Author summary Interest in machine learning as applied to challenges in medicine has seen an exponential rise over the past decade. A key issue in developing machine learning models is the availability of sufficient high-quality data. Another related issue is a requirement to validate a locally trained model on data from external sources. However, sharing sensitive biomedical and clinical data across different hospitals and research teams can be challenging due to concerns with data privacy and data stewardship. These issues have led to innovative new approaches for collaboratively training machine learning models without sharing raw data. One such method, termed ‘federated learning,’ enables investigators from different institutions to combine efforts by training a model locally on their own data, and sharing the parameters of the model with others to generate a central model. Here, we systematically review reports of successful deployments of federated learning applied to research problems involving biomedical data. We found that federated learning links research teams around the world and has been applied to modelling in such as oncology and radiology. Based on the trends we observed in the studies reviewed in our paper, we observe there are opportunities to expand and improve this innovative approach so global teams can continue to produce and validate high quality machine learning models.

The novelty cheque has long been a mainstay of the political "photo op" but a Guardian Australia analysis of photos posted during the 2022 and 2019 election campaigns suggests giant cheques are on the way out, while hi-vis workwear and photos of dogs are on the rise. During our work building the automated systems behind the pork-o-meter, which tracks election campaign pork barrelling as it occurs, the Guardian's data team found ourselves asking an important question. Could we teach a robot to spot photos of novelty cheques? We were already using machine learning to flag text from politicians' Facebook posts as likely grant announcements and election promises, but having another model in place to find big cheques and certificates in photos might pick up things we'd missed in the text.

If you spend too much time on your smartphone, scientists have a list of 10 solutions that can help you cut back on screen time. The small but effective changes can help curb smartphone addiction and mental health issues such as depression, say experts at McGill University in Canada. In experiments, people following the strategies reduced their screen time, felt less addicted to their phone and improved their sleep quality, the experts report. Among the 10 strategies are changing the phone display to'greyscale' so the display appears black and white, and disabling facial recognition as a method of unlocking the screen. A black and white screen makes smartphones'less gratifying' to look at compared to the bright colours offered by app icons such as TikTok and Instagram.

Continual learning - learning new tasks in sequence while maintaining performance on old tasks - remains particularly challenging for artificial neural networks. Surprisingly, the amount of forgetting does not increase with the dissimilarity between the learned tasks, but appears to be worst in an intermediate similarity regime. In this paper we theoretically analyse both a synthetic teacher-student framework and a real data setup to provide an explanation of this phenomenon that we name Maslow's hammer hypothesis. Our analysis reveals the presence of a trade-off between node activation and node re-use that results in worst forgetting in the intermediate regime. Using this understanding we reinterpret popular algorithmic interventions for catastrophic interference in terms of this trade-off, and identify the regimes in which they are most effective.

This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a tendency to rely on early interactions and ignore useful evidence encountered later. Because of training on progressively growing datasets, deep RL agents incur a risk of overfitting to earlier experiences, negatively affecting the rest of the learning process. Inspired by cognitive science, we refer to this effect as the primacy bias. Through a series of experiments, we dissect the algorithmic aspects of deep RL that exacerbate this bias. We then propose a simple yet generally-applicable mechanism that tackles the primacy bias by periodically resetting a part of the agent. We apply this mechanism to algorithms in both discrete (Atari 100k) and continuous action (DeepMind Control Suite) domains, consistently improving their performance.

Discourse cohesion facilitates text comprehension and helps the reader form a coherent narrative. In this study, we aim to computationally analyze the discourse cohesion in scientific scholarly texts using multilayer network representation and quantify the writing quality of the document. Exploiting the hierarchical structure of scientific scholarly texts, we design section-level and document-level metrics to assess the extent of lexical cohesion in text. We use a publicly available dataset along with a curated set of contrasting examples to validate the proposed metrics by comparing them against select indices computed using existing cohesion analysis tools. We observe that the proposed metrics correlate as expected with the existing cohesion indices. We also present an analytical framework, CHIAA (CHeck It Again, Author), to provide pointers to the author for potential improvements in the manuscript with the help of the section-level and document-level metrics. The proposed CHIAA framework furnishes a clear and precise prescription to the author for improving writing by localizing regions in text with cohesion gaps. We demonstrate the efficacy of CHIAA framework using succinct examples from cohesion-deficient text excerpts in the experimental dataset.

The Matrix-based Renyi's entropy enables us to directly measure information quantities from given data without the costly probability density estimation of underlying distributions, thus has been widely adopted in numerous statistical learning and inference tasks. However, exactly calculating this new information quantity requires access to the eigenspectrum of a semi-positive definite (SPD) matrix $A$ which grows linearly with the number of samples $n$, resulting in a $O(n^3)$ time complexity that is prohibitive for large-scale applications. To address this issue, this paper takes advantage of stochastic trace approximations for matrix-based Renyi's entropy with arbitrary $\alpha \in R^+$ orders, lowering the complexity by converting the entropy approximation to a matrix-vector multiplication problem. Specifically, we develop random approximations for integer order $\alpha$ cases and polynomial series approximations (Taylor and Chebyshev) for non-integer $\alpha$ cases, leading to a $O(n^2sm)$ overall time complexity, where $s,m \ll n$ denote the number of vector queries and the polynomial order respectively. We theoretically establish statistical guarantees for all approximation algorithms and give explicit order of s and m with respect to the approximation error $\varepsilon$, showing optimal convergence rate for both parameters up to a logarithmic factor. Large-scale simulations and real-world applications validate the effectiveness of the developed approximations, demonstrating remarkable speedup with negligible loss in accuracy.

In this paper, we propose a pre-trained-combined neural network (PTCN) as a comprehensive solution to the inverse design of an integrated photonic circuit. By utilizing both the initially pre-trained inverse and forward model with a joint training process, our PTCN model shows remarkable tolerance to the quantity and quality of the training data. As a proof of concept demonstration, the inverse design of a wavelength demultiplexer is used to verify the effectiveness of the PTCN model. The correlation coefficient of the prediction by the presented PTCN model remains greater than 0.974 even when the size of training data is decreased to 17%. The experimental results show a good agreement with predictions, and demonstrate a wavelength demultiplexer with an ultra-compact footprint, a high transmission efficiency with a transmission loss of -2dB, a low reflection of -10dB, and low crosstalk around -7dB simultaneously.

Understanding, modelling and predicting human risky decision-making is challenging due to intrinsic individual differences and irrationality. Fuzzy trace theory (FTT) is a powerful paradigm that explains human decision-making by incorporating gists, i.e., fuzzy representations of information which capture only its quintessential meaning. Inspired by Broniatowski and Reyna's FTT cognitive model, we propose a computational framework which combines the effects of the underlying semantics and sentiments on text-based decision-making. In particular, we introduce Category-2-Vector to learn categorical gists and categorical sentiments, and demonstrate how our computational model can be optimised to predict risky decision-making in groups and individuals.

Developed by Minderoo Foundation, the'Global Plastic Watch' tool uses advanced satellite data technology and machine learning to create a near-real-time, high resolution map of plastic pollution. The tool aims to help authorities better manage plastic leakage into the marine environment, and is said to provide the largest ever open source dataset of plastic waste across dozens of countries. Global Plastic Watch uses remote sensing satellite imagery from the European Space Agency and a novel machine learning model created in collaboration with digital product agency Earthrise Media. The tool can determine the size and scale of land-based plastic waste sites, which fuel the growing issue of plastic pollution in the world's rivers and oceans. By using the data, governments, industry and communities can evaluate and monitor the risk of land-based plastic waste sites as well as prioritise investment in solutions, Minderoo Foundation said.