Cell 4m
- Working with RNNs Using Vectors and Sequences 4m
- The Encoder Decoder for Language Translation 2m
- Representing Inputs and Targets in Our Language Translation Model 4m
- Inputs to the Decoder During Training 3m
- Inputs to the Decoder During Prediction 2m
- Demo: Getting the Language Translations Dataset 5m
- Demo: One Hot Encoding of English and French Sentences 5m
- Demo: Training the Encoder Decoder 6m
- Demo: Encoder Decoder for Prediction 4m
- Demo: English to French Translation 4m
- Module Overview 1m
- Introducing Cloud MLE 4m
- Training a Model Using Cloud MLE 2m
- Steps Involved in Working with Cloud MLE 2m
- Demo: Enabling Cloud MLE and Creating Buckets on the GCP 3m
- Demo: Iris Classifier Code and Creating a Python Package 4m
- Demo: Running Training Locally and on the Cloud 4m
- Module Summary and Further Study 2m