Emplois actuels liés à Machine Learning Intern Stochastic Gradient Descent - Lyon - Nova In Silico company
-
Machine Learning Engineer
il y a 5 jours
Lyon, France Inetum Temps plein**Description de l'entreprise** Chez Inetum, nous sommes une entreprise de conseil de premier plan dédiée à la conduite de l'innovation et à la résolution de défis commerciaux complexes. Le FabLab s'engage à repousser les limites de la technologie et à favoriser une culture de créativité et de collaboration. Avec un fort accent sur l'exploitation...
-
Internship - Machine Learning Engineer
il y a 2 semaines
Lyon, France Solvay Temps pleinSolvay is a science company whose technologies bring benefits to many aspects of daily life. Our purpose—we bond people, ideas and elements to reinvent progress—is a call to go beyond, to reinvent future forms of progress and create sustainable shared value for all through the power of science. In a world facing an ever-growing population and quest for...
-
Machine Learning
il y a 6 jours
Lyon, France Esker Temps plein**Lyon**: **Missions**: Nous possédons de nombreux logs Kibana traduisant l’utilisation de nos algorithmes de Machine Learning. L’objectif est d’être capable d’automatiser leurs récupérations, de présenter les statistiques sur un portail pour ainsi rendre possible la génération d’alertes. **Environnement de travail**: Vous aurez à...
-
QSP Modeling intern
il y a 2 jours
Lyon, France Nova In Silico company Temps pleinNova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities...
-
Machine Learning Engineer
il y a 1 semaine
Lyon, France SantéVet Temps plein**Direction Système d’Informations - Informatique & Télécommunications -** **France, Auvergne-Rhône-Alpes, Lyon, 69007, 35 Rue de Marseille** **Notre entreprise** Rejoignez Santévet Group, leader de l'assurance santé animale en France et en Belgique, avec des activités établies en Allemagne, Espagne et Italie. Avec 450 collaborateurs répartis...
-
Machine Learning
il y a 1 semaine
Lyon, France Esker Temps plein**Lyon**: **Missions**: Nous possédons de nombreux logs Kibana traduisant l’utilisation de nos algorithmes de Machine Learning. L’objectif est d’être capable d’automatiser leurs récupérations, de présenter les statistiques sur un portail pour ainsi rendre possible la génération d’alertes. **Environnement de travail**: Vous aurez à...
-
Machine Learning
il y a 6 jours
Lyon, France Esker Temps plein**Lyon**: **Missions**: Déterminer les performances du moteur de recherche appliqué à notre documentation Proposer des améliorations pour une nouvelle version **Environnement de travail**: Vous aurez à disposition un poste de travail au sein d’une équipe R&D d’Esker, avec un parc de machines performantes à disposition. Cela regroupe des machines...
-
Machine Learning Engineer
il y a 5 jours
Lyon, France Smily RH Temps pleinA la croisée des mondes entre la Data Science et le Data Ingénierie, le Machine Learning Engineer est responsable du déploiement et du maintien des modèles de machine learning à l'échelle. En collaboration étroite avec les Data Analysts, Data Scientists et Data Engineers, vous désignez et implémentez des solutions ML qui optimisent le traitement des...
-
Machine Learning
il y a 1 semaine
Lyon, France Esker Temps plein**Lyon**: Avec l’émergence des algorithmes d’intelligence artificiel aidant les développeurs tels que Copilot, nous souhaitons étudier la pertinence d’un algorithme semblable. Celle-ci sera entraînée à partir des nombreuses lignes de codes rédigées au sein d’Esker à destination de nos consultants. **Missions**: - Effectuer un état de...
-
Machine Learning
il y a 6 jours
Lyon, France Esker Temps plein**Lyon**: Avec l’émergence des algorithmes d’intelligence artificiel aidant les développeurs tels que Copilot, nous souhaitons étudier la pertinence d’un algorithme semblable. Celle-ci sera entraînée à partir des nombreuses lignes de codes rédigées au sein d’Esker à destination de nos consultants. **Missions**: Effectuer un état de l’art...
Machine Learning Intern Stochastic Gradient Descent
il y a 3 semaines
Nova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities and benefit from a steep learning curve, supported by a highly motivated team. Learn more at www.novainsilico.ai .KeywordsExpectation Maximization, Gradient Descent, Non-Linear Mixed-Effects Model, Surrogate Model, PyTorchBackgroundQuantitative Systems Pharmacology and its ChallengesQuantitative Systems Pharmacology (QSP) is a critical discipline in modern drug development. It involves creating complex, mechanistic mathematical models that describe the dynamic interactions between a drug and a biological system. These models integrate pathophysiology and pharmacology to predict a drug’s effect, safety, and efficacy across diverse patient populations. At Nova In Silico, our R&D efforts are focused on building and applying these high-fidelity QSP models.A significant challenge arises when fitting these models to real-world clinical data. To account for variability between individuals, QSP models are often formulated as Non-Linear Mixed-Effects (NLME) models. Parameter estimation for NLME models, which is typically performed via Maximum Likelihood Estimation (MLE), is a difficult and computationally intensive task. Traditional estimation algorithms can take hours or even days to converge, creating a substantial bottleneck in the R&D pipeline.PyTorch-based Surrogate ModelsTo address this computational bottleneck, Nova In Silico has successfully developed surrogate models for some of our key QSP models. These surrogates, built using the PyTorch deep learning framework, are lightweight, fast-to-execute approximations of the full, complex QSP models. They are designed to capture the essential input-output behavior of the original model while dramatically reducing computation time.This speed-up has enabled us to more efficiently perform parameter estimation. Currently, we leverage our surrogate models within Expectation-Maximization (EM) type algorithms. EM is a powerful and standard method for finding maximum likelihood estimates in models with latent variables (such as the random effects in NLME models). This approach has proven effective for our existing model structures.While effective, EM-type algorithms are often tailored to specific model structures and statistical assumptions. As our R&D pipeline evolves, we aim to explore more diverse and complex surrogate model architectures and apply them to various types of clinical data. The mathematical framework of EM can be restrictive in these more general cases.Stochastic Gradient Descent (SGD) offers a compelling and flexible alternative, as these algorithms:Can be applied to a much broader family of models and data structures.Are often more computationally efficient, as they can process large datasets in small batches.Integrate natively with the PyTorch ecosystem, as gradient computation is the framework’s core function.ObjectiveThe intern will implement the stochastic approximation gradient algorithm, drawing from the principles in the reference articles, and apply it to our existing surrogate models. This will equip Nova In Silico with a novel, flexible, and powerful estimation tool, expanding our capabilities to fit next-generation QSP models to complex clinical data.You areA team player , a good listener, and an effective communicatorCurious and proactive , ready to face real-life engineering challengesAutonomous and self-motivated with strong analytical and problem-solving skillsEager to learn mathematical modeling and simulations of biological systemsWilling to explore latest advances in science and technologyResponsive and capable of tackling time-sensitive issues with agilityYou willReview the scientific literature on relevant machine learning algorithmsPrototype the stochastic gradient algorithm under Nova’s specific constraintsEvaluate benchmark cases against the alternative SAEM algorithmIntegrate solutions into Nova’s simulation platformMethodology and technical skillsWe are looking for people who know some of the following or are eager learn and work with themMachine learning in Python, PyTorchStatistical modeling, NLME modelsA professional English level (written and oral) is required for this role. #J-18808-Ljbffr
