22 Dec 2019 · 13 mins read
An introduction to machine learning through polynomial regression
Machine learning is one of the hottest topics in computer science today. And not without a reason: it has helped us do things that couldn’t be done before like image classification, image generation and natural language processing. But all of it boils down to a really simple concept: you give the computer data and the computer then finds patterns in that data. This is called “learning” or “training”, depending on your point of view. These learnt patterns can be extrapolated to make predictions. How? That’s what we are looking at today.
20 Dec 2019 · Published on Heartbeat
Deploying Core ML models using Vapor
Core ML is Apple’s framework for machine learning. With Core ML, everyone can use machine learning in their apps—as long as that app runs on an Apple platform, and Apple platforms only. Core ML cannot be used with Android, Windows, or on websites. This is very unfortunate because Core ML is such a great piece of technology.
06 Dec 2019 · 13 mins read
An introduction to Generative Adversarial Networks (in Swift for TensorFlow)
Generative adversarial networks, or GANS, are one of the most interesting ideas in deep learning. Using GANs computers get a sense of imagination, they can create their own “things”. But how do they do that? It’s easy to have a computer generate random data, but that’s of low value to us, humans. How does a computer generate something that looks like items in the dataset?
04 Dec 2019 · Published on Heartbeat
An Empirical Comparison of Optimizers for Machine Learning Models
At every point in time during training, a neural network has a certain loss, or error, calculated using a cost function (also referred to as a loss function). This function indicates how ‘wrong’ the network (parameters) is based on the training or validation data. Optimally, the loss would be as low as possible. Unfortunately, cost functions are nonconvex — they don’t just have one minimum, but many, many local minima.
03 Dec 2019 · 11 mins read
Your first Swift for TensorFlow model
Swift for TensorFlow is TensorFlow, implemented in Swift. Its Python counterpart (“TensorFlow”) is one of the best deep learning libraries ever made, but it’s hitting its limits. Python, being interpreted, is quite a slow language. Python is also limiting in many other ways, it lacks features that could make your life, as a programmer, much easier.
14 Nov 2019 · Published on Heartbeat
Benchmarking deep learning activation functions on MNIST
Over the years, many activation functions have been introduced by various machine learning researchers. And with so many different activation functions to choose from, aspiring machine learning practitioners might not be able to see the forest for the trees. Although this range of options allows practitioners to train more accurate networks, it also makes it harder to know which one to use.
13 Oct 2019 · Published on Heartbeat
Building a Barcode Scanner in Swift
Barcodes are everywhere. They provide a uniform interface for machines to identify real world items. Thanks to the decimal code underneath the bars, barcodes are also interpretable by humans, which makes them wildly used virtually everywhere.
13 Aug 2019 · 5 mins read
Linear Regression in Swift with Tensorflow
Swift is a new programming language introduced by Apple in 2014. Despite being so young compared to other languages, it is already widely used in industry. It is mostly used to develop apps for Apple’s platforms. Recently however, after Apple making Swift open source, Swift was ported to linux and now Google is taking an interest in Swift by writing large parts of its deep learning library, TensorFlow, in Swift.
12 Aug 2019 · 3 mins read
Working in machine learning includes dealing with poorly labelled datasets. Very few companies can afford hiring people to label the huge amounts of data required for large scale projects. Luckily, high quality datasets are available for practise projects. In production however, one will most likely need a custom dataset. With applications such as BeautifulSoup and Scrapy it’s easy to collect large amounts of data from the internet. Labelling the data is a common pain-point. Luckily there are other solutions available than annotating the data yourself or hiring people to do it for you. Label smoothing is a mathematical technique that...
08 Aug 2019 · 4 mins read
Numpy vs PyTorch for Linear Algebra
Numpy is one of the most popular linear algebra libraries right now. There’s also PyTorch - an open source deep learning framework developed by Facebook Research. While the latter is best known for its machine learning capabilities, it can also be used for linear algebra, just like Numpy.
07 Aug 2019 · 7 mins read
GANs for Watermark Removal
Generative Adversarial Networks, or GANs, are a new machine learning technique developed by Goodfellow et al. (2014). GANs are generally known as networks that generate new things like images, videos, text, music or nealry any other form of media. This is not the only application of GANs, however. GANs can be used for image reconstruction as well as you’ll see in this post where we’re building a watermark remover tool.
28 Jul 2019 · 5 mins read
Introduction to natural language processing in Swift
As computers get smarter, the communication between machines and humans becomes more of a bottleneck. While humans are socially smarter, computers have surpassed us in many ways in areas like math and science. Perhaps the most important side of this bottleneck is communicating emotions. Although emotions are a fundamental part of human communications, computers often fail to comprehend. Luckily, there are people who are researching ways to use machine learning techniques to help computers understand humans emotions.
23 Jul 2019 · 6 mins read
Compressing images using Python
Compressing images is a neat way to shrink the size of an image while maintaining the resolution. In this tutorial we’re building an image compressor using Python, Numpy and Pillow. We’ll be using machine learning, the unsupervised K-means algorithm to be precise.
10 Jul 2019 · 4 mins read
For my WWDC Scholarship submission I used a custom machine learning model that I trained using CreateML. In this blogpost I will be explaining how I went from binary data to a state of the art machine learning model.
10 Jul 2019 · 9 mins read
On April 16th, 2019 an email landed in my inbox. The subject line read: “You’ve been awarded a WWDC19 Scholarship.” What?! Because this was my first time taking part in a programming competition, I didn’t expect to win at all.