Andrew Duncan

Happy weekend, happy reading: What are logical qubits and why should you care?💡🧑🏼‍💻🗞️ A big thanks to The Quantum Insider for an insightful piece on the significance of logical qubits and their growing impact on research and industry use cases. What’s the key takeaway? In the rapidly evolving world of #quantum computing, logical qubits are essential for enabling practical, large-scale quantum applications. As highlighted by The Quantum Insider this week, logical qubits offer greater stability and error resistance compared to physical qubits. 👉 Read the full article here: https://lnkd.in/dcTKCWqA What’s QMware AG‘s take? At QMware AG we provide up to 42 logical qubits on our hybrid quantum platform, empowering businesses and researchers to develop and execute advanced quantum algorithms with precision. With our Quantum-as-a-Service solutions, you can explore cutting-edge use cases across industries—from optimization problems to scientific research. Curious about how hybrid quantum computing can benefit your field? 👉 Visit our website or contact us to learn more and schedule an introduction! #QuantumComputing #QuantumCloud #QaaS #HybridQuantum #LogicalQubits #Innovation #B2B #Research #TechTransformation

13

1 Comment

Welcome to read the article "Using Graph Neural Networks for Social Recommendations" which is written by Dharahas Tallapally, John Wang, Katerina Potika and Magdalini Eirinaki. This excellent article was published in issue 11 in 2023 and has been viewed 2068 times! Article link: https://lnkd.in/ghSHBgPV MDPI San Jose State University #graphneuralnetworks #recommendationsystems

1

For all large language models (LLM) can do, it's important to recognise what they can't. This research paper addresses a critical question: How reliable is LLM's knowledge? The authors, including the Head of Aveni Labs, Dr. Alexandra Birch, and Dr. Barry Haddow, our Head of Natural Language Processing, introduce a novel metric called MOdel kNowledge relIabiliTy scORe (MONITOR) to assess LLM's factual reliability. MONITOR works by asking models the same question in different ways and seeing how likely the model is to give the same answer each time. This innovative approach helps identify situations where an LLM might be making things up rather than providing facts. Read more: https://hubs.la/Q02w7fJk0 #LLM #largelanguagemodels #naturalLanguageProcessing #machinelearning #artificalintelligence

5

1 Comment

"Bayesian inference stands as a cornerstone in the realm of statistical modelling and machine learning, offering us a robust framework for updating beliefs in light of new evidence. This article dives into an intricate Python-based Bayesian inference framework I created that amalgamates several advanced computational techniques: Markov Chain Monte Carlo (MCMC), Hyperdimensional Computing (HDC), Knowledge Graphs and Graph Neural Networks (GNNs)." https://lnkd.in/gWNj7XUX #BayesianInference #MachineLearning #MCMC #HyperdimensionalComputing #KnowledgeGraphs #GNN #ProbabilisticModeling #DataScience #StatisticalLearning #PythonProgramming #BayesTheorem #ComputationalStatistics #ArtificialIntelligence #ProbabilityTheory #DataAnalysis #StatisticalModeling #PredictiveAnalytics #BayesianNetworks #UncertaintyQuantification #AdvancedAnalytics

2

Table processing continues to be an open challenge in #NLProc, both because of the table structure and because of how tables often mix different data formats and modalities. In our paper presented at #ACL2024 findings this week, we show to effectively interpret tabular data using text-based and image-based table representations. Work led by Naihao Deng. https://lnkd.in/gnKv4viX

47

1 Comment

Expand your explainable-AI toolkit by following along Conor O'Sullivan's latest tutorial, where you'll learn how to apply the H-stat with the artemis package and interpret the pairwise, overall, and unnormalized metrics.

23

Expand your explainable-AI toolkit by following along Conor O'Sullivan's latest tutorial, where you'll learn how to apply the H-stat with the artemis package and interpret the pairwise, overall, and unnormalized metrics.

25

Attending #EMNLP2024 this week. NLP is the best 💪 Check out Yash's talk on our work on Wednesday, CaT-Bench: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans

11

In our latest preprint, we propose a methodology to design, develop, and validate RL algorithms for scaling network functions using a twofold approach. First, it assesses the training performance of these RL algorithms with various reward functions, i.e., it focuses on the performance from a learning perspective. Then, it validates their capabilities using performance indicators of the networking problem, i.e., it focuses on the performance of the algorithm from the networking perspective. Despite significant progress, our findings highlight considerable room for improvement in developing RL techniques for networking applications, especially for integration into AI-native next-generation networks. Paola Andrea Soto Arenas, Nina Slamnik - Kriještorac, Danny De Vleeschauwer, Yorick De Bock, Chia-Yu Chang, Natalia Gaviria, Juan Felipe Botero, Erik Mannens, Prof. PhD. MEng. MSc., Steven Latré Check out the full paper here: https://lnkd.in/gJvDiqGk "Designing, Developing, and Validating Network Intelligence for Scaling in Service-Based Architectures based on Deep Reinforcement Learning" #6G #DeepReinforcementLearning #NetworkIntelligence #AI #Research

32

Linear Discriminant Analysis (LDA) not only reduces the complexity of datasets but also highlights the key features that drive class separation, making it highly effective for identifying failure causes in production systems. Read 'Linear Discriminant Analysis (LDA)' by Dr. Ingo Nowitzky | #MachineLearning

16

I have written a brief accessible introduction to the latest paper Marta Andronic and I have written, NeuraLUT, on hiding neural network complexity in synthesisable Boolean functions. https://lnkd.in/e55MhuMV

47

I'm particularly interested in using AI /ML to facilitate discovery. The article below discusses how mathematics might offer a fertile training ground for such activities. https://lnkd.in/e74Kv56w

9

A couple of weeks back I released an R package, ggsmc, on CRAN. It can be used to visualise the output of IS, SMC and ensemble-based algorithms. https://lnkd.in/egP2Jy3F 1/4 Whilst I am a big admirer of dplyr/ggplot2, I don't use them regularly enough to remember what I need to do to convert Monte Carlo output (which I usually store in a matrix) to the tidy format needed for plotting. 2/4 I wrote this package to help me with this, and to provide an easy interface to construct the types of plots I commonly use. There is a vignette for the package. https://lnkd.in/eHvw5KgA 3/4 Over the next few days I'll post some details about some of the functions. For now, I'll highlight the matrix2tidy function, which can be used for converting from matrix format to the tidy format required for plotting. https://lnkd.in/eveHHqm3 4/4

31

🤔 Facing challenges with traditional Retrieval-Augmented Generation systems in your LLM projects? 🚀 Introducing GraphRAG: A Solution to Power Up LLMs with Knowledge Graphs: https://lnkd.in/gUpyKgSy Traditional retrieval systems often struggle with the complexity and volume of data, leading to suboptimal integration of information into LLMs. GraphRAG, developed by Microsoft Research, revolutionizes this by leveraging knowledge graphs to enhance data structuring, relevance, and retrieval efficiency. 📅 Join us at the DataHack Summit 2024 for an in-depth session: Topic: "GraphRAG: Powering Up LLMs with Knowledge Graphs" The speaker of this session will be Siddhant Agarwal, Developer Relations Lead - APAC at Neo4j. In this session, Siddhant will explore how GraphRAG addresses these challenges by: ➡️ Creating Knowledge Graphs: Extract entities and relationships to form a structured knowledge base. ➡️ Semantic Clustering: Organize the graph into semantic communities for better data cohesion. ➡️ Enhanced Query Processing: Generate comprehensive, diverse answers relevant to user queries. #AnalyticsVidhya #DataHackSummit2024 #DHS2024

132

4 Comments