Samet Oymak

Samet Oymak

By |

I am interested in principled approaches to machine learning with focus on data-driven decision making, deep learning foundations, and heterogeneous data. My research integrates optimization methods (specifically convex and first-order) and statistical learning theory to design efficient algorithms/architectures that address these data-science problems.

Additional Information

How did you end up where you are today?

I obtained my PhD degree from Caltech in 2015 where I received a Charles Wilts Prize for the best departmental thesis. During postdoc, I was at UC Berkeley as a Simons Fellow. After spending few years in industry, I joined UC Riverside where I received NSF CAREER and Google Research Scholar Awards. Starting Fall 2023, I will be joining EECS department at U-M.

An interesting fact: The elegance of mathematics has always amazed me and led me to participate in International Math Olympiad.
Also, my Erdos number is 3!


Accomplishments and Awards

Talia Moore

Talia Moore

By |

My research involves discovery, modeling, and design for comparative biomechanics and bio-inspired robotics. I develop new information-based methods to analyze the behavior and locomotion of animals in natural environments and use laboratory-based experiments to build detailed models of how animal motion is generated by muscles, tendons, and bones. I’ve developed machine learning methods to automatically segment non-standard animals in photographs for taxonomically-broad phylogenetic comparative analyses of color pattern and behavior. I also use Finite Element Analysis to understand how the evolution of 3-dimensional shape in animal bones and teeth have adapted to a variety of ecological situations, such as novel substrates or diet.

Because FEA and other biomechanical methods are so computationally intensive, I’ve adopted a surrogate model approach that uses Bayesian Optimization to perform stimulus selection and make accurate predictions of sample performance with the minimum number of model datapoints. I’ve also begun applying this surrogate model approach to explore the design space of bio-inspired grippers made from dielectric fluid actuators. Data-driven modeling also informs the design rigid legged robots in my lab, which we will use to test hypotheses regarding how limb shape affects overall locomotion.

Finite element modeling of snake fangs helps us understand how fang shape can be adapted for different types of loading conditions, and therefore prey types. We use Bayesian Optimization to select which species to analyze for our surrogate model, which minimizes the computation time while maximizing prediction accuracy.

Additional Information

What are some of your most interesting projects?

Jerboas are bipedal desert rodents that hop erratically with zig-zag trajectories when they are escaping from predators (some describe them as “ricochetal”). These animals are about the size of your fist, but they can jump over 3 feet straight up in the air or forwards. Little was known about their locomotion, and the majority of biomechanical locomotion research was performed in lab environments on treadmills. However, training an animal to run on a treadmill reduces the variability in direction and speed that the animals would need to survive in the wild. So I went out into the desert and filmed these animals jumping and running on their natural substrates.

To understand how these trajectories might confound predators, I measured the unpredictability (or entropy) and found that bipedal desert rodents are much less predictable than quadrupedal desert rodents. Then, taking a closer look using high-speed video cameras, I determined that they have at least 5 distinct bipedal gaits. Using both kinematic and dynamic data, I built a modified Spring-Loaded Inverted Pendulum model with a torsional spring to control the neutral leg swing angle. I then performed a numerical search using a continuing approach to test neighboring parameter values for viability to discover bifurcations in gait structure. I found that by decoupling the neutral leg swing angle between left and right legs, the model was capable of transitioning between gaits across the entire speed range, just as the real jerboas do. This research will be used to inform the design of controllers for legged robots to switch gaits smoothly across a wide range of speeds.

How did you end up where you are today?

I started off not knowing at all what I wanted to do, but enjoying martial arts. A friend told me to check out the biomechanics class in my last year in undergrad at UC Berkeley, and I was hooked! I joined the lab immediately and worked there for two years after graduating. I wanted to learn everything, so I worked on a different project with a different graduate student every day of the week. During that time, I worked with cockroaches, geckos, iguanas, and agama lizards, learning about how they generate and control their motions. I was also lucky to get hands-on experience with designing and building bio-inspired robots and using them to test biological hypotheses to reveal fundamental principles of animal locomotion.

After that, I went on to study biomechanics and evolutionary biology at Harvard, where I was introduced to jerboas for the first time. They are such strange and wonderful creatures that I knew I wanted to study them for the rest of my life. I came to UM in 2015 and worked as a postdoc in Ecology and Evolutionary Biology, where I developed a new modular ethogram system to analyze snake anti-predator behaviors and design snake-mimicking soft robots. Then I became a Research Scientist in the Robotics Institute, followed by being hired as an Assistant Professor in Mechanical Engineering in January of 2021. Now I am appointed in both Robotics and Mechanical Engineering and have affiliations with Ecology and Evolutionary Biology and the Museum of Zoology.

What is the most significant scientific contribution you would like to make?

I really want to build tools to bridge the gap between biology and engineering. So many biological questions are constrained by the technology we have available. By forming connections between these fields, I have already facilitated more quantitative study of non-steady-state locomotion in natural environments. There is also a big gap between what motions animals and robots are capable of performing. I hope to learn strategies from animals and design robots to succeed in unstructured and complex environments.

What makes you excited about your data science and AI research?

I’m extremely excited that data science is making it possible to analyze the types of large datasets that we can collect from animals. There is no limit to the amount of data you can collect about animal locomotion, behavior, appearance, or structure, and the types of studies that used to take decades can now be done in a semester thanks to data science and AI. This makes it possible to integrate information from multiple different data streams and understand more complex relationships between animals, their environments, and how these relationships change through space and time.

What are 1-3 interesting facts about yourself?

I’ve done fieldwork in Malaysia, China, Australia, California, the Bahamas and Peru. I think it’s incredibly important to examine animals in their natural habitats, because our assumptions about their behaviors might be totally wrong if we only see them in zoos or labs.
The first sentence I try to learn in every language is “Where is the bathroom?”
My two rules for fieldwork are: 1) Never stop moving and 2) Never sit down or lean on anything.

Sabine Loos

Sabine Loos

By |

My research focuses on natural hazards and disaster information, everything from understanding where disaster data comes from, how it’s used, and its implications to design improved disaster information systems that prioritize the human experience and lead to more effective and equitable outcomes.

My lab takes a user-centered and data-driven approach. We aim to understand user needs and the effect of data on users’ decisions through qualitative research, such as focus groups or workshops. We then design new information systems through geospatial/GIS analysis, risk analysis, and statistical modeling techniques. We often work with earth observation, sensor, and survey data. We consider various aspects of disaster information, whether it be the hazard, its physical impacts, its social impacts, or a combination of the three.

I also focus on the communication of information, through data visualization techniques, and host a Risk and Resilience DAT/Artathon to build data visualization capacity for early career professionals.

Geospatial model for predicting inequities in recovery from the 2015 Nepal earthquake

Brian Weeks

Brian Weeks

By |

In the Weeks lab, we work at the intersection of ecology and evolutionary biology to try to understand how large scale biodiversity patterns arose, and what they might tell us about how natural systems will respond to human activities. We have a particular focus on the impacts of climate change on birds, and are increasingly using computer vision tools to measure bird traits on large numbers of photographs of museum skeletal specimens. This new approach has enabled us to generate skeletal trait datasets at an unprecedented scale that have begun to reveal some fascinating patterns in bird morphology that we are using to understand biotic responses to global change.

Shai Revzen

Shai Revzen

By | | No Comments

“Professor Revzen and his team at the Biologically Inspired Robotics and Dynamical Systems (BIRDS) Lab are working on discovering, modeling, and reproducing the strategies animals use when interacting with physical objects. This work consists of collaboration with biomechanists to analyze experimental data, developing new mathematical tools for modeling and estimation of model parameters, and construction of robots which employ the new principles.”

Mojtaba Akhavan Tafti

Mojtaba Akhavan-Tafti

By | | No Comments

Comprehensive investigations of solar, interplanetary, and Earth’s Magnetospheric systems utilizing state-of-the-art in-situ observations and global simulations. The research topics of interest involve critical open science questions, including solar coronal heating, solar wind acceleration and heating processes, magnetospheric dynamics, and space weather predictions. The research tools include statistical data analyses to generate physics-based models.

 


Accomplishments and Awards

Dan Rabosky

Dan Rabosky

By |

The Rabosky lab seeks to understand how and why life on Earth became so diverse. We focus primarily on large-scale patterns of species diversification (speciation and extinction) and on the tempo and mode of phenotypic evolution, to better understand what regulates the “amount” of biodiversity through Deep Time. To this end, we develop theoretical frameworks and computational tools for studying evolutionary dynamics using DNA-sequence-based evolutionary trees (phylogenies), the fossil record, as well as phenotypic data from present-day species (morphology, ecology). We develop and apply a range of methods involving supervised and unsupervised learning, including Markov chain Monte Carlo, hierarchical mixture models, hidden Markov models, latent feature models, and more. We are increasingly interested in complex morphological and ecological traits, which – due to a rapidly expanding data universe – represent a tremendous opportunity for the field to answer long-standing questions about how organisms evolve. At these same time, we are embracing the analytical challenges of these data, because fully realizing their potential requires the development of new analytical paradigms that go beyond the limitations of traditional parametric models for low-dimensional data.

Automatic feature identification from a large-scale evolutionary tree (phylogeny) using a compound model of the generating process (speciation, extinction) developed in the Rabosky lab. Colors correspond to distinct evolutionary rate regimes as estimated using Markov chain Monte Carlo. This method revealed widespread heterogeneity in the rate of species formation during 350 million years of ray-finned fish evolution. Warm colors = fast rates; cool colors = slow rates.

Automatic feature identification from a large-scale evolutionary tree (phylogeny) using a compound model of the generating process (speciation, extinction) developed in the Rabosky lab. Colors correspond to distinct evolutionary rate regimes as estimated using Markov chain Monte Carlo. This method revealed widespread heterogeneity in the rate of species formation during 350 million years of ray-finned fish evolution. Warm colors = fast rates; cool colors = slow rates.


Accomplishments and Awards

Photograph of Alison Davis Rabosky

Alison Davis Rabosky

By |

Our research group studies how and why an organism’s traits (“phenotypes”) evolve in natural populations. Explaining the mechanisms that generate and regulate patterns of phenotypic diversity is a major goal of evolutionary biology: why do we see rapid shifts to strikingly new and distinct character states, and how stable are these evolutionary transitions across space and time? To answer these questions, we generate and analyze high-throughput “big data” on both genomes and phenotypes across the 18,000 species of reptiles and amphibians across the globe. Then, we use the statistical tools of phylogenetic comparative analysis, geometric morphometrics of 3D anatomy generated from CT scans, and genome annotation and comparative transcriptomics to understand the integrated trait correlations that create complex phenotypes. Currently, we are using machine learning and neural networks to study the color patterns of animals vouchered into biodiversity collections and test hypotheses about the ecological causes and evolutionary consequences of phenotypic innovation. We are especially passionate about the effective and accurate visualization of large-scale multidimensional datasets, and we prioritize training in both best practices and new innovations in quantitative data display.

Nate Sanders

Nate Sanders

By |

My research interests are broad, but generally center on the causes and consequences of biodiversity loss at local, regional, and global scales with an explicit focus on global change drivers. Our work has been published in Science, Nature, Science Advances, Global Change Biology, PNAS, AREES, TREE, and Ecology Letters among other journals. We are especially interested in using AI and machine learning to explore broad-scale patterns of biodiversity and phenotypic variation, mostly in ants.