Decoding of visual stimuli from noninvasive neuroimaging techniques such as functional magnetic resonance (fMRI) has advanced rapidly in the last years; yet, most high-performing brain decoding models rely on complicated, non-interpretable latent spaces. In this study we present an interpretable brain decoding framework that inserts a semantic bottleneck into BrainDiffuser, a well established, simple and linear decoding pipeline. We firstly produce a 214 dimensional binary interpretable space L for images, in which each dimension answers to a specific question about the image (e.g., "Is there a person?",

This simply turns everything white, besides the main subject of your image--there are no tools or settings to play around with in this case. As you would expect, it works better for images where the main subject is more obvious, but the results can be impressive--and can save you a lot of manual image editing time.

Understanding large corpora is an increasingly popular problem. Modern startups and established companies are working diligently to produce models that can extract meaningful data from a body of text. In this post, I will explain some Natural Language Processing (NLP) techniques that can be used to extract the main subject of a particular document. In addition to identifying the main subject, I will explain a technique for getting Subject Verb and Object sets, everywhere the subject is mentioned. To further explain what I'm talking about take a look at this TechCrunch article.