The rapid growth of deploying machine learning (ML) models within embedded systems on a chip (SoCs) has led to transformative shifts in fields like healthcare and autonomous vehicles. One of the primary challenges for training such embedded ML models is the lack of publicly available high-quality training data. Transfer learning approaches address this challenge by utilizing the knowledge encapsulated in an existing ML model as a starting point for training a new ML model. However, existing transfer learning approaches require direct access to the existing model which is not always feasible, especially for ML models deployed on embedded SoCs. Therefore, in this paper, we introduce a novel unconventional transfer learning approach to train a new ML model by extracting and using weights from an existing ML model running on an embedded SoC without having access to the model within the SoC. Our approach captures power consumption measurements from the SoC while it is executing the ML model and translates them to an approximated weights matrix used to initialize the new ML model. This improves the learning efficiency and predictive performance of the new model, especially in scenarios with limited data available to train the model. Our novel approach can effectively increase the accuracy of the new ML model up to 3 times compared to classical training methods using the same amount of limited training data.

Background Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes).

One year ago, we launched our Nuxeo Insight service and became the first and, at that time, only Content Services Platform to offer a trainable cloud service for machine learning. For those who might not be familiar with this unique service, Nuxeo Insight is an AI offering that enables our clients to use their own data and content to train custom, machine-learning (ML) models. Custom ML models can be used for a variety of business purposes, including enriching content with new metadata, auto-classifying vital records, identifying products and talent, and even automating forms processing. But the critical thing with Nuxeo Insight is that, because these models are trained with each customer's own data, they are much more accurate, insightful and therefore valuable than the commodity AI services that are available as public cloud offerings. If you are interested in learning more about the distinction between custom and commodity ML models, please refer back to a previous Nuxeo blog posting entitled, "The Difference Between Generic & Contextual AI." Today, we are very pleased to announce another first for Nuxeo Insight.

A new study suggested that two machine learning (ML) models Support Vector Regression (SVR) and Non-linear Canonical Correlation Analysis by Neural Networks (n-CCA) are able to predict the severity of three common symptoms faced by cancer patients such as depression, anxiety and sleep disturbance. The researchers believe that these type of models can be used to identify high-risk patients, educate them about the symptom and the experience. It can also improve the timing of preemptive and personalised symptom management interventions. Researchers from the University of Surrey in UK said that these three symptoms are associated with a severe reduction in cancer patients' quality of life. In addition, Professor from the varsity, Payam Barnaghi said, "These exciting results show that there is an opportunity for machine learning techniques to make a real difference in the lives of people living with cancer."