In the last post, you created a 2-layer neural network from scratch and now have a better understanding of how neural networks work.
In this second part, you’ll use your network to make predictions, and also compare its performance to two standard libraries (scikit-learn and Keras).
Continue reading Building a Neural Network From Scratch Using Python (Part 2)
This tutorial builds a login system for an Android app. The app allows the users to register using a username and a password. A local server implemented in Python using Flask accepts the user data and inserts them into a MySQL database.
For securing the password, it’s encrypted using the MD5 hashing algorithm. After successful registration, the user will be able to log into the system by entering a server-verified username and password.
Do you remember climbing trees in your childhood? According to researchers, at the University of North Florida, climbing a tree can dramatically improve cognitive skills, including memory. Climbing trees can help children become more flexible in body and mind, while also developing strong spatial reasoning skills.
Continue reading Implementing Regression Using a Decision Tree and Scikit-Learn
This post is a part of a series about feature engineering techniques for machine learning with Python.
You can check out the rest of the articles:
Welcome to the last of this series on feature engineering! In today’s article, we’ll explore some advanced feature engineering techniques across different tasks. Specifically, we’ll look at advanced categorical encoding, advanced outlier detection, automated feature engineering and more.
Continue reading Hands-on with Feature Engineering Techniques: Advanced Methods
At I/O 2018, Google announced the release of Firebase’s ML Kit, a developer-friendly software package that allows mobile engineers to quickly integrate Machine Learning features in their applications with just a few lines of code. With ML Kit, we’re able to do amazing things like face detection, text recognition, and landmark recognition, all without needing to have deep knowledge about neural networks or model optimization.
Quick answer:
In a nutshell and much more simple words that may not be as comprehensive, AI is the study of automating intelligent decisions.
In order to train and test the methodologies scientists come up with. They need some sort of a playground to experiment in. A playground is an environment that is inspired by reality and agents are the decision-makers.
In this post we’re going to embark on a journey to explore and dive deep into the world of optimizers for machine learning models. We will also try and understand the foundational mathematics behind these functions and discuss their use cases, merits, and demerits.
So, what are we waiting for? Let’s get started!
In this tutorial we’ll cover XGBoost, a machine learning algorithm that has dominated the applied machine learning space recently.
XGBoost is an open source library that provides gradient boosting for Python, Java and C++, R and Julia. In this tutorial, our focus will be on Python. Gradient Boosting is a machine learning technique for classification and regression problems that produces a prediction from an ensemble of weak decision trees.
Continue reading Boosting your Machine Learning Models Using XGBoost
Push notifications—being one of the most integral parts of a mobile application—should be one of the first things you configure while building your mobile app. This blog will help you get you familiar with the fundamentals of setting up push notifications in your Xamarin.Android project using Firebase.
Firebase Cloud Messaging (FCM) is a cross-platform service that handles the sending, routing and queueing of messages between server applications and mobile apps.
Continue reading Firebase Cloud Messaging for Remote Push Notifications on Android with Xamarin
Custom Vision is a platform that allows you to build your own customized image classifiers. If you want to develop a mobile app where you need to classify images, Custom Vision (by Microsoft) offers you one of the fastest ways to go about it.
With Custom Vision, you simply upload your labeled images, train the model on the platform, and then export a Core ML model (for iOS) or TensorFlow model for Android (and even ONNX for Windows ML and DockerFile for AzureML). Yes, you heard that correctly. And it is free for 2 projects, and up to 5000 training images per project.
Continue reading Build Your Own Customized Image Classification Mobile App in 10 Minutes
