Renumics has its information security concept assessed with TISAX

Renumics has its information security concept assessed with TISAX (Trusted Information Security Assessment Exchange)

Explaining LLMs for RAG and Summarization

Learn how to explain LLM outputs in RAG and summarization tasks using a simple similarity-based attribution method.

Reranking using Huggingface Transformers for Optimizing Retrieval in RAG Pipelines

Learn how to improve your RAG pipelines using reranking models from Huggingface Transformers.

How To Fine-Tune The Audio Spectrogram Transformer On Your Own Data

AI assistants can help test engineers to save valuable time. These 5 use cases illustrate how.

Top 15 data analysis tools for test engineers in 2024

There is a myriad of testing data analysis tools out there. Here are 15 tools you should know.

Automotive Testing: Automatic AI based Test Data Evaluation

An Example on Formula 1 Telemetry Data: Unsupervised AI for Time Series Preprocessing

Top 5 Use Cases for AI in Automotive Testing Data Analysis

AI assistants can help test engineers to save valuable time. These 5 use cases illustrate how.

How to build RAG-based assistants for industrial applications

Retrieval augmented generation (RAG) can augment the knowledge of machine operators, allow for deeper insights into customer needs and enhance the collaboration of engineering teams. It has has emerged as the de-facto standard for building such applications-specific assistants.

Interactive Visualization for Hugging Face Datasets

Hugging Face is the Github for AI. The platform helps you do discover new models and datasets. Now you can interactively inspect your Hugging Face datasets with just one line of code.

Join us for Hacktoberfest 2023

We’re thrilled to announce that Renumics Spotlight is joining the Hacktoberfest 2023. Every accepted Hacktoberfest PR not only elevates your skills and contributions to the open-source community but also earns you a limited-edition Renumics T-Shirt!

Hands-On Voice Analytics with Transformers

Voice analytics helps to build more sympathetic and more robust ML-based assistants. We show how to leverage open source tooling to effectively use pre-trained transformer models for this use case.

Interactive Data Insights Made Simple: Visualize with Just One Line of Code

Explore interactive data visualization with Spotlight. Dive into the wine dataset and uncover insights with our Open Source Tool.

Finding data slices in unstructured data

Data slices are semantically meaningful subsets of the data, where the model performs anomalously. We discuss current challenges and demonstrate hands-on examples of opens source tooling.

Changes of Embeddings during Fine-Tuning of Vision Transformers (ViT)

Fine-tuning significantly influences embeddings in image classification. Pre-fine-tuning embeddings offer general-purpose representations, whereas post-fine-tuning embeddings capture task-specific features. This distinction can lead to varying outcomes in outlier detection and other tasks. Both pre-fine-tuning and post-fine-tuning embeddings have their unique strengths and should be used in combination to achieve a comprehensive analysis in image classification and analysis tasks.

Interactive Data Exploration with Spotlight: Unveiling Critical Segments to Guide Synthetic Data Generation

Building robust models for Visual Inspection in production settings can be a real challenge. Here, cloud services like Amazon Lookout for Vision promise relief for model training but have limitations regarding data curation. This article explores those potential shortcomings and shows how to improve over them to leverage these services to the fullest.

The Industrial AI Canvas

The Industrial AI Canvas can be a useful tool for planning data and ml-based projects.

Enriched dataset for anomalous sound event detection

If you work in ML-based acoustics, the annual DCASE challenge is a great resource to learn about new state-of-the-art methods. We built an enriched dataset for the condition monitoring task that can be downloaded from Huggingface and explored with Spotlight in just five minutes.

Why we are building Spotlight

We have just released the open version of our data curation software Renumics Spotlight. It is intended for cross-functional teams who want to be in control of their data and data curation processes. In this post I would like to share our ideas behind this product.

Machine learning for test data analysis: Brake squeal example

Machine learning can drastically speed up the analysis of engineering test data. We use the AI-assisted Engineering Canvas to conceptualize a use case from brake squeal analysis.

Data curation checklist for condition monitoring (Part 2)

Data collection for condition monitoring has several pitfalls, potentially leading to data that is not suitable for training robust machine learning models. The data problems resulting from the data collection include but are not limited to the presence of failures in the recording equipment, the dominance of specific operating conditions, or mislabeled audio samples. In this article, we will thus help you to ask the right questions and equip you with a checklist you can use when collecting and preparing data for your condition monitoring use case.

Data curation checklist for condition monitoring (Part 1)

Data collection for condition monitoring has several pitfalls, potentially leading to data that is not suitable for training robust machine learning models. The data problems resulting from the data collection include but are not limited to the presence of failures in the recording equipment, the dominance of specific operating conditions, or mislabeled audio samples. In this article, we will thus help you to ask the right questions and equip you with a checklist you can use when collecting and preparing data for your condition monitoring use case.

Improving sample selection in surrogate modeling

Selecting samples for training robust surrogate models in simulation can be a real challenge. Active learning-like approaches where samples are selected iteratively can help overcome this challenge. We show how to apply such a procedure to save time and computational resources while making your surrogate model even more robust.

Building robust Visual Inspection models using Amazon Lookout for Vision

Building robust models for Visual Inspection in production settings can be a real challenge. Here, cloud services like Amazon Lookout for Vision promise relief for model training but have limitations regarding data curation. This article explores those potential shortcomings and shows how to improve over them to leverage these services to the fullest.

Removing unwanted bias

Making your data match the real-world data of your use-case is crucial for training a robust machine learning model. This post shows you how to interactively curate your data to adapt your data in an informed manner.

Matching vibroacoustic test and simulation data with machine learning

How to quickly find and correct label errors

Ensuring label consistency is critical for building robust machine learning models. This post shows you how to achieve label consistency in a data centric way.

Training an acoustic event detection system using Renumics Spotlight

Machine Learning based systems for acoustic event detection typically require a vast amount of training data. Intelligent labeling techniques open up new possibilities for small data scenarios.

How data-centric ML helps to build reliable models fast

ML researchers typically iterate different model architectures on a fixed dataset that they often know very little about. In real use cases, it is often a good idea to focus most efforts on the data and not on the model.

Data-centric AI for Engineering and Manufacturing

Data-centric machine learning is an emerging paradigm. Is this a game-changer for ML in engineering and manufacturing?

The AI-assisted Engineering Canvas

Data-driven methods have arrived and promise to speed up product development. The AI-assisted Engineering Canvas helps to get started.

What is AI-assisted Design?

Generative ML methods have achieved tremendous success in image and audio processing. Can mechanical engineers benefit from this technology?

Use Cases for AI-assisted Engineering

Machine learning will transform engineering work. But how does this process look like and where will it start?

What is AI-assisted Engineering ?

Engineers spend a lot of time on manual routine tasks. Novel machine learning techniques promise to change that.