{"id":37814,"date":"2023-09-29T15:07:42","date_gmt":"2023-09-29T14:07:42","guid":{"rendered":"https:\/\/www.innovationnewsnetwork.com\/?p=37814"},"modified":"2023-09-29T15:07:42","modified_gmt":"2023-09-29T14:07:42","slug":"what-are-the-limitations-to-reservoir-computing","status":"publish","type":"post","link":"https:\/\/www.innovationnewsnetwork.com\/what-are-the-limitations-to-reservoir-computing\/37814\/","title":{"rendered":"What are the limitations to reservoir computing?"},"content":{"rendered":"
A change in one place can trigger a huge change elsewhere in nonlinear dynamic systems.<\/p>\n
Examples of this include the climate, the workings of the human brain, and the behaviour of the electric grid. Dynamic systems like these are extremely difficult to model because of their inherent unpredictability \u2013 changing dramatically over time.<\/p>\n
However, researchers in the last two decades have reported success modelling high-dimensional chaotic behaviours with a Machine Learning approach<\/a> called reservoir computing.<\/p>\n \u201cMachine Learning is increasingly being used to learn some complex dynamic systems that we don\u2019t have a good mathematical description for from data,\u201d said Yuanzhao Zhang, an SFI Complexity Postdoctoral Fellow.<\/p>\n Recent papers have reported that reservoir computing is effective in predicting the trajectory of chaotic systems. It has been argued that they are efficient even after seeing little training data, and can determine where the system would end up from its initial conditions.<\/p>\n Zhang aimed to find out if the reports were true.<\/p>\n