Category: Articles

TensorFlow is a well-established player in the deep learning framework field. First, it works pretty damn well. Second, it’s a Google product that’s easily found throughout their own ecosystem (including Android, Chrome, and a slew of apps). Lastly, the TensorFlow team been very respectful of and responsive to both the researcher community as well as the commercial/production community.

Continue reading Python, Meet Swift

YOLO stands for You Only Look Once. It’s an object detection model used in deep learning use cases, of which there are mainly 2 main families:

The idea of one-stage detection (also referred to as one-shot detection) is that you only look at the image once.

Stating that it was simply a bit better than YOLOv2, but not much changed.
YOLOv4 was then recently introduced as the “Optimal Speed and Accuracy of Object Detection”.

Continue reading Introduction to YOLOv4: Research review

Naive Bayes algorithms are a set of supervised machine learning algorithms based on the Bayes probability theorem, which we’ll discuss in this article. Naive Bayes algorithms assume that there’s no correlation between features in a dataset used to train the model.

In spite of this oversimplified assumption, naive Bayes classifiers work very well in many complex real-world problems. A big advantage of naive Bayes classifiers is that they only require a relatively small number of training data samples to perform classification efficiently, compared to other algorithms like logistic regression, decision trees, and support vector machines.

Continue reading Naive Bayes Classifier in Python Using Scikit-learn

At WWDC 2018, Apple introduced a brand new framework for iOS developers called Natural Language. Simply put, this framework gives apps the ability to analyze natural language text and understand parts of it. Natural Language can perform a variety of tasks on a block of text by assigning tag schemes to the text. What does this mean?

Continue reading Natural Language in iOS 12: Customizing tag schemes and named entity recognition

For this article, I want to discuss a couple topics in the iOS world I’ve always found interesting: memory management, heaps, and stacks. I’ve never really understood the difference between them or how heaps and stacks relate to storing memory in Swift.

So, I decided to do some of my own research and dig deep into memory management in Swift. I hope you’re looking forward to this topic as much as I am! Let’s dive right in.

Continue reading Memory Management in Swift: Heaps & Stacks

So you’ve trained your Core ML model in Create ML or Turi Create. And now, you want to test it out on some real-world data. To make quick and dirty tests, you can leverage Swift Playgrounds and run Core ML models there. If you’re satisfied with the results, you can move over to Xcode project and run on-device or on a simulator.

Continue reading How to Run and Test Core ML Models in a Swift Playground

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 back! In this post, we’re going to cover the different imputation techniques used when dealing with missing data. Additionally, we’ll also explore a few code snippets you can use directly in your machine learning and data science projects.

Continue reading Hands-on with Feature Engineering Techniques: Imputing Missing Values

In a few of my previous posts, you’ve built a React Native app using Firebase as the backend service provider for email authentication, storing a user’s data upon successful signup.

Let’s add another common yet useful and necessary feature in our current app structure: Forgot Password. This feature will require another screen in the current React Native app. To follow this tutorial, you can work through any of the previous posts if you’re a beginner in the React Native world:

Continue reading Implementing a ‘Forgot Password’ feature in React Native with Firebase

ARIMA stands for Auto Regressive Integrated Moving Average. It’s a statistical library used for analyzing and forecasting time series data. Models created using ARIMA library are more flexible than other statistical models like simple linear regression. Here’s a closer look at the terms that make up this acronym:

Continue reading Implementing ARIMA using Statsmodels and Python