Articles about Tutorials

Building applications sometimes can be a bit challenging, especially when we need to build a fast and good-quality application. These times it can be necessary, especially when search engines can give bonus SEO points for faster working apps, and it can help us to reduce our bouncing rate very strongly. To help you with that, I’ve created a few hints and tips which you could use to make your app very fast.

You can download pdf version here. Intro to machine learning interview questions Machine learning (ML) is a rising field. It offers many interesting and well-paid jobs and opportunities. To start working in machine learning, you should become familiar with: mathematical fundamentals — linear algebra, calculus, optimization, probability, and statistics, etc., machine learning fundamentals — prepare data, validate and improve results, interpret results, recognize and avoid overfitting, etc.,

Recently, a lot of people ask what they should learn to become a front-end developer. How to learn front-end while there are so many things to learn, everything changes so fast, new technologies, new popular libraries almost once a year. When you start reading articles and news about it, you can feel lost. All these technologies React, Angular, Vue.js, jQuery, Javascript, even Bootstrap are popping up everywhere. And at this point, you probably wonder how and where to start and finally become good at it.

Natural language processing (NLP) is one of the most promising fields of artificial intelligence that uses natural languages to enable human interactions with machines. There are two main approaches to NLP: – rule-based methods, – statistical methods, i.e., methods related to machine learning. There are several exciting Python libraries for NLP, such as Natural Language Toolkit (NLTK), spaCy, TextBlob, etc. A chatbot is a computer software able to interact with humans using a natural language.

Image recognition is one of the most widespread machine learning classes of problems. It aims at training machines to recognize images similarly as people do. Image recognition belongs to the group of supervised learning problems, i.e., classification problems, to be more precise. This article presents a relatively simple approach of training a neural network to recognize digits. This approach uses an ordinary feedforward neural network. The accuracy of the model can be further improved using other techniques.