Microscopy Image Analysis Student Intern
Jackson Laboratory
- Bar Harbor, ME
- Training
- Full-time
- Apply Transfer learning approaches & pre-trained ResNet XX to Histo-Path problems
- Develop a strategy to apply the probability output of YOLO networks to identify the optical nerve in eyeball sections by:
- Generating training set based on the CS/MS group’s specifications, ideally within the capabilities of JAX Image Tools software (Slidescropper)
- Using HPC resource to retrain all weights of the full network
- Investigating on how exchanging different Resnets improves results
- Converting the script to use Cuda to classify test samples
- Investigating running classification on low-power devices, such as RaspberryPi
- Must be enrolled in a college or university program
- Pursuing a Master’s degree in computer science, biology, electrical engineering, or related field
- Experience with Pytorch or other ML framework
- Experience with programming languages (i.e. Python, Java, Typescript)
- Interest and familiarity with ML and/or Image Analysis
- Familiarity with CUDA programming is a plus