Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units

摘要

There has been a lot of interest in the use of discrete-time recurrent neu- ral nets (DTRNN) to learn finite-state tasks, with interesting results re- garding the induction of simple finite-state machines from input-output strings. Parallel work has studied the computational power of DTRNN in connection with finite-state computation.