A powerful idea has been slowly building for many years now, originally known as the Semantic Web, and then later as Linked Data. This idea has finally come of age with the emergence of Knowledge Graphs. These technological networks allow an organisation to release the ‘free energy’ bound up in the chaotic jumble of databases […]
The success of an experimentation programme depends upon its cultural adoption within the business. With commoditised tools on the market that lower both software and statistical barriers to randomised controlled testing, organisations have the opportunity to democratise experimentation and continuously iterate towards their north star. This talk addresses two key questions that stretch an organisation […]
Every person who goes online will sooner or later deal with content or behaviour that can be harmful or unhealthy. Think scams, misinformation, bullying or even worse, child sexual abusive material, grooming, radicalisation or (s)extortion. This talk will explain the different components needed to tackle harmful content, why adversarial behaviour ensure this problem is always […]
Join us on March 23rd in partnership with TimeXtender. We have a packed lunch time session planned for you, where you’ll learn how to take raw data to curated data in under 90 minutes. Data Management is one of the most important things that data scientists and data engineers do on a daily basis. Doing […]
Join us on Feb 23rd for our next Online DSF Sandbox Session. Our panel of 4 experts will discuss the future of AI and ethics and explore AI visibility and transparency. This panel will be hosted by Ben Byford and takes place from 1-2:30 PM GMT. This event will feature some lightning talks followed by […]
Hosted by Niclas Thomas. The largest issue ML teams face is due to AI models that silently fail. Silent failure occurs when model performance gradually degrades over time without showing any apparent signs of failure. These signs are therefore difficult to catch in time, usually leading to sudden or abrupt drops in performance after the […]
While traditional web analytics tools analyse customer experience on websites by tracking metrics such as visited pages or time spent on website, at Decibel we aggregate those simple metrics (plus others) to surface specific behaviours within the user activity. On top of these behaviours we then built more advanced features which describe the Customer Experience […]
Machine Learning (ML) and in particular Deep Learning (DL) require huge numbers of MIPS to implement the training and classification processes required of modern Edge AI applications. All of this comes at a cost of MIPS , power consumption and silicon cost. The frequency domain and, in particular, the Fourier Transform can be used to […]
The talk will be a deep dive on some of the technology Tom’s used to build a system that runs funnel and spend analysis without any prior knowledge of the data. There’s some novel data science being done using techniques which aren’t so popular that he thinks are really valuable.