In this article, we will continue building production machine learning systems on GCP with a special focus on the design of hybrid ML systems which covers the following:
Building hybrid cloud machine learning models Kubeflow for hybrid cloud Optimize Tensorflow graphs for mobileContinue reading “Building Production Machine Learning Systems on Google Cloud Platform”
Complex models such as deep neural networks are prone to overfitting because of their flexibility in memorizing the idiosyncratic patterns in the training set, instead of generalizing to unseen data.
Any modification we make to a learning algorithm that’s intended to reduce its generalization error but not its training error is called regularization. Keeping the model simple enough by using regularization techniques allows the network to generalize well on data points it hasn’t seen before.
In this tutorial, let’s start using a backend service to add real-time features to the chat app. For our backend services, I’m going to use Firebase. We’ll look at how to install and configure Firebase SDK in a React Native app with the help of react-native-firebase module, as well as set up and configure email authentication. In order to follow this tutorial and future posts, you’ll need to have an active Firebase project.
Core ML is Apple’s framework for machine learning. With Core ML, everyone can use machine learning in their apps—as long as that app runs on an Apple platform, and Apple platforms only. Core ML cannot be used with Android, Windows, or on websites. This is very unfortunate because Core ML is such a great piece of technology.
This tutorial covers how to set up DeepLab within TensorFlow to train your own machine learning model, with a focus on separating humans from the background of a photograph in order to perform background replacement—also known as image segmentation.
More generally, this article might be a good introduction for beginners without a lot of code experience in learning how to:
Continue reading How to replace backgrounds in photos with machine learning
In a previous tutorial titled Building an Android Login System, we created an Android login system, which allows the user to register by their first name, last name, username, and password. A Flask server listens for requests from the user and inserts a new record in a MySQL database. After successful registration, the user can log in and be verified by the server.
This tutorial extends upon the previous tutorial to allow users to enter an email address while registering. To verify the ownership of the entered email address, an email is sent to this address with a verification code. The user copies the code sent in the email and pastes it into the application to complete the email verification process.
Continue reading “Email Verification for an Android App Registration System”
Text embeddings always play an important role in natural language-related tasks. The quality of text embeddings depends upon the size of the dataset that the model is trained on which improves the quality of features extracted. Instead of training the model completely from scratch, one can use pre-trained models like Google’s Universal Sentence Encoder which is discussed in this story ahead.
Continue reading Introduction to Google’s Universal Sentence Encoder: A State-of-the-Art Model
This series of articles I’ll be writing over the coming weeks will focus on using JavaScript and the deep learning framework TensorFlow.js. Though I’ll try to make these articles as easy as possible, I’m making the following assumptions about you, the reader.
As an undergraduate I took a course on emergent phenomena — collective behaviors that arise from individual action. One of the most elegant examples we studied was Conway’s Game of Life. Devised by British mathematician John Conway, the Game of Life is played on an infinite 2-dimensional grid where each cell can occupy one of two states: dead (0) or alive (1). The world is initialized in a random state and three simple rules govern how each grid cell evolves [1]:
Continue reading Implementing Conway’s Game of Life in Lens Studio
Once you’ve trained a TensorFlow model and it’s ready to be deployed, you’d probably like to move it to a production environment. Luckily, TensorFlow provides a way to do this with minimal effort. In this article, we’ll use a pre-trained model, save it, and serve it using TensorFlow Serving. Let’s get moving!
TensorFlow Serving is a system built with the sole purpose of bringing machine learning models to production. TensorFlow’s ModelServer provides support for RESTful APIs. However, we’ll need to install it before we can use it. First, let’s add it as a package source.
