Abstract: Systems, apparatuses, and methods for efficiently and accurately processing an image in order to detect and identify one or more objects contained in the image, and methods that may be implemented on mobile or other resource constrained devices. Embodiments of the invention introduce simple, efficient, and accurate approximations to the functions performed by a convolutional neural network (CNN); this is achieved by binarization (i.e., converting one form of data to binary values) of the weights and of the intermediate representations of data in a convolutional neural network. The inventive binarization methods include optimization processes that determine the best approximations of the convolution operations that are part of implementing a CNN using binary operations.

Abstract: Systems, apparatuses, and methods for representing words or phrases, and using the representation to perform NLP and NLU tasks, where these tasks include sentiment analysis, question answering, and conference resolution. Embodiments introduce a type of deep contextualized word representation that models both complex characteristics of word use, and how these uses vary across linguistic contexts. The word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. These representations can be added to existing task models and significantly improve the state of the art across challenging NLP problems, including question answering, textual entailment and sentiment analysis.