Lessons learnt when doing a challenge I thought I didn’t need (but I needed it very much) — I started my journey in the cloud in November 2020, at the time I had experience with Python, git, Docker, Lambda and S3 from AWS, nothing about Azure and nothing about GCP. The first thing I did was take the ⭐️ AWS Cloud Practitioner Certification, which covers the basics of…

Find out about the main Azure services to build language, vision and search AI apps — It can be a daunting task to navigate cloud providers finding how to build your AI app in the cloud. This post goes over the main Azure AI resources for different AI applications. Vision 1. Computer vision Computer Vision is the main Azure resource for image applications. In its most basic form, it supports…

Azure services to bring your machine learning project to the cloud — It is becoming increasingly difficult to do data science in your own computer nowadays. Sure, normal computers have no problem to handle data exploration, analysis and visualization. But when it comes to model training, unless you own a GPU or you are using a classical machine learning model and not…

Create a system in order to be up to date with deep learning research — Deep learning is moving so fast, that the only way to keep up is by reading directly from the people who publish these new findings. If you’re a technical person and want to learn about deep learning in 2021, you need to read papers. Formal education will only get you…

Given similar sentences, how similar are their contextual embeddings? Let’s find out — Embeddings are a key part of modern NLP, they encode the meaning of words or other linguistic units into vectors of numbers. The embedding of a specific word might seem random, but the idea is that similar words have similar embeddings, and opposite words have opposite embeddings. For example, imagine…

Introduction to tokenization methods, including subword, BPE, WordPiece and SentencePiece — This article is an overview of tokenization algorithms, ranging from word level, character level and subword level tokenization, with emphasis on BPE, Unigram LM, WordPiece and SentencePiece. It is meant to be readable by both experts and beginners alike. …