The History of AI (part 2)

History of AI

In the second part of a series of articles about the history of artificial intelligence, we look at important published papers in the history of AI and the concept introduced in them.

Projects Basics in AIEX Platform

Projects Basics in AIEX Platform

In this paper, we cover the basics of projects. We describe the different types of projects, how to create new projects from existing ones, how to import and export projects, how to use tags and descriptions, and provide some best practices.

Organizations, Members & Access Level Management on the AIEX Platform

Organizations, Members & Access Level Management on the AIEX Platform

Training a highly accurate computer vision model requires many carefully annotated images. Data gathering and annotation take time and might often prove to be hard. As the saying goes, nothing is particularly hard if you divide it into small jobs (and assign it to a team of people). This chapter details the teamwork tools implemented on the AIEX deep learning platform. An overview of organizations, projects, workgroups, and some of the best practices will be outlined in this paper.

Dataset Development Lifecycle

Dataset-Development-Lifecycle copy

Google has come up with a framework for data collection inspired by software development concepts in a 5-step cyclical process. In this article, we will examine google’s proposed data collection framework.

Attention Mechanism: from NLP to Computer Vision

From NLP to Computer Vision

In this article, we discuss the Attention mechanism and trace its history of use from natural language processing to computer vision. And finally, we will examine transformers and their application in computer vision.

Annotating Computer Vision Projects

Choosing the right images for training, validating, and testing computer vision algorithms will significantly affect your AI project’s success. To train an AI model for object detection, segmentation, and classification with human-like performance, each image in the dataset must be labeled thoughtfully and accurately. This article examines dataset annotation and labeling techniques.

What Is Data Augmentation ?


To train a model or use transfer learning in machine vision, there must be enough data. Data Augmentation is a very important step that helps us increase our training data. The purpose of this article is to examine this feature and to review the techniques used to increase data on the AIEX platform.

Train, Test, and Validation Datasets

An artificial intelligence model output is affected by how we divide the input dataset. There are several factors to consider when choosing a data partitioning method. In this article, we will examine the types and uses of these divisions.