This means a lot

How do we learn the meaning of new concepts?
Inspired by projects like HistWords, we use natural language processing techniques to model changes in word meanings during an introduction to computer science course. Our goal is to then use this model to predict changes in neural activity that occur as students learn new ideas.

Methods & tools:

  • Natural Language Processing (NLP)
    • Word vector embeddings (incl. GloVe)
    • Deep learning language models (incl. BERT)
  • High-performance computing (HPC) (on prem)
  • Python3, TensorFlow & PyTorch
  • Functional MRI
  • Pattern analysis (MVPA)

This is work in progress, please check back for updates!

Photo by Grant Jacobson on Unsplash

Meir Meshulam
Meir Meshulam
Postdoc researcher

Meir Meshulam is a postdoc in Neuroscience at Princeton University, using machine learning and deep learning to study human cognition.