From: peter.luschny@gmail.com   
      
   Symbolic Mathematics Finally Yields to Neural Networks   
      
   I quote:   
      
   "Lample and Charton’s program could produce precise solutions to complicated   
   integrals and differential equations — including some that stumped popular   
   math software packages with explicit problem-solving rules built in."   
      
   "The new program exploits one of the major advantages of neural networks: They   
   develop their own implicit rules. As a result, “there’s no separation   
   between the rules and the exceptions,” said Jay McClelland, a psychologist   
   at Stanford University    
   who uses neural nets to model how people learn math. In practice, this means   
   that the program didn’t stumble over the hardest integrals. In theory, this   
   kind of approach could derive unconventional “rules” that could make   
   headway on problems that    
   are currently unsolvable."   
      
   https://www.quantamagazine.org/symbolic-mathematics-finally-yiel   
   s-to-neural-networks-20200520/   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)