Teddy Lazebnik

Teddy Lazebnik

Socks are produced and replaced at a massive scale, yet their paired use makes them unusually vulnerable to service loss, as the disappearance of a single sock can leave usable wear-capacity stranded and create sockless days even when functional socks remain available. In this study, we examine whether pairing non-matching \say{orphan} socks can preserve daily sock service under stochastic loss, and how this benefit trades off against perceived social discomfort. We formalize sock ownership as a sequential decision problem under uncertainty in which socks wear out and disappear stochastically during laundering, while public exposure induces a person-specific mismatch penalty. We conducted an in-person study to estimate mismatch sensitivity and diversity preference, linking behavioural heterogeneity to interpretable mixing policies. Using these results, an exact benchmark on small tractable instances, and a simulation-based evaluation of pairing policies, we show that strict matching can appear resource-frugal largely because it generates many sockless days. In contrast, controlled tolerance for mismatch sustains service and reduces stranded wear-capacity across loss regimes. The ecological-cost term is treated as a proportional embodied-cost proxy rather than an independent life-cycle assessment measure, so the environmental interpretation is suggestive and mechanism-based rather than a direct estimate of environmental savings. This study establishes the feasibility and limitations of matching non-matching socks as a simple strategy for preserving service from already-owned garments.

Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi et al.

Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing. FL keeps data local to clients while communicating only model updates, such as gradients or model deltas. Nevertheless, these updates can expose private client data through gradient inversion attacks (GIAs). We study this risk for tabular FL under an honest-but-curious server threat model across FL protocols, client batch sizes, training stages, attacker assumptions, model architectures, and binary classification, multiclass classification, and regression tasks. We use MIMIC-IV and complementary benchmark datasets. Our evaluation distinguishes numerical and categorical recovery, baseline recoverability, feature level recovery, and exact match rate (EMR). We evaluate FedSGD gradients and FedAvg model deltas with an exposure aligned protocol, comparing attacked models after matched client data exposure rather than matched communication rounds. We compare multilayer perceptron (MLP), ResNet, and FT-Transformer models, and isolate architecture effects through an MLP grid over width, depth, activation, normalization, and dropout. The results show that small client batches and updates representing few distinct records are most vulnerable. Larger local batches and stronger aggregation reduce reconstruction but do not eliminate leakage. FT-Transformer is consistently harder to invert than one-hot baselines, while reconstructability also varies substantially within the MLP family. These findings identify architecture as a practical privacy variable in tabular FL. We also show that aggregate reconstruction accuracy can overstate complete record recovery in sparse data, making EMR and baseline comparisons essential.

Simon De Reuver, Tamas Kristof Toth, Teddy Lazebnik

Symbolic regression (SR) offers a route to scientific discovery by converting observations into interpretable governing equations. However, despite its promise, its reliability degrades sharply when spatiotemporal measurements are sparse, noisy, or physically incomplete, as commonly occurring in practice. Data enrichment (DE) has been shown to be able to mitigate this limitation, yet additional samples can mislead equation discovery unless they preserve the physical structure of the target system. Such implication of DE requires narrow domain expertise as well as technical fluidity, highly limiting its practical usefulness. In this study, we introduce a physics-guided latent diffusion framework for DE for down the line SR models. The proposed framework combines a variational autoencoder, a conditional latent diffusion model, and a physics-informed residual corrector to complete sparse observations with synthetic fields constrained by governing relations. We evaluate the approach on heat conduction, incompressible Navier-Stokes flow, and a moving single-mass Newtonian gravitational potential, using GPLearn, DEAP, and PySR as downstream SR backends. Our results reveal that physics-corrected enrichment consistently improves recovery in sparse regimes across physical dynamics and SR models. These results show that generative enrichment can strengthen equation discovery without additional domain expertise.

Liron Simon Keren, Alex Liberzon, Teddy Lazebnik

Discovering a meaningful symbolic expression that explains experimental data is a fundamental challenge in many scientific fields. We present a novel, open-source computational framework called Scientist-Machine Equation Detector (SciMED), which integrates scientific discipline wisdom in a scientist-in-the-loop approach, with state-of-the-art symbolic regression (SR) methods. SciMED combines a wrapper selection method, that is based on a genetic algorithm, with automatic machine learning and two levels of SR methods. We test SciMED on five configurations of a settling sphere, with and without aerodynamic non-linear drag force, and with excessive noise in the measurements. We show that SciMED is sufficiently robust to discover the correct physically meaningful symbolic expressions from the data, and demonstrate how the integration of domain knowledge enhances its performance. Our results indicate better performance on these tasks than the state-of-the-art SR software packages , even in cases where no knowledge is integrated. Moreover, we demonstrate how SciMED can alert the user about possible missing features, unlike the majority of current SR systems.

Jennifer Magana, Dinu Gavojdian, Yakir Menachem et al.

The aim of this study was to employ machine learning algorithms based on sensor behavior data for (1) early-onset detection of digital dermatitis (DD); and (2) DD prediction in dairy cows. With the ultimate goal to set-up early warning tools for DD prediction, which would than allow a better monitoring and management of DD under commercial settings, resulting in a decrease of DD prevalence and severity, while improving animal welfare. A machine learning model that is capable of predicting and detecting digital dermatitis in cows housed under free-stall conditions based on behavior sensor data has been purposed and tested in this exploratory study. The model for DD detection on day 0 of the appearance of the clinical signs has reached an accuracy of 79%, while the model for prediction of DD 2 days prior to the appearance of the first clinical signs has reached an accuracy of 64%. The proposed machine learning models could help to develop a real-time automated tool for monitoring and diagnostic of DD in lactating dairy cows, based on behavior sensor data under conventional dairy environments. Results showed that alterations in behavioral patterns at individual levels can be used as inputs in an early warning system for herd management in order to detect variances in health of individual cows.

Assaf Shmuel, Oren Glickman, Teddy Lazebnik

In the realm of machine and deep learning regression tasks, the role of effective feature engineering (FE) is pivotal in enhancing model performance. Traditional approaches of FE often rely on domain expertise to manually design features for machine learning models. In the context of deep learning models, the FE is embedded in the neural network's architecture, making it hard for interpretation. In this study, we propose to integrate symbolic regression (SR) as an FE process before a machine learning model to improve its performance. We show, through extensive experimentation on synthetic and real-world physics-related datasets, that the incorporation of SR-derived features significantly enhances the predictive capabilities of both machine and deep learning regression models with 34-86% root mean square error (RMSE) improvement in synthetic datasets and 4-11.5% improvement in real-world datasets. In addition, as a realistic use-case, we show the proposed method improves the machine learning performance in predicting superconducting critical temperatures based on Eliashberg theory by more than 20% in terms of RMSE. These results outline the potential of SR as an FE component in data-driven models.

Teddy Lazebnik, Amit Somech, Abraham Itzhak Weinberg

Automated machine learning (AutoML) frameworks have become important tools in the data scientists' arsenal, as they dramatically reduce the manual work devoted to the construction of ML pipelines. Such frameworks intelligently search among millions of possible ML pipelines - typically containing feature engineering, model selection and hyper parameters tuning steps - and finally output an optimal pipeline in terms of predictive accuracy. However, when the dataset is large, each individual configuration takes longer to execute, therefore the overall AutoML running times become increasingly high. To this end, we present SubStrat, an AutoML optimization strategy that tackles the data size, rather than configuration space. It wraps existing AutoML tools, and instead of executing them directly on the entire dataset, SubStrat uses a genetic-based algorithm to find a small yet representative data subset which preserves a particular characteristic of the full data. It then employs the AutoML tool on the small subset, and finally, it refines the resulted pipeline by executing a restricted, much shorter, AutoML process on the large dataset. Our experimental results, performed on two popular AutoML frameworks, Auto-Sklearn and TPOT, show that SubStrat reduces their running times by 79% (on average), with less than 2% average loss in the accuracy of the resulted ML pipeline.

Dinu Gavojdian, Teddy Lazebnik, Madalina Mincu et al.

There is a critical need to develop and validate non-invasive animal-based indicators of affective states in livestock species, in order to integrate them into on-farm assessment protocols, potentially via the use of precision livestock farming (PLF) tools. One such promising approach is the use of vocal indicators. The acoustic structure of vocalizations and their functions were extensively studied in important livestock species, such as pigs, horses, poultry and goats, yet cattle remain understudied in this context to date. Cows were shown to produce two types vocalizations: low-frequency calls (LF), produced with the mouth closed, or partially closed, for close distance contacts and open mouth emitted high-frequency calls (HF), produced for long distance communication, with the latter considered to be largely associated with negative affective states. Moreover, cattle vocalizations were shown to contain information on individuality across a wide range of contexts, both negative and positive. Nowadays, dairy cows are facing a series of negative challenges and stressors in a typical production cycle, making vocalizations during negative affective states of special interest for research. One contribution of this study is providing the largest to date pre-processed (clean from noises) dataset of lactating adult multiparous dairy cows during negative affective states induced by visual isolation challenges. Here we present two computational frameworks - deep learning based and explainable machine learning based, to classify high and low-frequency cattle calls, and individual cow voice recognition. Our models in these two frameworks reached 87.2% and 89.4% accuracy for LF and HF classification, with 68.9% and 72.5% accuracy rates for the cow individual identification, respectively.

Assaf Shmuel, Oren Glickman, Teddy Lazebnik

The analysis of tabular datasets is highly prevalent both in scientific research and real-world applications of Machine Learning (ML). Unlike many other ML tasks, Deep Learning (DL) models often do not outperform traditional methods in this area. Previous comparative benchmarks have shown that DL performance is frequently equivalent or even inferior to models such as Gradient Boosting Machines (GBMs). In this study, we introduce a comprehensive benchmark aimed at better characterizing the types of datasets where DL models excel. Although several important benchmarks for tabular datasets already exist, our contribution lies in the variety and depth of our comparison: we evaluate 111 datasets with 20 different models, including both regression and classification tasks. These datasets vary in scale and include both those with and without categorical variables. Importantly, our benchmark contains a sufficient number of datasets where DL models perform best, allowing for a thorough analysis of the conditions under which DL models excel. Building on the results of this benchmark, we train a model that predicts scenarios where DL models outperform alternative methods with 86.1% accuracy (AUC 0.78). We present insights derived from this characterization and compare these findings to previous benchmarks.

Assaf Shmuel, Teddy Lazebnik, Oren Glickman et al.

Wildfires pose a significant natural disaster risk to populations and contribute to accelerated climate change. As wildfires are also affected by climate change, extreme wildfires are becoming increasingly frequent. Although they occur less frequently globally than those sparked by human activities, lightning-ignited wildfires play a substantial role in carbon emissions and account for the majority of burned areas in certain regions. While existing computational models, especially those based on machine learning, aim to predict lightning-ignited wildfires, they are typically tailored to specific regions with unique characteristics, limiting their global applicability. In this study, we present machine learning models designed to characterize and predict lightning-ignited wildfires on a global scale. Our approach involves classifying lightning-ignited versus anthropogenic wildfires, and estimating with high accuracy the probability of lightning to ignite a fire based on a wide spectrum of factors such as meteorological conditions and vegetation. Utilizing these models, we analyze seasonal and spatial trends in lightning-ignited wildfires shedding light on the impact of climate change on this phenomenon. We analyze the influence of various features on the models using eXplainable Artificial Intelligence (XAI) frameworks. Our findings highlight significant global differences between anthropogenic and lightning-ignited wildfires. Moreover, we demonstrate that, even over a short time span of less than a decade, climate changes have steadily increased the global risk of lightning-ignited wildfires. This distinction underscores the imperative need for dedicated predictive models and fire weather indices tailored specifically to each type of wildfire.

Roi Peleg, Yair Smadar, Teddy Lazebnik et al.

The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which often limit their ability to track complex gradient trends accurately. This fact can lead to a significant lag in trend identification and suboptimal optimization, particularly in highly dynamic gradient behavior. To address this fundamental limitation, we introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average. By incorporating an advanced tracking mechanism, FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimizes learning efficiency. Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures ranging from lightweight CNNs to Vision Transformers. Through rigorous benchmarking against state-of-the-art optimizers, FAME demonstrates superior accuracy and robustness. Notably, it offers high scalability, delivering substantial improvements across diverse model complexities, architectures, tasks, and benchmarks.

Teddy Lazebnik

Detecting and understanding out-of-distribution (OOD) samples is crucial in machine learning (ML) to ensure reliable model performance. Current OOD studies primarily focus on extrapolatory (outside) OOD, neglecting potential cases of interpolatory (inside) OOD. In this study, we introduce a novel perspective on OOD by suggesting it can be divided into inside and outside cases. We examine the inside-outside OOD profiles of datasets and their impact on ML model performance, using normalized Root Mean Squared Error (RMSE) and F1 score as the performance metrics on syntetically-generated datasets with both inside and outside OOD. Our analysis demonstrates that different inside-outside OOD profiles lead to unique effects on ML model performance, with outside OOD generally causing greater performance degradation, on average. These findings highlight the importance of distinguishing between inside and outside OOD for developing effective counter-OOD methods.

Noufa Haneefa, Teddy Lazebnik, Einav Peretz-Andersson

Manufacturing test flows in high-volume electronics production are typically fixed during product development and executed unchanged on every unit, even as failure patterns and process conditions evolve. This protects quality, but it also imposes unnecessary test cost, while existing data-driven methods mostly optimize static test subsets and neither adapt online to changing defect distributions nor explicitly control escape risk. In this study, we present an adaptive test-selection framework that combines offline minimum-cost diagnostic subset construction using greedy set cover with an online Thompson-sampling multi-armed bandit that switches between full and reduced test plans using a rolling process-stability signal. We evaluate the framework on two printed circuit board assembly stages-Functional Circuit Test and End-of-Line test-covering 28,000 board runs. Offline analysis identified zero-escape reduced plans that cut test time by 18.78% in Functional Circuit Test and 91.57\% in End-of-Line testing. Under temporal validation with real concept drift, static reduction produced 110 escaped defects in Functional Circuit Test and 8 in End-of-Line, whereas the adaptive policy reduced escapes to zero by reverting to fuller coverage when instability emerged in practice. These results show that online learning can preserve manufacturing quality while reducing test burden, offering a practical route to adaptive test planning across production domains, and offering both economic and logistics improvement for companies.

Ariel Rosenfeld, Teddy Lazebnik

Large Language Models (LLMs) are capable of generating text that is similar to or surpasses human quality. However, it is unclear whether LLMs tend to exhibit distinctive linguistic styles akin to how human authors do. Through a comprehensive linguistic analysis, we compare the vocabulary, Part-Of-Speech (POS) distribution, dependency distribution, and sentiment of texts generated by three of the most popular LLMS today (GPT-3.5, GPT-4, and Bard) to diverse inputs. The results point to significant linguistic variations which, in turn, enable us to attribute a given text to its LLM origin with a favorable 88\% accuracy using a simple off-the-shelf classification model. Theoretical and practical implications of this intriguing finding are discussed.

Teddy Lazebnik, Ariel Rosenfeld

Large Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM use, especially in scientific communication, genuine acknowledgment remains infrequent. A potential avenue to encourage accurate acknowledging of LLM-assisted writing involves employing automated detectors. Our evaluation of four cutting-edge LLM-generated text detectors reveals their suboptimal performance compared to a simple ad-hoc detector designed to identify abrupt writing style changes around the time of LLM proliferation. We contend that the development of specialized detectors exclusively dedicated to LLM-assisted writing detection is necessary. Such detectors could play a crucial role in fostering more authentic recognition of LLM involvement in scientific communication, addressing the current challenges in acknowledgment practices.

Uri Itai, Asael Bar Ilan, Teddy Lazebnik

Detecting out-of-distribution (OOD) data is a critical task for maintaining model reliability and robustness. In this study, we propose a novel anomaly detection algorithm that leverages the convex hull (CH) property of a dataset by exploiting the observation that OOD samples marginally increase the CH's volume compared to in-distribution samples. Thus, we establish a decision boundary between OOD and in-distribution data by iteratively computing the CH's volume as samples are removed, stopping when such removal does not significantly alter the CH's volume. The proposed algorithm is evaluated against seven widely used anomaly detection methods across ten datasets, demonstrating performance comparable to state-of-the-art (SOTA) techniques. Furthermore, we introduce a computationally efficient criterion for identifying datasets where the proposed method outperforms existing SOTA approaches.

Teddy Lazebnik

Data-driven models, in general, and machine learning (ML) models, in particular, have gained popularity over recent years with an increased usage of such models across the scientific and engineering domains. When using ML models in realistic and dynamic environments, users need to often handle the challenge of concept drift (CD). In this study, we explore the application of genetic algorithms (GAs) to address the challenges posed by CD in such settings. We propose a novel two-level ensemble ML model, which combines a global ML model with a CD detector, operating as an aggregator for a population of ML pipeline models, each one with an adjusted CD detector by itself responsible for re-training its ML model. In addition, we show one can further improve the proposed model by utilizing off-the-shelf automatic ML methods. Through extensive synthetic dataset analysis, we show that the proposed model outperforms a single ML pipeline with a CD algorithm, particularly in scenarios with unknown CD characteristics. Overall, this study highlights the potential of ensemble ML and CD models obtained through a heuristic and adaptive optimization process such as the GA one to handle complex CD events.

Bilge Taskin, Wenxiong Xie, Teddy Lazebnik

Symbolic regression (SR) has emerged as a powerful tool for automated scientific discovery, enabling the derivation of governing equations from experimental data. A growing body of work illustrates the promise of integrating domain knowledge into the SR to improve the discovered equation's generality and usefulness. Physics-informed SR (PiSR) addresses this by incorporating domain knowledge, but current methods often require specialized formulations and manual feature engineering, limiting their adaptability only to domain experts. In this study, we leverage pre-trained Large Language Models (LLMs) to facilitate knowledge integration in PiSR. By harnessing the contextual understanding of LLMs trained on vast scientific literature, we aim to automate the incorporation of domain knowledge, reducing the need for manual intervention and making the process more accessible to a broader range of scientific problems. Namely, the LLM is integrated into the SR's loss function, adding a term of the LLM's evaluation of the SR's produced equation. We extensively evaluate our method using three SR algorithms (DEAP, gplearn, and PySR) and three pre-trained LLMs (Falcon, Mistral, and LLama 2) across three physical dynamics (dropping ball, simple harmonic motion, and electromagnetic wave). The results demonstrate that LLM integration consistently improves the reconstruction of physical dynamics from data, enhancing the robustness of SR models to noise and complexity. We further explore the impact of prompt engineering, finding that more informative prompts significantly improve performance.

Assaf Shmuel, Oren Glickman, Teddy Lazebnik

Deep learning (DL) models have gained prominence in domains such as computer vision and natural language processing but remain underutilized for regression tasks involving tabular data. In these cases, traditional machine learning (ML) models often outperform DL models. In this study, we propose and evaluate various data augmentation (DA) techniques to improve the performance of DL models for tabular data regression tasks. We compare the performance gain of Neural Networks by different DA strategies ranging from a naive method of duplicating existing observations and adding noise to a more sophisticated DA strategy that preserves the underlying statistical relationship in the data. Our analysis demonstrates that the advanced DA method significantly improves DL model performance across multiple datasets and regression tasks, resulting in an average performance increase of over 10\% compared to baseline models without augmentation. The efficacy of these DA strategies was rigorously validated across 30 distinct datasets, with multiple iterations and evaluations using three different automated deep learning (AutoDL) frameworks: AutoKeras, H2O, and AutoGluon. This study demonstrates that by leveraging advanced DA techniques, DL models can realize their full potential in regression tasks, thereby contributing to broader adoption and enhanced performance in practical applications.

Adi Shuchami, Teddy Lazebnik

Large-scale crises, including wars and pandemics, have repeatedly shaped human history, and their simultaneous occurrence presents profound challenges to societies. Understanding the dynamics of epidemic spread during warfare is essential for developing effective containment strategies in complex conflict zones. While research has explored epidemic models in various settings, the impact of warfare on epidemic dynamics remains underexplored. In this study, we proposed a novel mathematical model that integrates the epidemiological SIR (susceptible-infected-recovered) model with the war dynamics Lanchester model to explore the dual influence of war and pandemic on a population's mortality. Moreover, we consider a dual-use military and civil healthcare system that aims to reduce the overall mortality rate which can use different administration policies. Using an agent-based simulation to generate in silico data, we trained a deep reinforcement learning model for healthcare administration policy and conducted an intensive investigation on its performance. Our results show that a pandemic during war conduces chaotic dynamics where the healthcare system should either prioritize war-injured soldiers or pandemic-infected civilians based on the immediate amount of mortality from each option, ignoring long-term objectives. Our findings highlight the importance of integrating conflict-related factors into epidemic modeling to enhance preparedness and response strategies in conflict-affected areas.

Amit Bengal, Teddy Lazebnik

Scientific research increasingly depends on multi-author collaboration, yet the systems used to allocate authorship credit remain vulnerable to conflict, strategic behavior, and project breakdown. Although prior work has shown that authors may rationally issue ultimatums over authorship order within a single manuscript, much less is known about how such behavior unfolds over repeated collaborations embedded in evolving academic networks. In this study, we develop a repeated, networked game-theoretic model of co-authorship in which researchers form collaborations over time, accumulate reputation through an evolving friendship network, and, in a subset of cases, learn strategic behavior through deep reinforcement learning. Using large-scale agent-based simulations, we compare myopic and forward-looking authors across mixed populations. We find that strategic agents do not raise fewer ultimatums than greedy agents, but instead learn to avoid insisting after rejection, thereby eliminating destructive manuscript termination. As strategic prevalence increases, paper destruction falls from 0.120 to 0.000 per paper, completion rates rise from 0.853 to 0.970, and average completed papers per agent increase from 15.2 to 16.9. Strategic agents also obtain a substantial utility advantage, reaching 30.8\% when rare, while overall inequality remains stable. These results suggest that reputational feedback and long-term incentives can make academic collaboration more resilient, offering a computational testbed for designing fairer and more productive authorship policies.

Lukas Toral, Teddy Lazebnik

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these are often extremely specific and require the developer's professionalism and dedicated expertise in the problem's domain. Tackling this challenge, in this study, we explore the effectiveness of pre-trained Large Language Models (LLMs) as tutors in a student-teacher architecture with RL algorithms, hypothesizing that LLM-generated guidance allows for faster convergence. In particular, we explore the effectiveness of reusing the LLM's advice on the RL's convergence dynamics. Through an extensive empirical examination, which included 54 configurations, varying the RL algorithm (DQN, PPO, A2C), LLM tutor (Llama, Vicuna, DeepSeek), and environment (Blackjack, Snake, Connect Four), our results demonstrate that LLM tutoring significantly accelerates RL convergence while maintaining comparable optimal performance. Furthermore, the advice reuse mechanism shows a further improvement in training duration but also results in less stable convergence dynamics. Our findings suggest that LLM tutoring generally improves convergence, and its effectiveness is sensitive to the specific task, RL algorithm, and LLM model combination.

Osnat Mokryn, Teddy Lazebnik, Hagit Ben Shoshan

The analysis of high-dimensional timeline data and the identification of outliers and anomalies is critical across diverse domains, including sensor readings, biological and medical data, historical records, and global statistics. However, conventional analysis techniques often struggle with challenges such as high dimensionality, complex distributions, and sparsity. These limitations hinder the ability to extract meaningful insights from complex temporal datasets, making it difficult to identify trending features, outliers, and anomalies effectively. Inspired by surprisability -- a cognitive science concept describing how humans instinctively focus on unexpected deviations - we propose Learning via Surprisability (LvS), a novel approach for transforming high-dimensional timeline data. LvS quantifies and prioritizes anomalies in time-series data by formalizing deviations from expected behavior. LvS bridges cognitive theories of attention with computational methods, enabling the detection of anomalies and shifts in a way that preserves critical context, offering a new lens for interpreting complex datasets. We demonstrate the usefulness of LvS on three high-dimensional timeline use cases: a time series of sensor data, a global dataset of mortality causes over multiple years, and a textual corpus containing over two centuries of State of the Union Addresses by U.S. presidents. Our results show that the LvS transformation enables efficient and interpretable identification of outliers, anomalies, and the most variable features along the timeline.

Teddy Lazebnik, Liron Simon-Keren

Genome data are crucial in modern medicine, offering significant potential for diagnosis and treatment. Thanks to technological advancements, many millions of healthy and diseased genomes have already been sequenced; however, obtaining the most suitable data for a specific study, and specifically for validation studies, remains challenging with respect to scale and access. Therefore, in silico genomics sequence generators have been proposed as a possible solution. However, the current generators produce inferior data using mostly shallow (stochastic) connections, detected with limited computational complexity in the training data. This means they do not take the appropriate biological relations and constraints, that originally caused the observed connections, into consideration. To address this issue, we propose cancer-inspired genomics mapper model (CGMM), that combines genetic algorithm (GA) and deep learning (DL) methods to tackle this challenge. CGMM mimics processes that generate genetic variations and mutations to transform readily available control genomes into genomes with the desired phenotypes. We demonstrate that CGMM can generate synthetic genomes of selected phenotypes such as ancestry and cancer that are indistinguishable from real genomes of such phenotypes, based on unsupervised clustering. Our results show that CGMM outperforms four current state-of-the-art genomics generators on two different tasks, suggesting that CGMM will be suitable for a wide range of purposes in genomic medicine, especially for much-needed validation studies.

Teddy Lazebnik, Liron Simon-Keren

Data encoding is a common and central operation in most data analysis tasks. The performance of other models downstream in the computational process highly depends on the quality of data encoding. One of the most powerful ways to encode data is using the neural network AutoEncoder (AE) architecture. However, the developers of AE cannot easily influence the produced embedding space, as it is usually treated as a black box technique. This means the embedding space is uncontrollable and does not necessarily possess the properties desired for downstream tasks. This paper introduces a novel approach for developing AE models that can integrate external knowledge sources into the learning process, possibly leading to more accurate results. The proposed Knowledge-integrated AutoEncoder (KiAE) model can leverage domain-specific information to make sure the desired distance and neighborhood properties between samples are preservative in the embedding space. The proposed model is evaluated on three large-scale datasets from three scientific fields and is compared to nine existing encoding models. The results demonstrate that the KiAE model effectively captures the underlying structures and relationships between the input data and external knowledge, meaning it generates a more useful representation. This leads to outperforming the rest of the models in terms of reconstruction accuracy.