Dimitris

Exploring the cutting-edge technologies and applications of AI and their potential to revolutionize industries and improve our daily livesImage generated by Stable Diffusion.The second half of 2022 was full of surprises and exciting moments regarding Artificial Intelligence, Machine Learning, and Deep Learning. Applications like Stable Diffusion and ChatGPT have taken the world by stays, and there’s a good reason for that. They are awe-inspiring pieces of technology. However, in this story, we’ll get a broader view of the…

Are you Bayesian or Frequentist?Image generated using Stable DiffusionRegarding the probability school of thought, there are two main approaches: the Bayesian and the frequentist approaches. Both of these approaches have their own strengths and weaknesses, and they are often used in different circumstances to help determine the probability of events.So, what are their differences? Is one better than the other? This is a wrong question to ask; Bayesian thinking is based on the idea that probabilities represent a degree of…

Enhance the quality of your slow-motion videos using Deep Learning and Video Frame Interpolation in 5 minutesA camera painted by Claude Monet — Image generated by Stable DiffusionWe can all agree that slow-motion videos create this dramatic effect, which certainly adds an extra flavor to specific scenes. On the other hand, slowing down a video might create several unwanted artifacts, which could deem it unwatchable. But what makes a slow-motion video great?Let’s use Deep Learning to produce the smooth result of a high-end…

Omnipresence, tools to keep you in the zone, and education were the main themes for Project Jupyter in 2022A programmer writing code on Jupiter — Image generated by Stable DiffusionJupyter notebooks are great for software development and documentation. They are widely used in the world of data science and Machine Learning (ML), and it's an ideal tool to use if you want to experiment with new algorithms, analyze and get familiar with your datasets, and create quick sketches of new approaches.Almost two years ago,…

How to use Stable Diffusion to create realistic images and art from a description in natural languageA robot with a painter's hat painting a picture of a mountain on a white canvas. Digital art. — Image generated by Stable DiffusionAs a kid, I always admired people that could draw whatever came to their mind. I could watch them for hours as they would give shape to seemingly arbitrary lines on paper. Unfortunately, I was not blessed with that gift.Time went by, and today AI can help me materialize the ideas I have in my…

How to transfer your machine learning code and its dependencies to your production environment.Packaging your ML model — Image created with Stable DiffusionJane works as a Machine Learning (ML) engineer at an accomplished startup. They are about to release the first version of their product, which relies heavily on the performance of the ML algorithm she is working on. After several iterations, the model she’s trained performs reasonably well on a held-out test set, and she is ready to take the next step.First, she…

Maintaining an inference server is distressing but necessary.Photo by Vadim Bogulov on UnsplashThis article continues a series of articles tackling the most frightening idea in the world of production ML: putting the damn thing in production.In previous stories, we saw two different approaches to designing a Machine Learning (ML) powered application. First, we examined why you’d want to keep your model within your web server and why you should not do it.Keeping your model side-by-side with your core business logic is a…

When to place your model in your database, how to do it, and whyPhoto by benjamin lehman on UnsplashIn the previous article, we saw one excellent reason you'd want to use tools like Streamlit and Gradio to deploy fast and deploy many versions of your Machine Learning (ML) application.We saw the advantages of the model-in-server architecture and why you'd definitely want to go down this road when you're prototyping. This is the easiest way to get quick feedback from a private circle of trusted testers and evaluate the…

What it takes to turn a promising ML model into a useful ML-powered productPhoto by Andre Taissin on UnsplashDeploying your Machine Learning (ML) models is never a job to take lightly. Sure, some great tools can help you share your models with the world quickly, like Gradio and Streamlit, but if we're talking about anything more than a proof of concept, you have some decisions to make!Gradio and Streamlit are great at what they do but provide limited frontend flexibility. There is only so much you can do, and the frontend…