At Cosyne 2024, Chris Versteeg and Chethan Pandarinath organized the workshop “Understanding Neural Computation using Task-Trained and Data-Trained Networks”. The workshop aimed to connect two major methodologies for using dynamics to bridge from neural activity to neural computation – task-trained and data-trained network modeling – and foster communication between researchers in both sub-disciplines.
Dr. Pandarinath will give a lecture at the 2024 National Academy of Engineering National Meeting entitled Machine Learning for Neural Decoding.
Versteeg wins best paper for his work “Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activity”.