Blog

ARKit allow developers to layer virtual objects onto real world environment. In this post, we’ll explore how we can make our real hands interact with virtual objects using ARKit and Core ML, Apple’s machine learning framework.

Augmented reality is a lot of fun. ARKit from Apple is a really powerful tool that uses computer vision to analyze your environment and detect features from it. The power lies in the fact that you can use the detected features from the video to anchor virtual objects in the world and give the illusion they are real.

Continue reading Hand Detection with Core ML and ARKit

In this piece, we’ll look at some of the AI and machine learning conferences that took place in 2019 and highlight some of the best speakers and presentations. These events form a fundamental part of the machine learning and AI communities because they bring people together to learn from each other as well as forge meaningful collaborations.

Continue reading Top AI & Machine Learning Conferences

From Kaggle to classrooms, one of the first lessons in machine learning involves decision trees. The reason for the focus on decision trees is that they aren’t very mathematics heavy compared to other ML approaches, and at the same time, they provide reasonable accuracy on classification problems.

Continue reading Introduction to Decision Tree Learning

In this post, we’ll learn to use basic React Native animations while creating a RN project that has an animated search bar. To do this, we’ll use the react-native-animatable package.

In most applications, animations are repetitive swipes, slides, bounces, and so on; react-native-animatable provides preconfigured animated components that you can use without rewriting commonly-used animations yourself. The package provides a standard set of easy-to-use animations and declarative transitions for React Native.

Continue reading Building an Animated Search Bar with React Native

Natural Language Processing (NLP) helps computers (machines) “read and understand” text or speech by simulating human language abilities.

However, in recent years, NLP has grown rapidly because of an abundance of data. Given that more and more unstructured data is available, NLP has gained immense popularity.

The purpose of this article series NLP Chronicles is to introduce you to the NLP field while offering practical knowledge on how to tackle various NLP-related tasks. There is no final destination of this series. It’s best to think of this as wandering into the wilderness of NLP.

Continue reading NLP Chronicles: Introduction to Natural Language Processing with NLTK

Lenses aren’t just for making your selfies better — they can also be used as an effective tool for marketing and promotion. This has been primarily noticed by musicians, who are making use of this immersive medium to bring their songs digital and worldwide.

You may be wondering, are the musicians themselves making these Lenses? It may come as a surprise to know that many Official Lens Creators are actually the masterminds behind these AR experiences, merging the Lens market with big names like Megan Thee Stallion, Green Day, and Dua Lipa — an artist from any genre can have a Lens (The Bee Gees even have one!)

Continue reading Pop Star to Snap Star — a Look Into Snapchat’s Celebrity Lenses

In this article, we’ll learn about how Android developers can effectively use the Room database to improve data storage processes—and specifically, inserting and fetching records. But before jumping in, let’s first take a look at what we’ve previously been using for data storage in Android.

Before Room, and for a long time, Android developers have relied on SQLite as a primary database. SQLite was mostly easy to use and had some distinct advantages—it allowed data storage in a structured manner, performed better than other databases, and was a lightweight option compared to other 3rd party databases.

Continue reading Insert and fetch records with Room on Android using Kotlin

Many deep learning frameworks have been released over the past few years. Among them, PyTorch from Facebook AI Research is very unique and has gained widespread adoption because of its elegance, flexibility, speed, and simplicity.

Most deep learning frameworks have either been too specific to application development without sufficient support for research, or too specific for research without sufficient support for application development.

Continue reading “Basics of Image Classification with PyTorch”

Deep learning has seen a lot of progress in recent years. It’s hard to think of an industry that doesn’t use deep learning. The availability of large amounts of data along with increased computation resources have fueled this progress. There have been many well known and novel methods responsible for the growth of deep learning.

One of those is transfer learning, which is the method of using the representations/information learned by one trained model for another model that needs to be trained on different data and for a similar/different task. Transfer learning uses pre-trained models (i.e. models already trained on some larger benchmark datasets like ImageNet).

Continue reading Pre-Trained Machine Learning Models vs Models Trained from Scratch

Text summarization is a well-known task in natural language processing. In general, summarization refers to presenting data in a concise form, focusing on parts that convey facts and information, while preserving the meaning. To understand this better, we can think of summarization as a process to find a subset of data that contains all the information.

Continue reading Extractive Text Summarization Using Neural Networks