Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟱𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗧𝗵𝗲 𝗞𝗼𝗿𝗲𝗮 𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗜𝗻𝘀𝘁𝗶𝘁𝘂𝘁𝗲 𝗼𝗳 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗮𝗻𝗱 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝘆 (𝗞𝗔𝗜𝗦𝗧) 𝗵𝗮𝘀 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 𝗗𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗲 𝗙𝗮𝗰𝗲 𝗗𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝗶𝗻 𝗨𝗻𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗗𝗲𝗲𝗽 𝗡𝗲𝘂𝗿𝗮𝗹 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀 𝗶𝗻 𝗡𝗮𝘁𝘂𝗿𝗲 𝗣𝘂𝗯𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: Demonstrate Face Detection in Untrained Deep Neural Networks in Nature Publication 🔸 This paper is published in Nature2021 🔸 Researchers have found that higher visual cognitive functions can arise spontaneously in untrained neural networks. A KAIST research team led by Professor Se-Bum Paik from the Department of Bio and Brain Engineering has shown that visual selectivity of facial images can arise even in completely untrained deep neural networks. 🔸 This new finding has provided revelatory insights into mechanisms underlying the development of cognitive functions in both biological and artificial neural networks, also making a significant impact on our understanding of the origin of early brain functions before sensory experiences. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 face-selective neurons are observed in the primate visual pathway and are considered as the basis of face detection in the brain.  🔸 However, it has been debated as to whether this neuronal selectivity can arise innately or whether it requires training from the visual experience.  🔸 Using a hierarchical deep neural network model of the ventral visual stream, we suggest a mechanism in which face-selectivity arises in the complete absence of training.  🔸 We found that units selective to faces emerge robustly in randomly initialized networks and that these units reproduce many characteristics observed in monkeys. This innate selectivity also enables the untrained network to perform face-detection tasks.  🔸 Intriguingly, we observed that units selective to various non-face objects can also arise innately in untrained networks. Our results imply that the random feedforward connections in early, untrained deep neural networks may be sufficient for initializing primitive visual selectivity. #computervision #artificialintelligence #innovation