More Like this

1. Circuit design in biology and machine learning. I. Random networks and dimensional reduction

   https://doi.org/10.1093/evolut/qpaf065  

   Frank, Steven A (May 2025, Evolution)

   Abstract A biological circuit is a neural or biochemical cascade, taking inputs and producing outputs. How have biological circuits learned to solve environmental challenges over the history of life? The answer certainly follows Dobzhansky’s famous quote that “nothing in biology makes sense except in the light of evolution.” But that quote leaves out the mechanistic basis by which natural selection’s trial-and-error learning happens, which is exactly what we have to understand. How does the learning process that designs biological circuits actually work? How much insight can we gain about the form and function of biological circuits by studying the processes that have made those circuits? Because life’s circuits must often solve the same problems as those faced by machine learning, such as environmental tracking, homeostatic control, dimensional reduction, or classification, we can begin by considering how machine learning designs computational circuits to solve problems. We can then ask: How much insight do those computational circuits provide about the design of biological circuits? How much does biology differ from computers in the particular circuit designs that it uses to solve problems? This article steps through two classic machine learning models to set the foundation for analyzing broad questions about the design of biological circuits. One insight is the surprising power of randomly connected networks. Another is the central role of internal models of the environment embedded within biological circuits, illustrated by a model of dimensional reduction and trend prediction. Overall, many challenges in biology have machine learning analogs, suggesting hypotheses about how biology’s circuits are designed. 

   more » « less
2. Combinatorial decision-making driven by multicomponent surface condensates

   https://doi.org/10.1073/pnas.2527873123  

   Zentner, Aidan; Halingstad, Ethan V; Chalk, Cameron; Brenner, Michael P; Murugan, Arvind; Winfree, Erik; Shrinivas, Krishna (July 2026, Proceedings of the National Academy of Sciences)

   Living organisms rely on molecular networks, such as gene circuits and signaling pathways, for information processing and robust decision-making in crowded, noisy environments. Recent advances show that interacting biomolecules self-organize by phase transitions into coexisting spatial compartments called condensates, often on cellular surfaces such as chromatin and membranes. In this paper, we demonstrate that multicomponent fluids can be designed to recruit distinct condensates to surfaces with differing compositions, performing a form of surface classification by condensation. We draw an analogy to multidimensional classification in machine learning and explore how hidden species, analogous to hidden nodes, expand the expressivity and capacity of these interacting ensembles to facilitate complex decision boundaries. By simply changing levels of individual species, we find that the same molecular repertoire can be reprogrammed to solve new tasks. Together, our findings suggest that the physical processes underlying biomolecular condensates can encode and drive adaptive information processing beyond compartmentalization. 

   more » « less
3. Anomaly Detection with Autoencoders for Spectrum Sharing and Monitoring

   https://doi.org/10.1109/CQR54764.2022.9918589  

   Tschimben, Stefan; Gifford, Kevin (September 2022, IEEE)

   Abstract—Demand for wireless communication devices has been growing continuously since the advent of mobile communication. Even though spectral efficiency and throughput keep increasing, consumer demand continues to seemingly outpace that growth. Spectrum sharing is becoming a more attractive solution to solving various capacity constraints as the resulting perceived spectrum scarcity can mostly be attributed to inefficient spectrum management. However, increasingly complex sharing arrangements come with an increased risk of interference. This makes it necessary to address such events in a timely manner. At the same time, research into using machine learning for solving issues such as signal classification, decision-making processes, and anomaly detection in wireless communication has been growing. To support machine learning research in anomaly detection for wireless communications, this research uses IQ data to train two autoencoders for anomaly detection in shared spectrum: a Long Short-Term Memory (LSTM) and a Deep Autoencoder. These algorithms are used to successfully identify anomalies in the time and frequency domain of recorded IQ data in the form of unauthorized LTE transmissions on top of Wi-Fi communication. 

   more » « less
4. Reconstructing Classification to Enhance Machine-Learning Based Network Intrusion Detection by Embracing Ambiguity

   Song, Chungsik; Fan, Wenjun; Chang, Sang-Yoon; Park, Younghee (December 2020, Silicon Valley Cybersecurity Conference)

   null (Ed.)

   Network intrusion detection systems (IDS) has efficiently identified the profiles of normal network activities, extracted intrusion patterns, and constructed generalized models to evaluate (un)known attacks using a wide range of machine learning approaches. In spite of the effectiveness of machine learning-based IDS, it has been still challenging to reduce high false alarms due to data misclassification. In this paper, by using multiple decision mechanisms, we propose a new classification method to identify misclassified data and then to classify them into three different classes, called a malicious, benign, and ambiguous dataset. In other words, the ambiguous dataset contains a majority of the misclassified dataset and is thus the most informative for improving the model and anomaly detection because of the lack of confidence for the data classification in the model. We evaluate our approach with the recent real-world network traffic data, Kyoto2006+ datasets, and show that the ambiguous dataset contains 77.2% of the previously misclassified data. Re-evaluating the ambiguous dataset effectively reduces the false prediction rate with minimal overhead and improves accuracy by 15%. 

   more » « less
5. Strategies for Crisis-Responsive Governance: Automated Anomaly Identification in Public Services

   Unveren, H; Lehyeh, AA; Pamukcu, D; Zobel, CW (May 2024, https://ojs.iscram.org/index.php/Proceedings)

   Penkert, B; Hellingrath, B; Rode, M; Widera, A; Middelhoff, M; Boersma, K; Kalthoner, M (Ed.)

   This paper introduces a machine learning tool for service systems, focusing on accurate classification of service requests and swift anomaly detection, particularly crucial during emergencies. Employing a Support Vector Machine model, this tool automatically classifies service calls into predefined categories with high accuracy, while effectively detecting irregular requests that require specific attention from operators. This approach streamlines resource management by reducing the manuaI categorization workload and enables early detection of emerging service needs. Examining Orange County, Florida 311 System data, with a specific focus on the COVID-19 period, we illustrate the tool's success in automatic request categorization and anomaly detection. Overall, this tool presents an effective automation approach to help with efficient resource management of service systems and proactive assessment of public service needs, promising to revolutionize service request management during crises. Future work will explore additional classification models for enhanced accuracy and integrate automated alerts for proactive disaster management. 

   more » « less