AI for Custom Classification

We benchmark Nyckel against leading AutoML providers using several public datasets. We evaluate performance, training time, latency, throughput, and developer experience.

A machine learning model is only as good as the data it is trained on. At Nyckel, our goal is to give you have the tools to keep your data fresh, correct, and up to date. To this end, we are excited to introduce our newest feature: invoke capture - automatically and intelligently capture important data to improve your model.

Thanks to recent advancements in AI, we’ve seen remarkable quality improvements in AI-generated images. However, these improvements have also led to growing concerns about identifying authentic and trustworthy images. This article explores if we can create an AI image detector with Nyckel image classification.

In this article, we explain how to make object detection – which counts items in images or video frames – more efficient. To do this, we compare two platforms that use different object detection methods: Nyckel and Vertex AI.

One of the first steps before creating a new classification function is to decide whether to use multi-class classification or multi-label classification. In this article, we’ll cover the differences between the two types of classification and help you choose which approach makes the most sense for your problem.

AutoML involves more than just training a model; it should span the entire ML development pipeline. In this post, we explore what features and functionality you should look for in an AutoML platform.

Train a text classification model for content moderation using SurgeAI's toxicity dataset.

IAB is a content taxonomy that is used by content publishers to organize their content in a consistent way. In this post we show you how to classify text and image content into IAB categories without any labeled data.

Search engines continue to get better at understanding what exactly we’re looking for when we search. Today, this also includes when we search image databases. Learn about semantic image search and how companies can use it to support a better user experience.