Congratulations to Prof. Percy Pierre, Chair of the BEACON Diversity Steering Committee

On April 10, 2018, BEACON’s own Prof. Percy Pierre, Chair of the BEACON Diversity Steering Committee and contributor to BEACON from its earliest proposal days, was honored with the Historical Leader Award of the MSU Black Faculty, Staff and Administrators Association (BFSAA). BEACON’s Business Manager, Connie James, who is Recording Secretary of the group, was on hand to describe to the group some of Percy’s most significant contributions.  His distinguished career has spanned serving as a White House Fellow, where he was deputy to the Assistant to the President for Urban Affairs; as Dean of Engineering at Howard University; Assistant Secretary of the Army for Research, Development and Acquisition, and later Acting Secretary of the Army; President of Prairie View A&M University; Vice President for Research and Graduate Studies at MSU, and Professor of Electrical and Computer Engineering at MSU.  In the latter role, he has mentored over 200 minority graduate students to degrees in Engineering, the accomplishment of which he is most proud. Dr. Pierre was a principal architect of the national minority engineering effort, co-chairing the 1973 National Academy of Engineering Symposium that launched the effort. He served as the program officer for minority engineering at the Alfred P. Sloan Foundation, where his efforts resulted in funding of many minority engineering organizations, including NACME, GEM, MESA, DAPCEP, and SECME. He was elected to membership in the National Academy of Engineering, and has received many other awards and honors.

Percy’s wisdom and vast experience have helped to shape BEACON’s diversity efforts to be among the most successful of any of NSF’s Science and Technology Centers. We all owe him a debt of gratitude for the positive and supportive atmosphere that pervades all of BEACON today.

Posted in Member Announcements | Tagged | Comments Off on Congratulations to Prof. Percy Pierre, Chair of the BEACON Diversity Steering Committee

Exploring the evolution of troglodytes?

This post is by MSU postdoc John Phillips

Some of you may be familiar with the term ‘troglodyte’, which is a somewhat old-timey derogatory term for an unintelligent person. The Greek root troglo- means “cave” so a troglodyte is a cave person. While we use(d?) this as an insult, caves are actually fascinating places to study, explore, and even earn a Ph.D!

Caves serve as fascinating evolutionary laboratories and are home to a variety of species, many of which have converged on adaptations allowing them to thrive underground. From invertebrates to fish to salamanders, cave-obligate species have repeatedly lost vision/eyes, deactivated pigments, slowed metabolic rates, and evolved behaviors to survive in a nutrient poor environment where most organic material gets washed in from the surface! Many cave food webs are based on bat guano, thus highlighting the importance of bats to the persistence of many cave species. Additionally, cave species are often overlooked when it comes to conservation efforts. This can be a HUGE problem because cave species are imperiled when you combine habitat-specialization, high rates of endemism and low rates of dispersal with a suite of anthropogenic threats (think groundwater pollution or climate change).

Cave crayfish

Cave millipede

Much of my research involves the study of biogeography–I like discovering when and how species got to where they are. Cave systems seemed like an excellent ecosystem which has been relatively ignored in genetic studies. Furthermore, I was living only an hour from the beautiful Ozark Plateau, which is known as a biodiversity hotspot with many endemic species (including several cave species) but was lacking for studies testing biogeographic hypotheses which can be crucial for conservation efforts. The Ozarks are made from limestone karst, which is easily fragmentable rock and often dissolves in ways that produce amazing caves and subsequently their fauna. There are over 10,000 caves in the Ozark Plateau, many of which have not been well-studied to understand their biodiversity.

Gyrinophilus palleucus

In one of my studies, I looked at the Grotto Salamander (Eurycea spelaea) that is unique among salamanders. While there are only 12 described cave-obligate species of salamanders in the world almost are paedomorphic, which means they retain characteristics of larvae throughout their life (predominantly gills and a fully aquatic lifestyle, see picture of the Tennessee Cave Salamander (Gyrinophilus palleucus)). Typically, these salamanders will never leave the cave. However, the Grotto Salamander larvae (pictured) can inhabit surface streams and possess fully functional eyes. After several years as larvae they metamorphose into adults, losing their gills, pigments, and eyes, whereupon they leave the water and are free to climb about the cave walls.


Grotto Salamander larvae (Eurycea spelaea)

As a group, salamanders employ various life-history strategies, but none as unique as this. All grotto salamanders obligately metamorphose, indicating this an evolved strategy as opposed to something environmentally driven. Because of this unique life-history shift, my colleagues (Ron Bonett: University of Tulsa, Sarah Emel: UMass – Amherst, and Danté Fenolio: San Antonio Zoo) were interested in testing colonization patterns of Grotto Salamanders across the Ozark Plateau. Grotto Salamanders occupy a much larger range than other cave salamanders (See #1 on the map below). Could this be due to the surface-dwelling larvae following drainage patterns? Or do the terrestrial adults disperse underground more readily that their fully aquatic relatives? SPOILER ALERT: It is actually hard to distinguish between the two causes, but using the DNA of these salamanders we find that the geologic history of the Ozarks and major changes in drainage basins of the regions combine to explain a majority of genetic variation.

How much genetic variation? Well we have discovered three highly divergent lineages of grotto salamanders dating back 10–15 million years. While these three groups have not changed noticeably in their morphological features (so far as we can tell yet), they are considerably more different genetically than many other species of salamanders are to one another. Therefore, my colleagues and I have “re-elevated” each lineage to species status based on strongly supported genetic differences and geographical separation (see lower map). This phenomenon–where multiple species are unknowingly classified as a single species–is known as “cryptic speciation”. This has turned out to be quite common in cave species. Partially due to their lack of study. Hopefully our efforts here will help conservation agencies (in Oklahoma, Arkansas, Missouri, and Kansas) better manage these lineages across their range.

Eurycea braggi

Eurycea nerea

For more info on my Grotto Salamander work, feel free to read: Phillips, J.G., Fenolio, D.B., Emel, S.L., Bonett, R.M., 2017. Hydrologic and geologic history of the Ozark Plateau drive phylogenomic patterns in a cave-obligate salamander. J. Biogeogr. 44, 2463–2474.

This work was done as part of my Ph.D. at the University of Tulsa in Oklahoma. Currently I am a postdoc at MSU with BEACON, EEBB, and the Department of Integrative Biology where I study evolution in Stickleback fish! Hopefully I will have another blog post down the line as my work here progresses.


Posted in BEACON Researchers at Work, Notes from the Field | Tagged , , , , , | Comments Off on Exploring the evolution of troglodytes?

NCAT Research Excellence Award

We are very excited to congratulate Dr. Joe Graves and the entire BEACON team at NCAT for receiving this year’s Research Excellence Award for Interdisciplinary Team. Every spring, NCAT celebrates outstanding accomplishments and efforts of faculty innovators, mentors and dynamic leaders with a Celebration of Faculty Excellence in Research and Teaching Banquet. The Interdisciplinary Team award honors research teams that break down the traditional boundaries of academic disciplines.

Back row (L—R) Keara Coffield (G), Dr. Misty Thomas, Dr. Joe Graves, Kimberly Hunter (UG), Dr. Jude Akamu Ewunkem, Sada Boyd (G). Front Row: Danielle Williams (G), Dr. Jessica Han, Anuolowapo Odelade (G), Adero Campbell (G); Janelle Robinson (G).

Posted in Uncategorized | Comments Off on NCAT Research Excellence Award

Art and Science, Science and Art: Science outreach to young artists

This post is by MSU grad student Cybil Nicole “Nikki” Cavalieri

Figure 1: Leonardo da Vinci Antonym of a women; Ernst Haeckel Thalamorpha Plate; Young REACH artist with a Terror Bird

“I am not good at science, I am more artistic.”

“I have decided to drop biology, I am changing my degree to packaging I want to work in a field that lets me be creative.”

“I can’t draw the shape of this skull I am not an artist.”

These are things undergraduate students at Michigan State have told me. Science and art have not always existed in the polarized state we think they do. They have always been connected. In fact, the similarities between artists and scientists far outweigh the stereotypical differences. Neither fear the unknown. They welcome it.

Art communicates scientific research. Art is how we visualize our data. Every scatterplot, phylogeny, and manuscript are art. They might not be judged on their beauty, emotion and uniqueness, but they are still art. Collaborations between artists and scientists can be fruitful. Artists can serve as partners in the communication of scientific research. They can help us visualize data in new ways. They can help us make our results easier to understand and present them more compellingly. Also, they can help us reach a larger and different audience with our scientific message. Not only can art help visualize data, art is data. Researches have examined paintings from the Tate and National Gallery in London (1500 – 2000 BCE) of sunsets as a proxy for information about the aerosol optical depth after major volcanic eruptions. Historically science has produced the materials (pigments, canvas, photographic emulsion etc.) and methods of art. Modern collaborations are more than just better paint. Modern artists use materials from the realm of science such as bacteria, robotics, and computer languages to express their visions. Scientists and artists have even teamed up to explore how art affects the human brain.

Figure 2a: Nikki Cavalieri shows artists pygmy hippo skull.

Figure 2b: Nikki Cavalieri explains the evolution of morphology in primates.









Figure 3: Kasey Pham botanical artist drawing squash.

In recent years there has been a push to change STEM (Science Teaching Education and Mathematics) to STEAM (STEAM plus an A for art) to ensure that creativity is not left out of education. A group of MSU scientists have been spending one afternoon each month communing with teen artists at a fantastic local (Lansing) community arts center called REACH!. Our goal is to connect MSU students and staff who seek to bridge science and art with junior high and high school artists. Through activities at REACH, we aim to link art and science in as many ways as possible. In one of our earlier visits, I brought museum specimens (Figure 2) for the REACH kids to sketch, emphasizing the link between biological form and function. Later, I helped them develop chimeras incorporating morphologies of plants and animals, endowed with adaptations befitting a randomly chosen (‘wheel of fortune’ style) environment. During another visit, Kasey Pham (Figure 3) brought a live chameleon and tarantula for students to draw. This gave them a chance to focus on the dynamics of animal movement, and the intricacies of the integument – how light catches hairs, scales, and colors. As a talented artist who is also a plant scientist, Kasey spent one afternoon teaching teens about the chemistry of henna tattooing and then left the kids (and us) with favorite animals stained on our arms.

Figure 4: Young artists examines a human skull, it is important to note there was a concurrent costume party.

Figure 5: Kasey Pham shares her artist notebook with students.

Figure 6: Artist drawing goliath frog, pygmy hippo and Dinocrocuta skull


Figure 7: Kasey Pham gives Eben Gering a henna tattoo.

Figure 8: Artist showing off their sweet henna tattoos.

Figure 9: Artist showing off their sweet henna tattoos.

The world is a much poorer place when we separate things that should be together. It is important that developing artists and scientists see that science and art are not opposed. Through this program and programs like it hopefully future students will understand it is not art or science it is art and science.


Posted in BEACON Researchers at Work, Education, Member Announcements | Tagged , , , | Comments Off on Art and Science, Science and Art: Science outreach to young artists

Evolution is the New Deep Learning

This is a repost of a blog post by Risto Miikkulainen, Vice President Research; Professor of Computer Science at the University of Texas at Austin

At Sentient, we have an entire team dedicated to research and experimentation in AI. Over the past few years, the team has focused on developing new methods in Evolutionary Computation (EC), i.e. designing artificial neural network architectures, building commercial applications, and solving challenging computational problems using methods inspired by natural evolution. This research builds upon more than 25 years of research at UT Austin and other academic institutions, and coincides with related efforts recently at OpenAI, DeepMind, Google Brain, and Uber. There is significant momentum building in this area; indeed, we believe evolutionary computation may well be the next big thing in AI technology.

Like Deep Learning (DL), EC was introduced decades ago, and it is currently experiencing a similar boost from the available big compute and big data. However, it addresses a distinctly different need: Whereas DL focuses on modeling what we already know, EC focuses on creating new knowledge. In that sense, it is the next step up from DL: Whereas DL makes it possible to recognize new instances of objects and speech within familiar categories, EC makes it possible to discover entirely new objects and behaviors—those that maximize a given objective. Thus, EC makes a host of new applications possible: designing more effective behaviors for robots and virtual agents; creating more effective and cheaper health interventions, growth recipes for agriculture, and mechanical and biological processes.

Today, Sentient released five papers and a web portal reporting significant progress in taking this step, focusing on three areas: (1) DL architectures are evolved to exceed state of the art in three standard machine learning benchmarks; (2) techniques are developed for increasing performance and reliability of evolution in real-world applications; and (3) evolutionary problem solving is demonstrated on very hard computational problems.

This post focuses on the first of these areas, i.e. optimization of DL architectures with EC.

Sentient Reveals Breakthrough Research in Neuroevolution

Much of the power of deep learning comes from the size and complexity of the networks. With neuroevolution, the DL architecture (i.e. network topology, modules, and hyperparameters) can be optimized beyond human ability. The three demos that we will cover in this article are Omni Draw, Celeb Match, and the Music Maker (Language Modeling). In all three examples, Sentient successfully surpassed the state-of-the-art DL benchmark using neuroevolution.

Music Maker (Language Modeling)

In the Language Modeling domain, the system is trained to predict the next word in a “language corpus”, i.e. a large collection of text such as several years of the Wall Street Journal. After the network has made its prediction, this input can be looped back into its input, and the network can generate an entire sequence of words. Interestingly, the same technique applies equally well to musical sequences, where it makes for a fun demo. The user inputs a few initial notes, and the system improvises an entire melody based on that starting point. By means of neuroevolution, Sentient optimized the design of the gated recurrent (Long Short-Term Memory or LSTM) nodes (i.e. the network’s “memory” structure) to make the model more accurate in predicting the next note.

In the language modeling domain (i.e. predicting the next word in a language corpus called Penn Tree Bank), the benchmark is defined by Perplexity Points, a measurement of how well a probabilistic model can predict real samples. The lower the number the better, as we want the model to be less “perplexed” when predicting the next word in a sequence. In this case, Sentient beat the standard LSTM structure by 10.8 Perplexity Points. Remarkably, although several human-designed LSTM variations have been proposed, they have not improved performance much—LSTM structure was essentially unchanged for 25 years. Our neuroevolution experiments showed that it can, as a matter of fact, be improved significantly by adding more complexity, i.e. memory cells and more nonlinear, parallel pathways.

Why does this breakthrough matter? Language is a powerful and complex construct of human intelligence. Language modeling, i.e. predicting the next word in a text, is a benchmark that measures how well machine learning methods can learn language structure. It is therefore a surrogate for building natural language processing systems that includes speech and language interfaces, machine translation (such as Google Translate), and even medical data such as DNA sequences and heart rate diagnosis. The better we can do in the language modeling benchmark, the better language processing systems we can build, using the same technology.

Omni Draw

Omniglot is a handwritten character recognition benchmark on recognizing characters in 50 different alphabets, including real languages like Cyrillic (written Russian), Japanese, and Hebrew, to artificial languages such as Tengwar (the written language in Lord of the Rings).

This demo showcases multitask learning, in which the model learns all languages at once and exploits the relationship between characters from different languages. So, for instance, the user inputs an image and the system outputs suggestions for different character matches in different languages, saying “this would be ‘X’ in Latin, ‘Y’ in Japanese, and ‘Z’ in Tengwar, etc.”—taking advantage of its understanding of the relationships between Japanese, Tengwar, and Latin to figure out which character is the best match. This differs from a single task learning environment where the model trains on one language at a time and cannot make the same connections across language data sets.

In this Omniglot multitask character recognition task, our research team improved error of character matching from 32% to 10%.

Omniglot is an example of a dataset that has relatively little data per language—for instance, it may have only a few characters in Greek but many in Japanese. It succeeds by using its knowledge of the relationships between languages to find solutions, hence, finding a solution in the face of missing or sparse data. Why is this important? For many real world applications, labeled data is expensive or dangerous to acquire (e.g., medical applications, agriculture, and robotic rescue), hence automatically designing models that exploit the relationships to similar or related datasets could, in a way, substitute the missing dataset and boost research capabilities. It is also an excellent demonstration of the power of neuroevolution: there are many ways in which the languages can be related, and evolution discovers the best ways to tie their learning together.

Celeb Match

The Celeb Match demo deals similarly with multitask learning, but this time, with a large-scale data sets. The demo is based on the CelebA dataset, which consists of around 200,000 images of celebrities, each of which is labeled with 40 binary attributes such as “Male vs. Female”, “beard vs. no beard”, “glasses vs. no glasses”, etc. Each attribute induces a “classification task” that induces the system to detect and identify each attribute. As a fun add-on, we’ve created a demo that turns this task around: The user can set the desired degree for each attribute, and the system finds the closest celebrity match, as determined by the evolved multitask learning network. For instance, if the current attribute settings result in an image of Brad Pitt, the user can increase “gray hair” to find which celebrity would be similar to Brad Pitt but with different hair.