International Business Machines Corporation

Kothagorla Lakshmana Rao

Sathya Santhar

Sridevi Kannan

Suvedhahari Velusamy

Samuel Mathew Jawaharlal

A method, computer program product, and computer system for predicting a class of a given input to multiple models. Class parameters of the models are received. A process that predicts the class of a given input to the models is performed using the class parameters of the models. The process is (i) a model ensemble process predicting that the class of the given input is a class that maximizes a function of class accuracy parameters selected from combinations of the class parameters, (ii) a first threshold process based on a requirement that the class of the given input be predicted by running a model whose class accuracy parameter is at least a specified threshold, or (iii) a second threshold process based on a requirement that a specified class be predicted by a running of all models whose class accuracy parameter is at least the specified threshold.

Class prediction based on class accuracy of multiple models

A computer-implemented method according to one embodiment includes causing an environment generator of a Generative Adversarial Network (GAN) to generate realistic training environments, and causing a first discriminator of the GAN to determine whether the realistic training environments are real or fake. In response to a determination that an accuracy of the first discriminator at determining whether the realistic training environments are real or fake is within a predetermined range, the environment generator is caused to generate a first realistic environment. The method further includes causing the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator, and receiving, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment. The environment generator is caused to generate a second realistic environment based on the feedback associated with the first realistic environment.

Training an environment generator of a generative adversarial network (GAN) to generate realistic environments that incorporate reinforcement learning (RL) algorithm feedback

A method, computer program product, and computer system for translating, using a beam search, a source sentence in a source language into a target sentence in a target language by an iterative process. Each iteration of the iterative process includes: generating, using a sequence-to-sequence model, probability vectors of conditional probabilities of respective vocabulary words in the target language being translations of a source word in the source sentence; sorting the probabilities in the probability vectors; generating probability difference vectors containing numerical differences between adjacent elements in respective sorted probability; vectors determining, by a fully connected neural network (FCNN), a best beam width B using the probability difference vectors as input to the FCNN; selecting B vocabulary words and B target vectors corresponding to the B highest conditional probabilities; and after all words in the source sentence have been translated, outputting the B target vectors generated in the last iteration.

Growing community of inventors

Chirala, India

Kothagorla Lakshmana Rao