3 papers
cs.CL2018
Modeling natural language emergence with integral transform theory and reinforcement learning
Bohdan Khomtchouk, Shyam Sudhakaran
Zipf's law predicts a power-law relationship between word rank and frequency in language communication systems and has been widely reported in a variety of natural language process…
cs.LG2018
Polynomial Regression As an Alternative to Neural Nets
Xi Cheng, Bohdan Khomtchouk, Norman Matloff +1
Despite the success of neural networks (NNs), there is still a concern among many over their "black box" nature. Why do they work? Here we present a simple analytic argument that N…
physics.soc-ph2016
Zipf's law emerges asymptotically during phase transitions in communicative systems
Bohdan B. Khomtchouk, Claes Wahlestedt
Zipf's law predicts a power-law relationship between word rank and frequency in language communication systems, and is widely reported in texts yet remains enigmatic as to its orig…