Better than humans? You decide. — Artificial intelligence is getting good at making art. Like, real good. Most people don’t realize that it’s already significantly better than humans in most respects. Of course, you probably don’t believe me. But that’s the thing about AI — it has a funny way of being in your rear view…

What’s an AI art generator? It is a tool that creates any artwork with the assistance of Artificial Intelligence. The process uses a neural network and a series of algorithms that is trained with pre-existing dataset from real human artworks to come up with something unique and quite frankly amazing results. In this article, I…

Using the CLIP and VQGAN models to generate ChromaScapes, high-quality digital paintings for sale as NFTs on OpenSea — I first wrote about using Generative Adversarial Networks (GANs) to create visual art in August of 2020. For that project, MachineRay, I trained NVidia’s StyleGAN2 [1] with abstract paintings in the public domain to create new works. Since then, I have written a few more articles on using GANs to…

Learn to use Python to extract text from PDFs — In this blog, we are going to examine the most popular libraries for processing PDFs with Python. A lot of information is shared in the form of PDF, and often we need to extract some details for further processing. To assist it in my research in identifying the most popular…

A minimalistic neural network implementation which can be trained on the CPU — Offline Handwritten Text Recognition (HTR) systems transcribe text contained in scanned images into digital text, an example is shown in Fig. 1. We will build a Neural Network (NN) which is trained on word-images from the IAM dataset. As the input layer (and therefore also all the other layers) can…

A legitimate means of leveraging your python to profit — Introduction: After learning Python to a reasonable level of fluency, I have tried to leverage my knowledge and skills for financial benefit. After trying my hand at methods like automated stock trading, I have found that many methods are too inconsistent, and could result in massive losses. After some research, I…

A detailed, step-by-step write-up on how I built Text2Art.com — Overview This article is a write-up on how I built Text2Art.com in a week. Text2Art is an AI-powered art generator based on VQGAN+CLIP that can generate all kinds of art such as pixel art, drawing, and painting from just text input. The article follows my thought process from experimenting with VQGAN+CLIP…

A playbook to learn the essentials behind deep learning focused on convolutional neural networks — I recently taught a mini-course on Machine Learning 101 for those who want to become data scientists. One of its modules was about Deep Learning. I found that many newbies are confused with this topic mostly because it is often taught with many complexities. In this article, I aim to…

Results of using Facebook Prophet to trade cryptocurrencies — In the world of cryptocurrency, everyone is looking to make money. Either through mining, trading, or something else entirely. For me, I wanted to see if money could be made through trading. However, not just trading alone, but trading with machine learning! Using machine learning to predict market prices is…

Smaller players can now enter the game of large AI models — I can confidently say artificial intelligence is advancing fast when a neural network 50 times larger than another can be trained at a 100 times less energy cost — with just one year in between! On June 25, Alibaba DAMO Academy (the R&D branch of Alibaba) announced they had built…

What could an environmentally-friendly AI look like in the future? — Disclaimer: This is an opinion piece, and the opinions expressed here only belong to the author. You’re probably asking, “Raveena, just what exactly do you mean by a Green AI?” Well, I guess I did reveal my intention in the italic summary above, but that doesn’t exactly give us a…

How to build a scientific discovery engine in 3 easy steps — Introduction In this article, I demonstrate how to build a simple automated scientific discovery engine. Check the demo out. The current scientific practice is bounded by our cognitive and sociological limitations. Machines are faster, more efficient, and more durable than we are. Most importantly, machines are free from human bias. …

Four key takeaways from the fireside chat with two leading AI experts at the intersection of data science and healthcare — DeepLearning.AI and Stanford HAI recently organized a virtual fireside chat with two of the world’s most eminent computer scientists — Andrew Ng and Fei-Fei Li. Driven by a strong belief in healthcare’s social mission and importance to humanity, they have focused their efforts and expertise on the healthcare industry in…

Introduction If you are new to NFT, please read the below articles to understand it. What is NFT? | Make money using NFT + AI Getting started with Opensea. Reduce the gas cost Create art images using AI. Feature Optimization Create different images within AI. Use GAN’s for image creation In…

How recent neuroscience research points the way towards defeating adversarial examples and achieving a more resilient, consistent and flexible form of artificial intelligence —

Introduction By now, you would have at least heard about NFT. If not, you would have heard about art which sold for $69 million. May be at-least record sales on NBA and with NFT. This got me curious, I started to research more on it recently by wearing my Data Scientist…

Introduction If you are new to NFT, please read these articles to understand it. This article will discuss how to create a unique type of art that can be minted. I will go over the basic to advanced version to generate art. …

Do you want to know how to create NFT art, but don’t know where to start? It’s easier than you think! Collaborate with artificial intelligence to create amazing art you can sell as NFTs. NFTs are booming, with many digital artworks selling for millions of dollars. In this article, we’ll…

A Self-Contained Introduction — Spatial Transformer modules, introduced by Max Jaderberg et al., are a popular way to increase spatial invariance of a model against spatial transformations such as translation, scaling, rotation, cropping, as well as non-rigid deformations. They can be inserted into existing convolutional architectures: either immediately following the input or in deeper…