The NeuroML team invites highly motivated students for work towards their Bachelor and Master theses. We offer research in the following directions:

  • EEG and MRI based pathology diagnostic tools for autism, schizophrenia, depression and other psychiatric disorders;
  • Radiologist assistance tools for neurosurgery;
  • Disease outcome prediction and treatment planning for stroke;
  • Neuroeducation and cyber-sport methods based on eye-tracking and wearing sensors;

Requirements

  • Good Python programming skills;
  • Background in statistics, numerical optimization, algorithms, and learning;
  • Knowledge of modern numerical software and deep learning frameworks (PyTorch, or others) is a strong plus;
  • High motivation, commitment, and punctuality.

How to apply

For your application, prepare your CV, Bachelor/Master transcripts, and (optionally) recommendation letters. Email your application directly to Dr. Maxim Sharaev m.sharaev@skoltech.ru. We will respond within a few days, inviting you for a personal interview. During the interview, you will be asked to describe your previous experience (both academic and industrial). Please be aware that your theoretical and programming skills will be tested during the interview.

What do we offer: Are you a student form Data Science or IST, HSE, Yandex.SDA who feels sick from experimenting on MNIST or CIFAR and want to solve real-life problems?

Or are you a Life Sciences student with Neuroscience background, and you want to try yourself interpreting pioneering Deep Learning results and do sophisticated medical visualization? Here is an option for you. In our group you can learn to:

  • Use Deep Learning and Computer Vision methods for 3D-4D data analysis. We have ongoing studies on domain adaptation and transfer learning, ensembling, segmentation, detection and deep learning network explanation;
  • Work with classical ML and statistics: feature engineering, feature extraction and selection, sampling and validation techniques;
  • Develop solid engineering methods for noisy experimental data cleaning, apart from ML approaches;
  • Work on real cases in clinics with doctors: develop strategies for data collection and labelling, analysis interpretation;