What is it about?
Deep Neural Network (DNN)
Neural Network:
This ML
images
DATA
individual
fMRI
brain activitydata
direct visualization
memorized visualization
*over a ten-month period
*images (geometric shapes, natural phenomena and letters of the alphabet)
individual
Deep Image Reconstruction - a method to visualize perceptual content from human brain activity
Combined the DNN feature decoding from fMRI signals and the methods for image generation.
- built a model of how the brain encodes information
- train the model to associate images with brain activity
- the network partially reconstruct what a participant saw, decoding brain activity into pixels
THE MODEL
"The results suggest that hierarchical visual information in the brain can be effectively combined to reconstruct perceptual and subjective images"
A way to access, explore and share the content of our perception, memory, and imagination
RESULTS
- patients in permanent vegetative states to communicate
- make video recordings of daydreams
- therapy (analysis of thoughts)
- criminal investigations
APPLICATIONS
Access to complex and intimate places on our minds
Be able to know what others might be thinking, can be dangerous...
ETHICAL implications
Other similar projects
Thank you!
Questions?