Because it’s really GOOD.
Indeed, XGBoost, a gradient boosting algorithm, has been consistently employed in the winning solutions in Kaggle competitions involving structured data. XGBoost has excellent precision and adapts well to all types of data and problems, making it the ideal algorithm when performance and speed take precedence.
Continue reading “Introduction to XGBoost with an Implementation in an iOS Application”
From training to experimenting with different parameters, the process of designing neural networks is labor-intensive, challenging, and often cumbersome. But imagine if it was possible to automate this process. That imaginative leap-turned-reality forms the basis of this guide.
We’ll explore a range of research papers that have sought to solve the challenging task of automating neural network design.
In this guide, we assume that the reader has been involved in the process of designing neural networks from scratch using one of the frameworks such as Keras or TensorFlow.
Continue reading “Research Guide for Neural Architecture Search”
Finding old black and white photos and imagining what people, landscapes, and objects looked like in color has probably already crossed the minds of many.
While it is possible to manually colorize black and white photos using image editing and retouching software such as Photoshop, the manipulation, which is only available to insiders and professional image editors, can be time-consuming and tedious.
Continue reading “Colorizing Images in an iOS App Using DeOldify and a Flask API”
Depression is among the most prominent mental illnesses, affecting more than 300 million people globally, according to the World Health Organization (WHO).
Beyond the potentially devastating personal and social effects of depression, the economic costs related to this mental health issue have substantially increased in recent years. In fact, it’s currently estimated to cost the global economy over $1 trillion USD each year.
Continue reading “Predicting Depression from Routine Survey Data using Keras”
Since we founded Fritz AI in late 2017, we’ve seen tremendous growth in the Boston-area tech scene. What was once a city whose tech economy centered on academia, biotech, and robotics, Boston has flourished into one of the most attractive locations for all kinds of tech start-ups, early- and late-stage alike.
Continue reading “Fritz AI Named a 2020 Boston “Startup to Watch” by Built In Boston”
Let’s say you want to make an iOS app that can recognize audio signals in real time, followed by the triggering of an action. From a global point of view, we’d need to explore the crossroads of machine learning and and mobile development.
Continue reading “Building a Sound Classification iOS Application using AI”
Over the past few years, deep learning techniques have dominated computer vision. One of the computer vision application areas where deep learning excels is image classification with Convolutional Neural Networks (CNNs).
Transfer learning, an approach where a model developed for a task is reused as the starting point for a model on a second task, is an important approach in machine learning. Prior knowledge from one domain and task is leveraged into a different domain and task.
Transfer learning, therefore, draws inspiration from human beings, who are capable of transferring and leveraging knowledge from what they have learned in the past for tackling a wide variety of tasks.
Continue reading “Using Transfer Learning and Pre-trained Language Models to Classify Spam”
Computer Vision is one of the hottest research fields within Deep Learning at the moment.
It sits at the intersection of many academic subjects, such as Computer Science (Graphics, Algorithms, Theory, Systems, Architecture), Mathematics (Information Retrieval, Machine Learning), Engineering (Robotics, Speech, NLP, Image Processing), Physics (Optics), Biology (Neuroscience), and Psychology (Cognitive Science).
Continue reading “The 5 Computer Vision Techniques That Will Change How You See The World”
The style transfer is one of the most creative applications of Convolutional Neural Networks. It allows you to retrieve the style of an image and use it to transform any given image.
It is an interesting technique that highlights the capacities and internal representations of neural networks. It can also be useful in certain scientific fields for augmenting or simulating image data.
The almost endless combinations of content and styles possible bring out unique and ever more creative results from neural network enthusiasts.
