In this blog, we are going to discuss privacy-preserving Edge AI work we have conducted in Accenture Labs Security R&D team in Washington DC. This work is part of the Trustworthy AI project, in which we have explored a wide range of topics, including Responsible AI, Robust AI, Explainable AI…

Adrianna Janik and Eda Bayram With the growing adoption of AI solutions, explainability needs to grow even faster. In June 2023, the EU Commission approved a draft of the legal framework called the AI Act¹ that mandates AI systems to provide explanations to users¹. It means that model’s explainability is…

Co-authored by David Goedicke, Wendy Ju, and Mike Kuniavsky Sound is consequential — most actions that take place in the physical world produce sound. …

Machine learning (ML) models, including deep neural networks (DNN), have been successfully applied to a wide range of computer vision tasks, including, but not limited to, image classification, object detection, autonomous vehicle control and visual concept discovery. Given the ubiquity of machine learning applications, the security aspects of machine learning…

When it comes to using LLM models that deal with small molecules or proteins, there are essentially two families of pretained models BERT and GPT. Both model families are based on the transformer architecture, but they differ in their training objectives and the way they process input data. BERT is…

Part 1: Towards Hands-Free Eyes-Free Interaction — Co-authored by Wendy Ju, Mike Kuniavsky, David Goedicke Your most awaited Ikea purchase has just arrived! You open the package with excitement to meet a very long instruction booklet. You feel the overwhelming pressure slowly rising, until you see the Audio AR compatible hardware logo. You immediately pick up your…

Processing brain signals has traditionally involved researchers with carefully cleaning data and extracting features, but recent techniques have demonstrated the capability to develop AI models that take on that responsibility in their neural architecture. In this tutorial series I demonstrate the efficacy and how-to of implementing Computer Vision techniques for…

By Jake Metzger and Alexandria Pabst — Accenture Labs Introduction Knowledge Graphs (KGs) have become a ubiquitous technology in the time of the Semantic Web. Google Search and Wikipedia alone account for millions of interactions with information worldwide, and part of their secret sauce has been the flexible semantic reasoning enabled…

By Jake Metzger and Alexandria Pabst — Accenture Labs Setting the Scene This post is an opinionated, whirlwind introduction to the motivations of Bayesian epistemology, probability, and statistical inference. We get into some philosophical and mathematical details here, which produce downstream scientific and technological differences as well. …