A Primer on Text Classification with PyTorch
If you were given a single line from a movie, would you be able to identify the gender of the character who delivered the line? Unless you’ve memorized a lot of movie scripts, probably not. Lucky for you, you don’t have to do this as long as we have computers! The field of Natural Language Processing (NLP) has us covered. By applying Deep Learning to NLP and creating a text classifier we can train a computer to identify whether a line from a movie was delivered by a male or female character!
For my final project for an Advanced Java course I was taking at school, I decided to combine my interest in Machine Learning with Java and make a Natural Language Processing project. One of the most basic Natural Language Processing projects is analyzing the sentiment analysis of tweets on Twitter. So naturally, I went about attempting to analyze the sentiments of tweets with the words “USA Coronavirus Response.”
As a programmer, you probably have a love-hate relationship with your craft. There are times that you love programming and there are other times that you just don’t want to write
print("Hello World"). However, you probably always want to get your work done and make it as enjoyable as possible, and using some productivity apps can have that exact effect. I’ve been using all of the tools I list in here for at least a month now and I love each and every single one of them. They’ve made working a lot more fun for me and have definitely allowed…
If you’ve read an Introduction to Competitive Programming, then you’re probably familiar with why Competitive Programming is important. For those of you who haven’t, I believe that Competitive Programming is important because it helps you build your problem-solving skills and your technical knowledge of data structures and algorithms.
One of the biggest parts of Competitive Programming is learning the algorithms you need to succeed. I’ll be covering a large number of those algorithms in this post, specifically all the graph algorithms you’ll need to be successful in solving graph problems in Competitive Programming contests. Of course, just knowing the algorithms…
Competitive programming is an art form. It’s creative problem-solving at its finest, a combination of hard analytical thinking and creativity.
Competitive programmers use their knowledge of algorithms and data structures and logical reasoning skills to solve challenging algorithmic problems in a limited time frame.
Java and C++ are extremely popular due to their relative run-time efficiency compared to a language like Python. C++ is my preferred competitive programming language, as I love its Standard Template Library (STL) which allows for quick write ups of solutions.
Without further ado, lets get right into it.
I know most people might not want…
Cybersecurity is important, there’s no dodging that fact. It is also nothing like the hacking that is shown in most popular media.
However, that does not mean it isn’t interesting, it is undoubtedly so. Due to this intrigue, lots of people want to dip their feet into cybersecurity, myself included, and I have found capture the flag events (CTFs) to be a wonderful way to get a taste of the field.
Now, by no means are CTFs completely accurate in the day-to-day work of a cybersecurity professional but they are very educational and they do help people develop their cybersecurity…
In this article, I’ll be explaining how to use an API to build a cross-platform mobile app that uses a neural network to classify images. I will be using the model I built in one of my previous articles, but this tutorial will work with any single-label image classification model.
There are two components to this app; one is the API we create which will also serve as a web app, and the other is the Flutter mobile app itself. So let’s get straight to it.
Machine Learning is wonderful, but people need to stop selling it as the solution to everything.
First of all, what is Machine Learning?
It is the field of study that gives computers the ability to learn without being explicitly programmed using statistical models.
Machine Learning presents exciting opportunities and amazing solutions to problems we didn’t even know we had. However, it can’t solve everything, and should not be applied everywhere.
I’ve had friends ask me to make them a model that will fill out a perfect March Madness bracket 100% of the time. Now, this isn’t impossible to do for…
I’ve recently delved into the world of deep learning; more specifically, image classification.
After completing the first lecture in the fast.ai MOOC, I decided to play around a little with their library. This led me to make a model that could classify different types of cricket shots.
Try it out at Classify Cricket Shots. The model is not perfect, but it does have an accuracy rate of 96%.