Their method for introducing machine learning in chemistry classes has been honored with the inaugural James C. McGroddy Award for Innovation in Education, named for a donor who funded the award’s cash prize. (See related story.)

The recipients are Elizabeth Thrall, Ph.D., assistant professor of chemistry; Yijun Zhao, Ph.D., assistant professor of computer and information science; and Joshua Schrier, Ph.D., the Kim B. and Stephen E. Bepler Chair in Chemistry. They will share the $10,000 prize, awarded in April.

Chemistry and Computation Come Together

The three awardees’ project shows how to reduce the barriers to learning about programming and computation by integrating them into chemistry lessons. The project came together during the COVID pandemic—since chemistry students were working from their computers, far from the labs on campus, it made sense to give them some computational projects, in addition to experiments they could conduct at home, Thrall said.

Because little had been published about teaching machine learning to chemistry students, she got together with Schrier and Zhao to design an activity. Zhao, director of the Master of Science in Data Science program at Fordham, involved a student in the program, Seung Eun Lee, GSAS ’22, who had studied chemistry as an undergraduate.

Their first classroom project—published in the Journal of Chemical Education in 2021—involves vibrational spectroscopy, used to identify the chemical properties of something by shining a light on it and recording which wavelengths it absorbs. Students built models that analyzed the resulting data and “learned” the features of different molecular structures, automating a process that they had learned in an earlier course.

For another project, the professors taught students about machine-learning tools for identifying possible hypotheses about collections of molecules. Machine learning lets the students winnow down the molecular data and, in Schrier’s words, “make that big haystack into a smaller haystack” that is easier for a scientist to manage. The professors designed the project with help from Fernando Martinez, GSAS ’23, and Thomas Egg, FCRH ’23, and Thrall presented it at an American Chemical Society meeting in the spring.

Thumbs-Up from Students

How did students react to the machine learning lessons? According to a survey following the first project, 63% enjoyed applying machine learning, and 74% wanted to learn more about it.

“I think that students recognize that these are useful skills … that are only going to become more important throughout their lives,” Thrall said. Schrier noted that students have helped develop additional machine learning exercises in chemistry over the past two years.

Machine Learning in Education and Medicine

Zhao noted the growing applications of machine learning and data science. She has applied them to other fields through collaborations with Fordham’s Graduate School of Education and the medical schools at New York University and Harvard, among other entities.

The McGroddy Award came as a surprise. “I don’t think that we expected to win,” Schrier said, “just because there’s so many other excellent pedagogical innovations throughout Fordham.”

Eva Badowska, Ph.D., dean of the Faculty of Arts and Sciences at the time the award was granted, said the professors’ “path-breaking interdisciplinary work has transformed lab courses in chemistry.”

There were 20 nominations, and faculty members reviewing them “were humbled by the creativity, innovation, and generative energy of the faculty’s pedagogical work,” she said.

In addition to the McGroddy Award, the Office of the Dean of Faculty of Arts and Sciences is providing two $1,000 honorable mention prizes recognizing the pedagogy of Samir Haddad, Ph.D., and Stephen Holler, Ph.D., associate professors of philosophy and physics, respectively.

“[We are] mostly focused on pedagogy, and how we can actually take advantage of…artificial intelligence in education,” said Fleur Eshghi, associate vice president of education technology and research at Fordham and one of the organizers of the event. “[We are] also examining the areas [to figure out]where we can be more creative with artificial intelligence.” 

Faculty Technology Day is a full-day conference that is open to all interested faculty and administrators. 

“This event started actually 24 years ago, with a very small group of faculty getting together in one classroom, and gradually grew to become a major conference,” explained Eshghi, “During the pandemic, we had to stop it, and this is the first year we are reviving this again.” 

Every year, the event organizers pick a topic that they think is most relevant to the cross-section of technology and education. This year, it was AI. 

A major theme throughout the day was that faculty need to be open to change. No one is quite sure yet how AI will change the way things are done, but the speakers emphasized that being flexible, unafraid of the future, and willing to adapt will set every professor up for success no matter what happens.

Poetry, Cybersecurity, and Robots

The event included several notable AI-focused keynote speakers, as well as breakout sessions that were more participatory. These sessions ranged from “Hands-on AI Play Sesh and Poetry Slam,” “Immersing Students in Virtual Reality,” and “Developing an Inclusive Augmented Reality (AR) Project Template” to “AI in Cybersecurity,” “3D Printing and AI,” and, maybe surprisingly, “How Can I Get the Robot to Do My Research?”  

Many of the sessions focused on the AI world’s new darling, ChatGPT.  Faculty members and administrators learned how to ask the chatbot specific questions, and heard about possible uses that they may have for this technology: Maybe you only have three things in the fridge and you need to know what you could make for dinner without buying anything new. Maybe you are going on vacation and would like a list of notable places you should visit. Or maybe you are researching something very niche and would like to know which articles feature your topic. 

A ‘More Efficient Version of What We Have Today’

“It’s just a more efficient version of what we have today,” said Daniel Susskind, Ph.D., a Research Professor in Economics at King’s College London, Senior Research Associate at Institute for Ethics in AI at Oxford University, and the morning’s keynote speaker. 

In her opening remarks, Fordham President Tania Tetlow said we may not have all the answers where AI is concerned, but it’s a good thing we’re asking the questions. 

“This is one of the most promising things about Fordham– that you have chosen to come [to this conference]– because we have so much to learn at this moment in humanity’s history,” Tetlow said to the conference participants. “That you are embracing the challenge, and showing up today to leap in with both feet, is an extraordinary thing.”

–by Rebecca Rosen

“It’s particularly exciting to see how data science is being used to enhance ethically informed and motivated research,” said Ann Gaylin, dean of the Graduate School of Arts and Sciences. “I’m also pleased to note how this research aligns so closely with GSAS’s mission of graduate education for the global good.”

Social Media’s Impact on LGBTQ+ Students

Xiangyu Tao, a fourth-year doctoral student in the applied developmental psychology program, used survey data to illustrate social media’s effects on LGBTQ+ students. She found that the more time the students spent on social media, the more discrimination and hateful language they were exposed to, which caused higher levels of stress, anxiety, and depression.

Tao’s research also found that while LGBTQ+ students reported some positives regarding social media, such as finding a community and resources online, they did not outweigh the negatives. She shared her findings with members of the undergraduate Queer Student Advisory Board who had some insights.

“[A] member brought up that positives that happen on social media fade away when you close your phone, but the negatives on social media, like discrimination, will linger and impact a person’s mental health,” she said.

Making Scientific Advancements

Understanding the relationship between brain activity and behaviors is a main focus of neuroscience, said Rabia Gondur, an integrative neuroscience major who graduated from Fordham College at Lincoln Center in 2022 and is currently part of the accelerated master’s program in data science in the Graduate School of Arts and Sciences.

“How do we relate these rich, complex naturalistic behaviors to their simultaneously recorded neural activity? With our research we are trying to answer this question,” she said.

But Gondur noted that oftentimes models for documenting these, are “restricted to only one data modality, so either neural activity or behavior, but usually not in conjunction.”

With Stephen Keeley, an assistant professor of natural sciences, Gondur worked to combine existing models to better show how that conjunction of neural activity and behavior is related. She gave an example of a fly and showed how the model tracked both the neural activity in the brain taking place and what the behavior of the fly was, such as moving its left limb or right limb.

“We hope that [this combined]model can be a general tool for understanding the relationship between the brain and behavior,” she said.

Nolan Chiles, a senior at Fordham College at Rose Hill majoring in integrative neuroscience, worked with chemistry professor Joshua Schrier to conduct research on a classification algorithm that he hopes, with some additional work, can be used for drug discovery.

“The predominant way that we discover new drugs, say for HIV, [is by trying]to find molecules that are effective in inhibiting infection,” he said.

Traditionally this is done through a method called “High Throughput Screening,” which involves testing many molecules, often blindly, Chiles said, for how effective they are.

“This is often costly and time inefficient, and so we are beginning to find other ways of using computational prescreening so that we can cut down on the number of molecules that we actually have to evaluate in the lab,” he said.

Data Poisoning

Courtney King, a doctoral student in computer science who received her master’s degree in the subject from the Graduate School of Arts and Science in 2022, worked with Juntao Chen, an assistant professor of computer and information sciences, to examine how an “attacker” can manipulate data to make something like a chatbot do something it was not made to do.

King gave the example of the chatbot Tay from Microsoft, which was “not supposed to be able to be taught offensive language,” but “through policy poisoning, Twitter users were able to make her say racist things.”

“Data poisoning is reported as a leading concern for industry applications,” King said.

Their research helped to identify a “potential vulnerability” where an attacker can trick the machine learner into “implementing a targeted malicious policy by manipulating the batch data,” such as a chatbot saying racist phrases. By pointing out this vulnerability, the researchers showed that it is crucial for a system to “actively protect its stored data, and specifically its sensor data, for trustworthy batch learning.” King’s paper stated that future work could include exploring how to detect or protect against this type of attack.

Breadth and Depth of Research

Other presentations included a look into Project FRESH Air and how the citizen science program uses monitors to detect air quality at schools in the Bronx and Manhattan; how functional difficulties, such as vision impairment, can be mapped by region; and how algorithms can be used to identify data vulnerable to ransomware attacks.

Gaylin praised all of the presenters, particularly the graduate students, for their research.

“It’s heartening to see that graduate students in the first cohorts of our two newest programs—the Ph.D. in computer science, and the dual master’s degree in economics and data science—have hit the ground running,” she said. “These students are our future.”

Now, student-developed software that works with the camera technology promises to help conservationists better understand how to protect future generations of the toads so that they can continue to thrive in their natural habitat in Tanzania. Next year, two more students will pick up the project.

From Africa to the Bronx, and Back Again

Discovered in 1996, the Kihansi spray toad lived in a five-acre microhabitat created by the spray of waterfalls in the Kihansi Gorge, which came under threat with the construction of a nearby dam that dramatically changed the habitat and decreased the size of the mist zone. The species was last seen in the wild in 2005 and was declared extinct-in-the-wild by 2009 by the International Union for Conservation of Nature, likely due to the environmental changes and the emergence of a deadly fungus.

As the toad population declined, a partnership between the Bronx Zoo and the Tanzanian government, and the World Bank facilitated the collection of 499 spray toads to be brought to the Bronx to initiate an off-site conservation program. Custom microhabitats replicating their home in Tanzania were built in bio-secure facilities at the Bronx Zoo and later at the Toledo Zoo where they successfully bred the toads in the hopes of reintroducing them to the wild.

Back in Tanzania, the government managed the Lower Kihansi Environment Management Project to create a gravity-fed misting system. The project resuscitated the toads’ habitat and in 2010 the first 200 toads were returned to Tanzania to a breeding facility at University of Dar es Salaam. The first of several reintroductions to the gorge occurred in 2013, making them the first amphibian species to be reintroduced after being declared extinct in the wild.

Enter Fordham

The Fordham piece of the project began about five years ago when Kelly Cunningham, FCRH ’14, worked with James MacDonall, Ph.D., professor emeritus of psychology, to study the pecking behavior of pigeons. At the time, contact switches and touch-screen sensors were the state of the art for recording pigeons pecking at a target as part of psychological learning experiments, but a disadvantage of that simple mechanism is that when the pigeons’ beaks began to hurt, they stopped pecking at the switches. Further complicating things was the fact that this technology missed when pigeons were distracted or facing the wrong way, said Lyons.

As a computer scientist under the tutelage of Lyons, Cunningham worked in Fordham’s Computer Vision Lab to institute the use of the Microsoft Kinect sensor for the study. The Kinect is a motion-sensing input system initially developed for Xbox. Its cameras presented a flexible and inexpensive image-based approach to solving the tired-beak problem, as well as a way to observe behaviors beyond pecking.

Lyons and Cunningham wrote a paper published in a Psychometric Society journal in 2014 on their findings, which caught the eye of Avi Shuter at the Wildlife Conservation Society’s Bronx Zoo. Shuter is the Senior Wild Animal Keeper in the zoo’s Department of Herpetology.

He was researching the behavior of the Kihansi spray toad, and he thought the technology might be helpful in the zoo’s efforts to better understand the animal. He reached out to Lyons, who in turn put Armando Califano, FCRH ’17, GSAS ’19, on the case.

Taking the Toads to Task

With the help of an undergraduate research grant from Fordham College at Rose Hill, Califano refined the tracking system developed by Cunningham, shifting the camera from Microsoft Kinect to the Intel RealSense, which had more accurate depth perception. But Califano could only take the project so far before entering graduate school, and the experiment was put on hold.  That’s when Philip Bal, FCRH ’19, came into the picture.

In Bal’s junior year he decided to shift his focus from biology to computer science—making him a perfect candidate to pick up the project.  Over the past year and a half, Bal wrote new software that would use the camera to track the toads and generate behavior analytics, ultimately by distinguishing toads from other moving and stationary elements in their tanks. With Lyons overseeing the computer technology and Shuter overseeing the biology, Bal was able to further develop software that responded to the needs of zookeepers.

A Tiny Target

The average size of the toad is no more than an inch, at most. The tanks that they are kept in are the typical fish tank size, about two feet wide, two feet deep, and about three feet high. The camera sits an inch and a half away from the glass. Researchers choose a subsection of the tank to focus on, just a few dozen cubed inches along the bottom or the top. A focal length is established to determine how deep into the tank the camera will take measurements. The camera has two lenses: one that’s recording color, and infrared that records movement.

“We have to do a whole bunch of calculations, try to figure what’s actually a toad moving and eliminate the noise, like moving leaves,” said Bal. “The first thing we do to track toads is to match them to a particular movement.”

Providing a More Accurate Picture

The group gathered approximately two days of footage that took up four and a half terabytes of stored data. Up until then, previous behavioral studies relied on direct observations of toads by scientists at predetermined time intervals. Those projects were an important start, but this new technology and software will give researchers a more complete view of toad behavior, said Shuter.

“Previous studies almost didn’t see any toads hopping,” said Shuter, who worked with the Fordham students and Lyons. “This can be a pretty shy species of toad that hides or stays still when you walk by. A lot of their behavioral repertoire also seems to be made up of split-second movements, like quick calls or hops. So, that’s part of the reason why I thought that a system where a computer could catch all that would give us a more accurate idea of what’s going on.”

One of the things that distinguish the Fordham research from other studies on these toads was that the technology and software were new.

“This is from the ground up; it didn’t exist before,” said Shuter, adding that as a result, the project is more complex than previous studies. “I’m amazed that it has only taken this long to get to where we’ve gotten since it’s totally from scratch.”

Bal said that the project taught him quite a bit about programming.

“I learned what I was capable of, I created thousands of lines of code I never thought I would be able to write,” he said. “This is one of my favorite things to talk about, my passion project.”

Shuter said that when the zoo first recovered the toads in the year 2000, the focus at the time was to build up a colony in captivity that could be relied upon in the event that the wild population continued to decline. The zoo was able to bring the number of toads to almost 2,000 toads.

“The struggle back then was to make more, make more, make more, and we didn’t publish research about their natural history or biology, aside from what would keep them alive, healthy, and breeding in zoos,” said Shuter. “Now, we’re a little bit calmer and things are going well in Tanzania, and we have a good handle on how to keep them alive. So now, we’re starting to look more into, ‘what’s their behavior like?’”

At a recent meeting at the zoo, Bal presented some interactions he observed in the data, including “meetings” of toads, characterized by a certain distance between the toads and the amount of time spent together.

Shuter plans to continue observing these interactions, and also plans to examine fighting behaviors and look to tell them apart from mating—also referred to as amplexing.

And he may get some help from the next cohort of Lyons’ students.

“These guys might end up doing some track analysis for that,” said Lyons, gesturing to two younger students in the lab. “That’s great! We might be able to distinguish fights from amplexing.”