Content area
In neural decoding, reconstruction seeks to create a literal image from information in brain activity, typically achieved by mapping neural responses to a latent representation of a generative model. A key challenge in this process is understanding how information is processed across visual areas to effectively integrate their neural signals. This requires an attention mechanism that selectively focuses on neural inputs based on their relevance to the task of reconstruction --- something conventional attention models, which capture only input-input relationships, cannot achieve. To address this, we introduce predictive attention mechanisms (PAMs), a novel approach that learns task-driven "output queries" during training to focus on the neural responses most relevant for predicting the latents underlying perceived images, effectively allocating attention across brain areas. We validate PAM with two datasets: (i) B2G, which contains GAN-synthesized images, their original latents and multi-unit activity data; (ii) Shen-19, which includes real photographs, their inverted latents and functional magnetic resonance imaging data. Beyond achieving state-of-the-art reconstructions, PAM offers a key interpretative advantage through the availability of (i) attention weights, revealing how the model's focus was distributed across visual areas for the task of latent prediction, and (ii) values, capturing the stimulus information decoded from each area.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
* This revision improves the clarity of the explanation of PAM. The results themselves remain unchanged.