Author: Fritz

In part 1, I introduced the field of Natural Language Processing (NLP) and the deep learning movement that’s powered it. I also walked you through 3 critical concepts in NLP: text embeddings (vector representations of strings), machine translation (using neural networks to translate languages), and dialogue & conversation (tech that can hold conversations with humans in real time). In part 2, I’ll cover 4 other important NLP techniques that you should pay attention to in order to keep up with the fast growing pace of this research field.

Continue reading The 7 NLP Techniques That Will Change How You Communicate in the Future (Part II)

Flutter has a rich pool of packages and widgets. You can achieve most things by either using the rich widget pool that Flutter offers or by using a package.

However, sometimes you might find yourself in situations that demand you write native Java code*.

In this fourth installment of our Flutter series, we’ll look at how you can write Java code that communicates with your Flutter application.

Continue reading Writing Native Java Code in Flutter for Android

Tree-based machine learning methods are among the most commonly used supervised learning methods. They are constructed by two entities; branches and nodes. Tree-based ML methods are built by recursively splitting a training sample, using different features from a dataset at each node that splits the data most effectively. The splitting is based on learning simple decision rules inferred from the training data.

Continue reading Understanding Tree-Based Machine Learning Methods

I’ve recently been working a lot with video data—in fact, I’d already shared some learnings on a few deep learning-based video summarization techniques, in a recent article published on Heartbeat.

While I searched a lot for research papers that dealt with video summarization, I came across a paper that dealt with creating these summaries in the simplest way possible—by using the subtitles of a given video. You can check out the paper here.

Continue reading Video Summarization Using Subtitles: A Simplified Approach

I’d been interested in the idea of learning machine learning for quite a while. This interest in the field started after I discovered ML as being a subfield of AI from an online forum. My understanding of AI before this was limited to what I watched in sci-fi movies, where AI is portrayed as an artificial human that could outperform real humans in intelligence, which I didn’t find interesting.

Continue reading Why I thought machine learning was boring

There were quite a few interesting announcements during WWDC 2020. Without a doubt, enhancements in SwiftUI 2.0 and Apple’s bold decision to move away from Intel for Mac in favor of in-house Silicon chips became the major talking points.

But that didn’t stop Apple from showcasing its computer vision ambitions once again this year. The Vision framework has been enhanced with some exciting new updates for iOS 14.

Continue reading What’s New in the Vision Framework in iOS 14

If you’ve read my earlier blogs centered on AutoML and machine learning on edge devices, you know how easy it is to train and test a custom ML model with little to no prerequisite knowledge.

However, just training an ML model isn’t enough. You also need to know how to use them to make predictions. Maybe you need to build a cross-platform app using tools like QT, or maybe you want to host your model on a server to serve requests via an API. This third blog in the series on training and running Tensorflow models in a Python environment covers just that!

Continue reading Using Google Cloud AutoML Edge Image Classification Models in Python

Note: The original research report on which this post is based can be found here

If you’re one of those people with a large number of GPU compute nodes in your basement, or if you work for Google, training neural networks in a short time for challenging tasks is probably easy for you.

Continue reading The Mobile Neural Network Lottery

K-Nearest Neighbors (KNN) is a supervised learning algorithm used for both regression and classification. Its operation can be compared to the following analogy:

To make a prediction, the KNN algorithm doesn’t calculate a predictive model from a training dataset like in logistic or linear regression. Indeed, KNN doesn’t need to build a predictive model. Thus, for KNN, there is no actual learning phase. That’s why it’s usually categorized as a lazy learning method.

Continue reading Understand the Fundamentals of the K-Nearest Neighbors (KNN) Algorithm