Lawrence Livermore National Laboratory

The Machine Learning group has expertise in developing and tailoring Machine Learning algorithms to solve classification, anomaly/change detection, prediction, and clustering tasks on "Big Data". Our researchers have extensive experience with Random Forests, Deep Neural Networks, SVMs, Mixture Models, HMMs and Dynamic Bayesian Networks, Ensemble Methods, and Big Data frameworks like Hadoop, Storm, and Spark.

Brenda Ng, 925-422-4553
Group Leader

ContactPhoneDiscipline Expertise
Lance Bentley-Tammero 925-423-9545 Radiation detection, epidemiological modeling, biothreat detection, uncertainty estimation, bioengineering
Jose Cadena Pico 925-422-7941 Network data analysis, anomaly detection in network data, graph theory, statistical modeling, algorithm design, discrete optimization
Barry Chen 925-423-9429 Ensemble methods, deep learning, density estimation, graphical models, speech recognition, network security, Hadoop, Spark
Thomas Desautels 925-423-3525 Active learning, Gaussian processes, Bayesian methods, control theory, and biomedical applications
Gerald Friedland 925-422-2031 Processing of multimedia data, multimodal integration, unsupervised machine learning, speech recognition, privacy. Adjunct faculty at UC Berkeley
Andre Goncalves 925-423-2297 Machine learning, multi-task learning, probabilistic graphical models, optimization, sparse models, deep learning, speech processing
Brenda Ng 925-422-4553 Graphical models and dynamic Bayesian networks, multi-agent sequential decision-making under uncertainty, modular uncertainty quantification, deep learning
Priyadip Ray 925-423-4232 Statistical signal processing, Graphical models, Bayesian statistical modelling, Multi-sensor and multi-modal data fusion, Distributed inference over large networks, and Cognitive communications and networks
David Widemann 925-423-4351 Recurrent neural networks for natural language processing and multimodal learning, neuromorphic computing with TrueNorth and spiking neural networks, signal processing for sensor systems using sparse representations and compressive sensing