Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟮𝟲 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗔 𝗡𝗲𝘄 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗢𝗻 𝗨𝗻𝘀𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗗𝗲𝗲𝗽 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝗵𝗼𝘄𝘀 𝗧𝗵𝗮𝘁 𝗧𝗵𝗲 𝗕𝗿𝗮𝗶𝗻 𝗗𝗶𝘀𝗲𝗻𝘁𝗮𝗻𝗴𝗹𝗲𝘀 𝗙𝗮𝗰𝗲𝘀 𝗜𝗻𝘁𝗼 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰𝗮𝗹𝗹𝘆 𝗠𝗲𝗮𝗻𝗶𝗻𝗴𝗳𝘂𝗹 𝗙𝗮𝗰𝘁𝗼𝗿𝘀, 𝗟𝗶𝗸𝗲 𝗔𝗴𝗲 𝗔𝘁 𝗧𝗵𝗲 𝗦𝗶𝗻𝗴𝗹𝗲 𝗡𝗲𝘂𝗿𝗼𝗻 𝗟𝗲𝘃𝗲𝗹 Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗨𝗻𝘀𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗱𝗲𝗲𝗽 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗲𝘀 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗱𝗶𝘀𝗲𝗻𝘁𝗮𝗻𝗴𝗹𝗲𝗺𝗲𝗻𝘁 𝗶𝗻 𝘀𝗶𝗻𝗴𝗹𝗲 𝗶𝗻𝗳𝗲𝗿𝗼𝘁𝗲𝗺𝗽𝗼𝗿𝗮𝗹 𝗳𝗮𝗰𝗲 𝗽𝗮𝘁𝗰𝗵 𝗻𝗲𝘂𝗿𝗼𝗻𝘀. 🔸 This paper is published in nature 2021. 🔸 The ventral visual stream is widely known for supporting the perception of faces and objects. Extracellular single neuron recordings define canonical coding principles at various stages of the processing hierarchy, such as the sensitivity of early visual neurons to orientated outlines and more anterior ventral stream neurons to complex objects and faces, over decades. A sub-network of the inferotemporal cortex dedicated to facial processing has received a lot of attention. Faces appear to be encoded in low-dimensional neural codes inside such patches, with each neuron encoding an orthogonal axis of variation in the face space. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 In order to better understand how the brain perceives faces, it is important to know what objective drives learning in the ventral visual stream.  🔸 To answer this question, we model neural responses to faces in the macaque inferotemporal (IT) cortex with a deep selfsupervised generative model, β-VAE, which disentangles sensory data into interpretable latent factors, such as gender or age.  🔸 Our results demonstrate a strong correspondence between the generative factors discovered by β-VAE and those coded by single IT neurons, beyond that found for the baselines, including the handcrafted state-of-the-art model of face perception, the Active Appearance Model, and deep classifiers.  🔸 Moreover, β-VAE is able to reconstruct novel face images using signals from just a handful of cells. Together our results imply that optimising the disentangling objective leads to representations that closely resemble those in the IT at the single unit level. This points at disentangling as a plausible learning objective for the visual brain.