--The increased demand for data privacy and security in machine learning (ML) applications has put impetus on effective edge training on Internet-of-Things (IoT) nodes. Edge training aims to leverage speed, energy efficiency and adaptability within the resource constraints of the nodes. This paper presents a Dynamic Tsetlin Machine (DTM) training accelerator as an alternative to DNN implementations. Underpinned on the V anilla and Coalesced Tsetlin Machine algorithms, the dynamic aspect of the accelerator design allows for a run-time reconfiguration targeting different datasets, model architectures, and model sizes without resynthesis. This makes the DTM suitable for targeting multivariate sensor-based edge tasks. Compared to DNNs, DTM trains with fewer multiply-accumulates, devoid of derivative computation. It is a data-centric ML algorithm that learns by aligning Tsetlin automata with input data to form logical propositions enabling efficient Lookup-T able (LUT) mapping and frugal Block RAM usage in FPGA training implementations. The proposed accelerator offers 2.54x more Giga operations per second per Watt (GOP/s per W) and uses 6x less power than the next-best comparable design. Index T erms --Edge Training, Coalesced Tsetlin Machines, Dynamic Tsetlin Machines, Embedded FPGA, Machine Learning Accelerator, On-Chip Learning, Logic-based-learning. ACHINE Learning (ML) offers a generalized approach to developing autonomous applications from "Internet-of-Things" (IoT) sensor data. Having ML execution units in close proximity to the sensor, at the so-called edge, enables faster task execution with high data security and privacy. However, sensor degradation and environmental factors may require recalibration [1] or user-personalized on-field training [2] to ensure continued functionality. Implementing solutions to these challenges is nontrivial. It requires finding the right balance between achieving the appropriate learning efficacy for the ML problem and the restrictive compute/ memory resources available on the platforms [3]. This work was supported by EPSRC EP/X036006/1 Scalability Oriented Novel Network of Event Triggered Systems (SONNETS) project and by EPSRC EP/X039943/1 UKRI-RCN: Exploiting the dynamics of self-timed machine learning hardware (ESTEEM) project. For ML inference tasks on edge nodes, these challenges have been widely explored, e.g., quantization [4], sparsity-based compression, and pruning for the most commonly used Deep Neural Network (DNN) models [3], [5], [6].

The bees are having a rough go of it. Declining populations, parasitic wasps, and continued environmental degradation would be stressful situations for any species--and the planet's vital pollinators appear to respond to pressure much like many humans do. New research published on October 9 in the Proceedings of the Royal Society B from a team at Newcastle University suggests that just like us, bees are more likely to make pessimistic choices after being put through the ringer. To test what happens when bees are under duress, the team first trained three groups of the female worker bumblebees to identify and associate different colors with varying outcomes--a blue LED screen represented a location with a sweeter reward, while green indicated a less favorable water solution. Once the bees understood each color's reward amount, researchers then placed the groups in chambers with varying hues that fell in the spectrum between blue and green, then simulated a predatory attack for two groups, either by giving them a light shake or temporarily trapping them with a sponge-tipped robotic arm.

Hosted by Eleanor Drage and Kerry Mackereth, The Good Robot is a podcast which explores the many complex intersections between gender, feminism and technology. In this episode, we talked to Rebecca Woods, a Senior Lecturer in Language and Cognition at Newcastle University. We have an amazing chat about language learning in AI, and she tells us how language is crucial to how GPT functions. She's also an expert in how children learn languages, and she compares this to teaching AI how to process language. Rebecca is a Lecturer in Language and Cognition in the School of English Language, Literature and Linguistics at Newcastle University.

A unique studentship opportunity to join an interdisciplinary team with world class reputation is offered by Newcastle University. This PhD studentship is part of a biomedical research European project funded by FOREUM (Foundation for Research in Rheumatology) and with partners in Italy, Spain and the UK. The project focuses on Rheumatoid Arthritis (RA), affecting 35 million people worldwide with many of them unable to achieve sustained disease remission with current treatments. The aim of the project is to understand and characterise the disease mechanisms at molecular level that lead to disease flares, with a combination of skills including experimental medicine, immunology and artificial intelligence. In this doctoral project you will focus on the challenge of devising innovative strategies to process, using artificial intelligence, the rich data that the project will generate in order to design prediction models relevant to RA flares (e.g.

Type 2 Diabetes is a fast-growing, chronic metabolic disorder due to imbalanced insulin activity.The motion of this research is a comparative study of seven machine learning classifiers and an artificial neural network method to prognosticate the detection and treatment of diabetes with high accuracy,in order to identify and treat diabetes patients at an early age.Our training and test dataset is an accumulation of 9483 diabetes patients information.The training dataset is large enough to negate overfitting and provide for highly accurate test performance.We use performance measures such as accuracy and precision to find out the best algorithm deep ANN which outperforms with 95.14% accuracy among all other tested machine learning classifiers.We hope our high-performing model can be used by hospitals to predict diabetes and drive research into more accurate prediction models.

Whether men or women make better drivers has has long been a hotly-debated topic. While the latter historically take more jibes about their skills behind the wheel, studies have shown that female drivers are far less likely to commit driving offences. But with driverless cars getting closer to reality, engineers are looking closely at all factors that affect their safety. A new study from Newcastle University has revealed that autonomous vehicles may need to be fitted with gender-specific settings - as women are better at using them than men. Their research found that females were better at taking back control of the vehicle when required to respond to a hazard.

We are a world class research-intensive university. We deliver teaching and learning of the highest quality. We play a leading role in economic, social and cultural development of the North East of England. Attracting and retaining high-calibre people is fundamental to our continued success. We are delighted to be seeking a motivated individual to join our project, in the School of Computing.

If you're irritated by the mere sight of people fidgeting, a new scientific study suggests you're not alone. Researchers in Canada recruited 4,100 participants who were asked to self-report whether they have sensitivities to seeing people fidget. They found that almost one in three people experienced the psychological phenomenon known as'misokinesia, or a'hatred of movements'. Misokinesia is psychological response to the sight of someone else's small but repetitive movements, the experts say, and it can seriously affect daily living. Misokinesia - the'hatred of movements' - is a psychological response to the sight of someone else's small and repetitive movements (concept image) Misokinesia - or the'hatred of movements' - is a psychological phenomenon that is defined as a strong negative affective or emotional response to the sight of someone else's small and repetitive movements.

People who have an extreme reaction to certain noises, specifically loud chewing and breathing, may have a'supersensitized' brain connection, a new study reveals. Scientists at Newcastle University discovered an increased connectivity between the auditory cortex and the motor control areas related to the face, mouth and throat in those suffering with misophonia. Misophonia, which means'hatred of sound', is a condition in which people experience intense and involuntary reactions to certain sounds made by others, referred to as'trigger' sounds. The findings suggest that misophonia is not an abreaction of sounds, but'manifestation of activity in parts of the motor system involved in producing those sounds,' according to the study published in the Journal of Neuroscience. Dr Sukhbinder Kumar, Newcastle University Research Fellow in the Biosciences Institute said: 'Our findings indicate that for people with misophonia there is abnormal communication between the auditory and motor brain regions - you could describe it as a'supersensitized connection'.

Neurological conditions such as Parkinson's and Alzheimer's could be diagnosed from simple eye scans performed by high street opticians thanks to a new NHS artificial intelligence (AI) project. Newcastle University is working on the project with medics at North East hospitals as part of a national £50 million boost to use AI in a range of health schemes. Early diagnosis in progressive neurological diseases such as Parkinson's and Alzheimer's, which affect more than one million people in the UK, is important, so speeding up the process could be crucial. Anya Hurlbert, professor of visual neuroscience at Newcastle University, is leading the Octahedron project. She said: "The retina at the back of the eye is basically an outpost of the brain and the only part of the central nervous system we can see directly from the outside. "We know that in Alzheimer's disease and Parkinson's disease the retina is affected." Very detailed images of the retina can be captured by optical coherence tomography, or OCT scanning, which is quick and cheap and increasingly available at high street opticians. Further analysis of these scans will now be developed with the use of AI, to recognise signs of neurological disease. Prof Hurlbert said: "The aim of the project is to use NHS data to teach computers how to detect early signs of neurological disease via retinal imaging.