How artificial neural networks build their own learning machinery

According to MIT News, the scientists made the case in a paper published Oct. 9 in the journal PNAS[1]. The McGovern Institute says they argue that a network's biological plausibility depends on its ability to organise itself "without the guiding hand of a developer."[2]MIT News reports that with some simple instructions about how and when connections should change, a group of randomly connected units can reshape itself into an effective information-processing network[1]. The outlet adds that the network uses the rule that "neurons that fire together wire together."[3]According to MIT News, most modern AI implements gradient descent through some form of the back-propagation algorithm, which neuroscientists say is unlikely to be used by the brain.[1] The outlet says the team compared its self-organizing network to networks designed to learn in this way and found that it performed at a similar level.[1]Co-first author Qianli Liao told MIT News that "Current AI technology is working very well, but it doesn't necessarily use a learning algorithm that is used by the brain."[1]Tomaso Poggio told the outlet that if the brain does use the proposed motifs, "we will have a strong connection at the level of fundamental mechanisms"[4] between machines and brains.ALLATRA Media notes that every result here is theory and simulation inside artificial networks[5]. It also reports that the matching performance holds for the image-classification tasks reported[5].