Author: Martino Russi

Martino Russi is a ML engineer who holds a master’s degree in AI from the University of Sussex. He has a keen interest for reinforcement learning, computer vision and human-computer interaction. He is currently researching unsupervised reinforcement learning and developing low-cost, high-dimensional control interfaces for robotics

Latest Natural Language Generation Research Introduces ‘Typical Sampling,’ A New Decoding Method that is Principled, Effective, and can be Implemented Efficiently

Natural language models can model a text corpus C by learning the probability distribution p over all natural language strings Y∈C, with Y={y_1,y_2,y_3...,y_t}. For...