Our report on using AI to predict the riskiness of public procurement calls based on their text is available on tenders.guru
(more…)Using AI to Predict Risk in Public Procurement
Tag: Python
Software engineering for data scientists – Part 1, Development Tools
I have bad news; being able to write programs is only a tiny fraction of software development and data science. You have to know a lot of things and this can become very frustrating. You will be bombarded with acronyms and silly-named tools, like IDE, git, version control, CI, etc, etc. At some point, you have to start use the tools of the trade along with coding and here we give you some advice on what to use to become a pro.
(more…)A simple Markov chain text generator in Python
What does it mean to build a language model? How it is related to the Beat Generation’s cut-up technique and can be used for text generation? We’ll shed light on these questions using Python!
(more…)Order emerging from randomness or the joy of random Boolean networks and Python
Boolean networks are widely used in computational biology to model gene regulatory networks, and they can be very useful in time-series analysis too. Here, we will use the concept of random Boolean networks to generate interesting images which show some sort of repetitive patterns. Let complexity meet generative art and Python!
(more…)Getting Started with Colab Using TensorFlow is freely available on Manning LP
We developed a free course for Manning liveProject. Getting Started with Google Colab Using TensorFlow has got a very descriptive title, so it teaches you the very basics of using Colab with TensorFlow.
(more…)Getting Started with Colab Using PyTorch is freely available on Manning LP
We developed a free course for Manning liveProject. Getting Started with Google Colab Using PyTorch has got a very descriptive title, so it teaches you the very basics of using Colab with PyTorch.
(more…)Getting Started with Jupyter is freely available on Manning liveProject
We’ve been working hard on our newest liveProject, Getting Started with Jupyter Notebook during the last few months and now it is freely available!
(more…)Content Analysis with Similarity Graphs
We had the opportunity to present our thoughts on content analysis with similarity graphs at the Graph Data Science conference. Below, you can watch our presentation and other useful materials to get started with similarity graphs.
(more…)Graph Theory and Network Science for Natural Language Processing – Part 4, TextGraphs & Graph Neural Networks
We close our series on Graph Theory and Network Science for NLP with an overview of the recent developments in the field. It means deep learning enters the scene – finally.
(more…)How Jina Saves Your Time on Building Cloud-Native Neural Search Systems
Today, with the ever more long documents and multimedia data, finding the right information is more important and challenging than ever. The rise of deep learning has ushered in a new era of “neural search”. However, building a neural search system is non-trivial work for many engineers. The main challenges are: (1) long dev cycle due to the complex tech stack (2) poor scalability due to the glued-architecture (3) strong requirements on the domain knowledge to fine-tune the results. With Jina (https://github.com/jina-ai/jina), engineers can quickly build up a search engine powered by state-of-the-art AI in just minutes. In this talk, I will introduce the design philosophy and the key features of Jina; and showcase how Jina bootstraps a QA semantic search system and a short-video search system in just lines of code.
(more…)