Search for: All records

Recognizing food types through sensor signals for unseen users remains remarkably challenging, despite extensive recent studies. The efficacy of prior machine learning techniques is dwarfed by giant variations of data collected from multiple participants, partly because users have varied chewing habits and wear sensor devices in various manners. This work treats the problem as an instance of the domain adaptation problem, where each user represents a domain. We develop the first multi-source domain adaptation (MSDA) method for food-typing recognition, which consists of three major components: stratified normalization, a multi-source domain adaptor, and adaptive ensemble learning. New techniques are developed for each component. Using a real-world dataset comprised of 15 participants, we demonstrate that our method achieves\(1.33\times\)to\(2.13\times\)improvement in accuracy compared with nine state-of-the-art MSDA baselines. Additionally, we perform an in-depth ablation study to examine the behavior of each component and confirm their efficacy.

 

Prior research on evolutionary mechanisms during the origin of life has mainly assumed the existence of populations of discrete entities with information encoded in genetic polymers. Recent theoretical advances in autocatalytic chemical ecology establish a broader evolutionary framework that allows for adaptive complexification prior to the emergence of bounded individuals or genetic encoding. This framework establishes the formal equivalence of cells, ecosystems and certain localized chemical reaction systems as autocatalytic chemical ecosystems (ACEs): food-driven (open) systems that can grow due to the action of autocatalytic cycles (ACs). When ACEs are organized in meta-ecosystems, whether they be populations of cells or sets of chemically similar environmental patches, evolution, defined as change in AC frequency over time, can occur. In cases where ACs are enriched because they enhance ACE persistence or dispersal ability, evolution is adaptive and can build complexity. In particular, adaptive evolution can explain the emergence of self-bounded units (e.g. protocells) and genetic inheritance mechanisms. Recognizing the continuity between ecological and evolutionary change through the lens of autocatalytic chemical ecology suggests that the origin of life should be seen as a general and predictable outcome of driven chemical ecosystems rather than a phenomenon requiring specific, rare conditions.

 

Vector search has drawn a rapid increase of interest in the research community due to its application in novel AI applications. Maximizing its performance is essential for many tasks but remains preliminary understood. In this work, we investigate the root causes of the scalability bottleneck of using intra-query parallelism to speedup the state-of-the-art graph-based vector search systems on multi-core architectures. Our in-depth analysis reveals several scalability challenges from both system and algorithm perspectives. Based on the insights, we propose iQAN, a parallel search algorithm with a set of optimizations that boost convergence, avoid redundant computations, and mitigate synchronization overhead. Our evaluation results on a wide range of real-world datasets show that iQAN achieves up to 37.7× and 76.6× lower latency than state-of-the-art sequential baselines on datasets ranging from a million to a hundred million datasets. We also show that iQAN achieves outstanding scalability as the graph size or the accuracy target increases, allowing it to outperform the state-of-the-art baseline on two billion-scale datasets by up to 16.0× with up to 64 cores.