ai – AI Tools
Recently, we tend to use chat language models more and more in our everyday activities. If you are a traditional office worker, using it through web chat interface or co-pilot seems natural. However, for developers, who spend a lot of their time on the command line, having terminal interface for chat models is totally useful. Read More ›
art – Art of the Artificial
Recently, there have been a lot of debates on whether generative AI can be creative, and whether its creations can be considered art. In this regard, I want to share our experience of working together with AI to create works of art for an exhibition. Read More ›
ai – Recipe
Large language models handle conversations on general topics perfectly, but often it is necessary to add some domain knowledge to a chatbot. Let's see how to use the Retrieval-Augmented Generation approach to create such a chatbot based on the LangChain framework and the Yandex GPT generative model Read More ›
ai – AI in Prose
March 15th was a big day for a humankind - GPT-4 was released. New family of neurogenerative tools for both text and images offer us unprecedented productivity when putting our ideas to life. Here is a short story we wrote together with ChatGPT, illustrated by Stable Diffusion Read More ›
ai – Why Eating Cucumbers in the Evening Leads to Sleeping Disorders
With the ChatGPT model being currently publicly available, many people start using it, and some believe that it can be used instead of Google to find the answers to their questions. Here I will explain why a neural network model should not be trusted. Read More ›
tech – Fediverse or Metaverse, that is the question.
With the latest changes happening to twitter, many of my friends are moving towards more decentralized social communications, and in particular social network called Mastodon Read More ›
scienceart – Some thoughts about AI Art
Latest text-to-image models can generate stunning images based on text prompts, both photorealistic and artistic, stylized under many existing artists. In this post, I show some examples, and try to speculate on the influence this can have on the way we enjoy art Read More ›
education –
As human beings, we know how a cat looks like. But what about neural networks? In this post, we will reveal how a cat looks like inside a neural network brain, and also talk about adversarial attacks. Read More ›
education –
Summer is coming, and it is a great time to do some out-of-class learning! I am proud to announce the release of AI for Beginners Curriculum, on which my colleagues and I have been working for the last several months. Read More ›
education –
Did you always wish that you could read one short article and understand how neural networks work? Here is my attempt at writing such an article... Read More ›
scienceart – Science Art
Most of us probably have a huge collection of photographs lying around, and not enough time to watch them all. Using Cognitive Portrait technique, we can use our photo collection to automatically create beautiful digital christmas presents for our friends and family! Read More ›
education –
New year is coming! We are working hard to release brand new AI for Beginners Curriculum by the New Year, so that you can start off your 2022 by learning something new! Read More ›
education –
Jupyter Notebooks are quickly becoming de facto standard for sharing code in AI, ML and Data Science. They are also extremely effective tool in education, allowing authors to mix text content with executable code. In this post, I will cover different ways to run Jupyter Notebooks that you come across, without a need to install complete Python environment on your machine. Read More ›
education – Education
Deep Learning is one of the most popular topics amongst both students and software developers. We have recently released a learning path on Microsoft Learn that will help you get started with Deep Learning, based on one of the most popular frameworks: PyTorch. Read More ›
science – Science
GitHub is well-known as a platform where software developers host their code and collaborate with their teams on a project. In this article, we'll show you how you can use the GitHub model to do the same thing and collaborate seamlessly on your research papers. Read More ›
science – Science
Since the beginning of COVID pandemic more than a year ago, there have been more than 400000 scientific papers published on the subject. A human researcher cannot possibly get acquainted with such a huge text corpus - and therefore some help from AI is highly needed. In this post, we will show how we can extract some knowledge from scientific papers, gain insights, and build a tool to help researcher navigate the paper collection in a meaningful way. Read More ›
azure – Conversational AI on Microsoft Platform
During the pandemic, we all found ourselves in isolation, and relying more and more on effective electronic means of communication. The amount of digital conversations increased dramatically, and we need to rely on bots to help us handle some of those conversations. In this blog post, I give brief overview of conversational AI on Microsoft platform and show you how to build a simple educational bot to help students learn. Read More ›
Azure – Azure
Unlike theoretical data science, applied data science involves additional steps to manage the lifetime of a model, which are commonly called MLOps. Azure Machine Learning is a service that conveniently supports MLOps practices, so getting to know it seems like a good idea. In this post, I will talk about the best way to learn (Udacity), and to demonstrate your knowledge (Certification). Read More ›
azure – Azure
It is estimated that a Data Scientist spends about 80% of her time on data preparation, and not on the model training. If your training setup is just a GPU virtual machine in the cloud - it means that you are spending 80% of its uptime in vain, because GPU is not utilized. For more cost-effective way we may want to split the work between two virtual machines, one for data preparation, and another one for actual training. This is exactly the setup I used for some time when working in Microsoft CSE, before switching to AzureML, so I will share my knowledge here. Read More ›
science – Science
One of the main characteristics of an epidemic is the effective reproduction number (Rt), which indicates the number of people each infected individual will further infect at any given time. Being able to estimate Rt is an important task, because this number defines whether the epidemic is expected to grow (Rt>1), or will start declining (Rt<1). In this post, I suggest sliding SIR method of estimation of Rt based on fitting SIR epidemic model to the infections data in different countries. Read More ›
azure – News
Data Science is one of the most demanding and most popular areas of computer science. One might assume that a data scientist need to know Python and programming in general to be successful. While this might be true to a certain extent, in this post we discuss whether Data Science is possible without programming, and how to start learning if you are not a programmer. TL;DR: Microsoft and Udacity just announced a collaboration that will help you with that! Read More ›
azure – Tutorial
In the field of image-related deep learning, Keras library plays an important role, radically simplifying such tasks as transfer learning or using pre-trained models. If you switch to the area of NLP, to perform relatively complex task such as question answering or intent classification, you would need to put several models at work together. In this post, I describe DeepPavlov library that democratizes NLP, and how to use it with Azure ML to train question answering network on COVID dataset. Read More ›
scienceart – Tutorial
As you may know, I am a big fan of Science Art. This January, Moscow ElectroMuseum made an open call for Open Museum 2020 Exhibition. In this post, I will describe the exhibit that I made, and how it was transformed due to quarantine and museum closing. Read More ›
scienceart –
Generative Adversarial Network can produce a lot of original paintings much much faster than human painter. But does it make AI creative? Let's discuss the nature of creativity, and try to challenge Artificial Intelligence on this front. Read More ›
scienceart –
Deep Learning can look like Magic! I get the most magical feeling when watching neural network doing something creative, for example learning to produce paintings like an artist. Technology behind this is called Generative Adversarial Networks, and in this post we will look at how to train such a network on Azure Machine Learning Service. Read More ›
education –
During the times of social distancing, online education becomes extremely important. I worked for more that 10 years in evangelism and content development, and I want to share with you some secrets on creating engaging online content at home using PowerPoint. Read More ›
azure –
Most machine learning models are quite complex, containing a number of so-called hyperparameters, such as layers in a neural network, number of neurons in the hidden layers, or dropout rate. To build the best model, we need to chose the combination of those hyperparameters that works best. This process is typically quite tedious and resource-consuming, but Azure Machine Learning can make it much simpler. Read More ›
azure –
I know many data scientists, including myself, who do most of their work on a GPU-enabled machine, either locally or in the cloud, through Jupyter Notebooks or some Python IDE. On the other hand, there is a specific service called Azure ML, made for Machine Learning in the cloud. Many people have heard about it, but most of them think that it is only suitable for large-scale tasks. I can assure you that it is not the case! I have recently learned how to start your journey towards Azure ML painlessly, and will share my experience. Read More ›
scienceart –
I am quite passionate about using anything cross-disciplinary, and in particular Science Art. This time I will explore using Cognitive Science and AI in creation of beautiful blended portraits from a series of photographs. Read More ›
azure –
Azure Notebooks are essentially a Jupyter running in the cloud, and even more. Whether you know what Jupyter is or not, read this post to discover a few useful scenarious for Azure Notebooks in your life. Read More ›