Benjamin
Gitai
Princeton student (class of 2029) researching non-invasive brain stimulation and deep network models of visual cortex. I also take on freelance coding and data analysis projects.
Research
Four projects, newest first.
Pesaran Lab, Penn Medicine, with Prof. Bijan Pesaran, Summer 2026
Focused ultrasound for non-invasive deep brain stimulation
I built a planning tool that takes a macaque's own CT and MRI, aims a focused-ultrasound transducer at a deep target, designs a 3-D-printable lens that corrects for the skull, and simulates where the focus really lands.
Forward simulation with the designed lens: the pressure peak lands on the subthalamic nucleus (557 kPa on target; brain and global peak 604 kPa at the target). Pillow Lab, Princeton Neuroscience Institute, with Prof. Jonathan Pillow, Summer 2026 to present
Deep network models of visual cortex
I'm revising Moskovitz et al. (2018) around the finding that V1 complex cells are higher-dimensional than classical models assume, and compressing deep network models of motion-sensitive MT/MST neurons.
Filters recovered by iSTAC, ES-pool, CBF, and a fully connected network for an example simple and complex cell. Complex cells keep improving as filters are added; simple cells level off. Princeton Learning Lab, with Prof. Olga Troyanskaya, Summer 2024
Computer vision for ankle replacement surgery
A YOLO model finds the ankle bones in X-rays, then measures the joint angles surgeons plan with. Regeneron Science Talent Search semifinalist (top 300), 2025.
Detecting the ankle bones in X-rays. With J. Sheehan, 2023
E. coli growth dynamics during phage infection
Growth curves during Lambda(vir) infection revealed phage decay. Oral presentation at the IEEE Integrated STEM Education Conference.
Growth curves under phage infection.
About
I'm a Princeton sophomore studying computer science, focused on computational neuroscience and machine learning. Outside the lab I'm president of Princeton's Magic: The Gathering Club and play for ClockWork Ultimate.
Coding
Most of my work is in Python for data science, machine learning, and simulation, and I also write Java, JavaScript, C++, C#, and MATLAB. I've built computer vision models, genetic algorithms, and websites like this one.
Pricing
My coding rates depend on the kind of work: planning, computation, and debugging are priced separately. Use the calculator to get a quick estimate before we talk.
Schedule
Book a Zoom or in-person meeting at any open time on my calendar. If I ever have to move a meeting, I'll let you know in advance.