Sentinel gate for modulating auxiliary information in a long short-term memory (lstm) neural network
The technology disclosed presents a novel spatial attention model that uses current hidden
state information of a decoder long short-term memory (LSTM) to guide attention and to …
state information of a decoder long short-term memory (LSTM) to guide attention and to …
Spatial attention model for image captioning
The technology disclosed presents a novel spatial attention model that uses current hidden
state information of a decoder long short-term memory (LSTM) to guide attention and to …
state information of a decoder long short-term memory (LSTM) to guide attention and to …
Dense video captioning
Systems and methods for dense captioning of a video include a multi-layer encoder stack
configured to receive information extracted from a plurality of video frames, a proposal …
configured to receive information extracted from a plurality of video frames, a proposal …
Adaptive attention model for image captioning
The technology disclosed presents a novel spatial attention model that uses current hidden
state information of a decoder long short-term memory (LSTM) to guide attention and to …
state information of a decoder long short-term memory (LSTM) to guide attention and to …
Natural language processing using a neural network
A system includes a neural network for performing a first natural language processing task.
The neural network includes a first rectifier linear unit capable of executing an activation …
The neural network includes a first rectifier linear unit capable of executing an activation …
Natural language processing using context specific word vectors
A system is provided for natural language processing. In some embodiments, the system
includes an encoder for generating context-specific word vectors for at least one input …
includes an encoder for generating context-specific word vectors for at least one input …
Block-diagonal hessian-free optimization for recurrent and convolutional neural networks
Embodiments for training a neural network are provided. A neural network is divided into a
first block and a second block, and the parameters in the first block and second block are …
first block and a second block, and the parameters in the first block and second block are …
Question answering from minimal context over documents
A natural language processing system that includes a sen tence selector and a question
answering module. The sen tence selector receives a question and sentences that are …
answering module. The sen tence selector receives a question and sentences that are …
Systems and methods for learning for domain adaptation
A method for training parameters of a first domain adaptation model includes evaluating a
cycle consistency objective using a first task specific model associated with a first domain …
cycle consistency objective using a first task specific model associated with a first domain …
Unsupervised non-parallel speech domain adaptation using a multi-discriminator adversarial network
A system for domain adaptation includes a domain adaptation model configured to adapt a
representation of a signal in a first domain to a second domain to generate an adapted …
representation of a signal in a first domain to a second domain to generate an adapted …